Article(id=1266471245261459555, tenantId=1146029695717560320, journalId=1266358635761254452, issueId=1266471145588019694, articleNumber=null, orderNo=null, doi=10.11884/HPLPB202638.250370, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1761580800000, receivedDateStr=2025-10-28, revisedDate=1767024000000, revisedDateStr=2025-12-30, acceptedDate=1767024000000, acceptedDateStr=2025-12-30, onlineDate=1779879874767, onlineDateStr=2026-05-27, pubDate=1776182400000, pubDateStr=2026-04-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1779879874767, onlineIssueDateStr=2026-05-27, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1779879874767, creator=13701087609, updateTime=1779879874767, updator=13701087609, issue=Issue{id=1266471145588019694, tenantId=1146029695717560320, journalId=1266358635761254452, year='2026', volume='38', issue='4', pageStart='041001-1', pageEnd='049003-11', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1779879851004, creator=13701087609, updateTime=1779879869427, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1266471222939374548, tenantId=1146029695717560320, journalId=1266358635761254452, issueId=1266471145588019694, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1266471222943568853, tenantId=1146029695717560320, journalId=1266358635761254452, issueId=1266471145588019694, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=041001-1, endPage=041001-11, ext={EN=ArticleExt(id=1266471245534089318, articleId=1266471245261459555, tenantId=1146029695717560320, journalId=1266358635761254452, language=EN, title=Laser self-mixing interference micro displacement reconstruction based on convolutional neural network, columnId=1266471245458591845, journalTitle=High Power Laser and Particle Beams, columnName=High Power Laser Physics and Technology, runingTitle=null, highlight=null, articleAbstract=
Background

Laser self-mixing interferometry (SMI) is a highly sensitive and non-contact technique widely used for micro-displacement measurement. However, traditional displacement reconstruction methods typically involve complex phase unwrapping calculations, which increases computational difficulty and limits the efficiency of signal processing in practical applications.

Purpose

This study aims to propose a novel micro-displacement reconstruction method for semiconductor laser SMI based on convolutional neural networks (CNN). The objective is to achieve direct and accurate reconstruction of micron-scale displacement while bypassing the tedious phase unwrapping process.

Methods

The proposed method involves segmenting the SMI signal and using the window-averaged displacement as the label for training the CNN. The architecture of the network consists of three sets of convolutional layers, pooling layers, and Rectified Linear Unit (ReLU) functions. Specifically, the convolutional layers are utilized to extract local displacement features from the SMI signal, the pooling layers are designed to compress feature information and enhance noise immunity, and the ReLU functions help highlight critical displacement features within the signal.

Results

In theoretical simulations, SMI signals with 10 dB noise were input into the trained CNN, resulting in a displacement reconstruction RMSE of 5.3 × 108. In experimental tests, SMI signals containing system noise were processed by the network, yielding a reconstructed displacement RMSE of 2.1 × 107. The simulation and experimental results demonstrate consistent performance.

Conclusions

Both theoretical and experimental results indicate that the convolutional neural network can effectively achieve micron-level displacement reconstruction by analyzing the temporal segments of SMI signals. This method provides an efficient alternative for semiconductor laser self-mixing interference systems by eliminating the need for complex phase-based algorithms.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 High Power Laser and Particle Beams. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Xintao Li, Hui Liu, Shuo Qiao, Yifan Yang, Yang Lv, Xia Liu, Lingling Xiong), CN=ArticleExt(id=1266471261732491465, articleId=1266471245261459555, tenantId=1146029695717560320, journalId=1266358635761254452, language=CN, title=基于卷积神经网络的激光自混合干涉微位移重构, columnId=1266471245617975399, journalTitle=强激光与粒子束, columnName=强激光物理与技术, runingTitle=null, highlight=null, articleAbstract=

提出了一种基于卷积神经网络(CNN)的半导体激光自混合干涉(SMI)微位移重构方法,将SMI信号分段并以窗口平均位移作为标签输入卷积神经网络,实现了物体微米量级位移的直接重构,避免了位移重构过程中复杂的SMI信号相位解包裹计算过程。所使用的卷积神经网络由三组卷积层、池化层和线性整流函数组成,其中卷积层用于提取SMI信号中的局部位移特征,池化层用于压缩SMI信号中的特征信息并增强抗干扰能力,线性整流函数有助于突出SMI信号中的关键位移特征。在理论仿真中,将具有10 dB噪声的SMI信号输入至已训练完成的卷积神经网络中,直接输出物体重构微位移的均方根误差为$ 5.3\times {10}^{-8}$;在实验中,将包含系统噪声的SMI信号输入已训练完成的卷积神经网络中,直接输出物体重构微位移的均方根误差为$ 2.1\times {10}^{-7} $。理论仿真与实际实验结果均表明,卷积神经网络通过分析SMI信号的时序片段,能够实现半导体激光自混合干涉信号的微米量级位移重构。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
刘晖,
, copyrightStatement=版权所有 © 《强激光与粒子束》编辑部 2026, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=V03o0STT8/PTYp8Oeculxg==, magXml=vznhg2zn5SFGFzkollFuKQ==, pdfUrl=null, pdf=Po/uqC387XYrYKwgZ2W4AA==, pdfFileSize=2977358, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=HndUVzNKDiV9geoSZa2CFg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=Mee3GSAtVp3hcJxLrzQMag==, mapNumber=null, authorCompany=null, fund=null, authors=

李鑫涛,

, authorsList=李鑫涛, 刘晖, 乔硕, 杨一帆, 吕杨, 刘霞, 熊玲玲)}, authors=[Author(id=1266743816297013463, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=230221119@stu.xpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1266743816376705241, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743816297013463, language=EN, stringName=Xintao Li, firstName=Xintao, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1266743816615780570, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743816297013463, language=CN, stringName=李鑫涛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安工程大学 机电工程学院,西安 710048, bio={"content":"

李鑫涛,

"}, bioImg=null, bioContent=

李鑫涛,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1266743816196350163, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, xref=null, ext=[AuthorCompanyExt(id=1266743816204738772, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China), AuthorCompanyExt(id=1266743816217321685, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安工程大学 机电工程学院,西安 710048)])]), Author(id=1266743816708055260, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=huiliu@xpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1266743817119097054, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743816708055260, language=EN, stringName=Hui Liu, firstName=Hui, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1266743817471418591, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743816708055260, language=CN, stringName=刘晖, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安工程大学 机电工程学院,西安 710048, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1266743816196350163, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, xref=null, ext=[AuthorCompanyExt(id=1266743816204738772, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China), AuthorCompanyExt(id=1266743816217321685, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安工程大学 机电工程学院,西安 710048)])]), Author(id=1266743817542721761, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1266743817928597731, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743817542721761, language=EN, stringName=Shuo Qiao, firstName=Shuo, middleName=null, lastName=Qiao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1266743818306085092, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743817542721761, language=CN, stringName=乔硕, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安工程大学 机电工程学院,西安 710048, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1266743816196350163, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, xref=null, ext=[AuthorCompanyExt(id=1266743816204738772, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China), AuthorCompanyExt(id=1266743816217321685, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安工程大学 机电工程学院,西安 710048)])]), Author(id=1266743818696155366, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1266743818801012968, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743818696155366, language=EN, stringName=Yifan Yang, firstName=Yifan, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1266743819287552233, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743818696155366, language=CN, stringName=杨一帆, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安工程大学 机电工程学院,西安 710048, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1266743816196350163, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, xref=null, ext=[AuthorCompanyExt(id=1266743816204738772, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China), AuthorCompanyExt(id=1266743816217321685, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安工程大学 机电工程学院,西安 710048)])]), Author(id=1266743819551793387, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1266743819988001005, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743819551793387, language=EN, stringName=Yang Lv, firstName=Yang, middleName=null, lastName=Lv, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1266743820050915566, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743819551793387, language=CN, stringName=吕杨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安工程大学 机电工程学院,西安 710048, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1266743816196350163, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, xref=null, ext=[AuthorCompanyExt(id=1266743816204738772, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China), AuthorCompanyExt(id=1266743816217321685, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安工程大学 机电工程学院,西安 710048)])]), Author(id=1266743820440985840, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1266743820801695986, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743820440985840, language=EN, stringName=Xia Liu, firstName=Xia, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1266743820910747891, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743820440985840, language=CN, stringName=刘霞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安工程大学 机电工程学院,西安 710048, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1266743816196350163, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, xref=null, ext=[AuthorCompanyExt(id=1266743816204738772, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China), AuthorCompanyExt(id=1266743816217321685, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安工程大学 机电工程学院,西安 710048)])]), Author(id=1266743821242097909, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1266743821640556791, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743821242097909, language=EN, stringName=Lingling Xiong, firstName=Lingling, middleName=null, lastName=Xiong, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1266743821741220088, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, authorId=1266743821242097909, language=CN, stringName=熊玲玲, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安工程大学 机电工程学院,西安 710048, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1266743816196350163, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, xref=null, ext=[AuthorCompanyExt(id=1266743816204738772, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China), AuthorCompanyExt(id=1266743816217321685, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安工程大学 机电工程学院,西安 710048)])])], keywords=[Keyword(id=1266743822173233401, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, orderNo=1, keyword=laser self-mixing interference), Keyword(id=1266743822538137850, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, orderNo=2, keyword=displacement reconstruction), Keyword(id=1266743822630412539, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, orderNo=3, keyword=convolutional neural network), Keyword(id=1266743822907236604, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, orderNo=4, keyword=feature extraction), Keyword(id=1266743823309889789, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, orderNo=5, keyword=semiconductor laser), Keyword(id=1266743823389581566, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, orderNo=1, keyword=激光自混合干涉), Keyword(id=1266743823746097407, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, orderNo=2, keyword=微位移重构), Keyword(id=1266743823804817664, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, orderNo=3, keyword=卷积神经网络), Keyword(id=1266743824169722113, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, orderNo=4, keyword=特征提取), Keyword(id=1266743824270385410, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, orderNo=5, keyword=半导体激光器)], refs=[Reference(id=1266743827432890655, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Changying, Wang Qi. Laser self-mixing interference displacement signal filtering method based on empirical mode decomposition and wavelet threshold[J]. Measurement Science and Technology, 2024, 35: 045201., articleTitle=null, refAbstract=null), Reference(id=1266743827504193824, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Qinyu, Li Quan, Wei Xia, et al. Laser self-mixing interferometry for direct displacement reconstruction using deep learning[J]. Optics & Laser Technology, 2025, 192: 113423., articleTitle=null, refAbstract=null), Reference(id=1266743827567108385, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Hui, Li Xintao, You Yaqiang, et al. Wiener filtering in wavelet domain on laser self-mixing interference for micro-displacement reconstruction[J]. Photonics, 2025, 12: 40., articleTitle=null, refAbstract=null), Reference(id=1266743827663577378, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Skripal A V, Dobdin S Y, Inkin M G, et al. Measurement of distance by the maximum frequency of the interference signal with harmonic deviation of the wavelength of the self-mixing laser[J]. Technical Physics, 2024, 69(5): 1400-1406., articleTitle=null, refAbstract=null), Reference(id=1266743827755852067, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=曹雪, 冯立娜, 王秀芳, 等. 基于差分的激光自混合光栅干涉位移测量[J]. 吉林大学学报(信息科学版), 2023, 41(4): 583-589, articleTitle=null, refAbstract=null), Reference(id=1266743827885875492, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Cao Xue, Feng Lina, Wang Xiufang, et al. Displacement measurement of self-mixing grating interferometer based on difference[J]. Journal of Jilin University (Information Science Edition), 2023, 41(4): 583-589, articleTitle=null, refAbstract=null), Reference(id=1266743827965567269, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=张玉杰, 徐雷, 管钰晴, 等. 基于平面反射式全息光栅的激光自混合纳米位移测量研究[J]. 红外与激光工程, 2023, 52: 20220676, articleTitle=null, refAbstract=null), Reference(id=1266743828041064742, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Yujie, Xu Lei, Guan Yuqing, et al. Research on laser self-mixing Nano-displacement measurement based on plane reflective holographic grating[J]. Infrared and Laser Engineering, 2023, 52: 20220676, articleTitle=null, refAbstract=null), Reference(id=1266743828108173607, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=彭婉妮, 牛海莎, 潘雨婷, 等. 基于全光纤激光自混合干涉技术的石英玻璃热光系数测量[J]. 光电子·激光, 2022, 33(6): 578-584, articleTitle=null, refAbstract=null), Reference(id=1266743828166893864, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Peng Wanni, Niu Haisha, Pan Yuting, et al. Measurement of thermo-optical coefficient of quartz glass based on all-fiber laser self-mixing interference technology[J]. Journal of Optoelectronics·Laser, 2022, 33(6): 578-584, articleTitle=null, refAbstract=null), Reference(id=1266743828242391337, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=张晨, 陈涛, 赵宇. 基于激光自混合干涉技术的单个微纳颗粒探测[J]. 激光与光电子学进展, 2020, 57: 192803, articleTitle=null, refAbstract=null), Reference(id=1266743828317888810, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Chen, Chen Tao, Zhao Yu. Single micro-Nano particle detection based on laser self-mixing interference technology[J]. Laser & Optoelectronics Progress, 2020, 57: 192803, articleTitle=null, refAbstract=null), Reference(id=1266743828376609067, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=蔡家轩, 楚卫东. 基于THz-QCL自混合干涉的运动传感[J]. 太赫兹科学与电子信息学报, 2022, 20(10): 985-990, articleTitle=null, refAbstract=null), Reference(id=1266743828439523628, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Jiaxuan, Chu Weidong. Motion sensing based on Self-Mixing interferometry with THz-QCL[J]. Journal of Terahertz Science and Electronic Information Technology, 2022, 20(10): 985-990, articleTitle=null, refAbstract=null), Reference(id=1266743828506632493, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Lian, Yang Yu, Liu Bin, et al. Laser self-mixing interference: optical fiber coil sensors for acoustic emission detection[J]. Photonics, 2023, 10: 958., articleTitle=null, refAbstract=null), Reference(id=1266743828603101486, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Xie Yan, Wang Yingxin, Li Lianhe, et al. Realization of high depth resolution using two-beam self-mixing interferometry with a terahertz quantum cascade laser[J]. Optics Communications, 2023, 545: 129737., articleTitle=null, refAbstract=null), Reference(id=1266743828670210351, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Jha A, Cenkeramaddi L R, Royo S. Generalized multi-cavity laser self-mixing interferometry based on scattering theory[J]. Optics Express, 2023, 31(10): 16508-16522., articleTitle=null, refAbstract=null), Reference(id=1266743828741513520, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Hui, You Yaqiang, Li Sijia, et al. Denoising of laser self-mixing interference by improved wavelet threshold for high performance of displacement reconstruction[J]. Photonics, 2023, 10: 943., articleTitle=null, refAbstract=null), Reference(id=1266743828812816689, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=尤亚强, 李鑫涛, 刘晖, 等. 基于小波阈值滤波和S-G滤波相结合的激光自混合干涉微位移重构[J]. 强激光与粒子束, 2024, 36: 081002, articleTitle=null, refAbstract=null), Reference(id=1266743828930257202, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=You Yaqiang, Li Xintao, Liu Hui, et al. Micro displacement reconstruction of laser self mixing interference based on wavelet threshold filtering and S-G filtering[J]. High Power Laser and Particle Beams, 2024, 36: 081002, articleTitle=null, refAbstract=null), Reference(id=1266743829009948979, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=吴军, 陈杨, 赵君伟, 等. 基于激光自混合原理的涡轮叶片转速与叶尖间隙动态同步测量方法[J]. 仪器仪表学报, 2023, 44(11): 13-21, articleTitle=null, refAbstract=null), Reference(id=1266743829072863540, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Jun, Chen Yang, Zhao Junwei, et al. Dynamic synchronous measurement method of turbine blade speed and blade tip clearance based on laser self-mixing principle[J]. Chinese Journal of Scientific Instrument, 2023, 44(11): 13-21, articleTitle=null, refAbstract=null), Reference(id=1266743829131583797, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=韩玉祥, 丛至诚, 高丙坤, 等. 基于激光自混合干涉调频信号的位移测量实验[J]. 激光与红外, 2022, 52(5): 695-699, articleTitle=null, refAbstract=null), Reference(id=1266743829198692662, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Han Yuxiang, Cong Zhicheng, Gao Bingkun, et al. Displacement measurement experiment based on laser self mixing interference frequency modulation signal[J]. Laser & Infrared, 2022, 52(5): 695-699, articleTitle=null, refAbstract=null), Reference(id=1266743829257412919, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Yan, Zhang Baofeng, Han Lianfu. Laser self-mixing interference displacement measurement based on VMD and phase unwrapping[J]. Optics Communications, 2020, 456: 124588., articleTitle=null, refAbstract=null), Reference(id=1266743829353881912, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=樊毓臻, 寇科, 王晛, 等. 线性调频激光自混合干涉双通道微位移测量方法研究[J]. 仪器仪表学报, 2023, 44(10): 22-29, articleTitle=null, refAbstract=null), Reference(id=1266743829425185081, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Fan Yuzhen, Kou Ke, Wang Xian, et al. Study on the dual-channel displacement measurement method using linearly tuned laser self-mixing interference[J]. Chinese Journal of Scientific Instrument, 2023, 44(10): 22-29, articleTitle=null, refAbstract=null), Reference(id=1266743829500682554, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Yidan, Lai Wenzong, Chen Enguo. Displacement sensing for laser self-mixing interferometry by amplitude modulation and integral reconstruction[J]. Sensors, 2024, 24: 3785., articleTitle=null, refAbstract=null), Reference(id=1266743829588762939, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Awad A, Eldosoky M A A, Soliman A M, et al. Automatic diagnosis of hyperkinetic dysphonia from speech recordings based on deep learning approaches[J]. Engineering Research Express, 2025, 7: 035263., articleTitle=null, refAbstract=null), Reference(id=1266743829710397756, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Ying, Xue Jiahao, Li Daxiang, et al. Image recognition based on lightweight convolutional neural network: recent advances[J]. Image and Vision Computing, 2024, 146: 105037., articleTitle=null, refAbstract=null), Reference(id=1266743829773312317, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Farajollahi A, Fakhrabadi M M S. Convolutional neural networks to predict dispersion surfaces-based properties of acoustic metamaterials with arbitrary-shaped unit cells[J]. Results in Engineering, 2025, 26: 104905., articleTitle=null, refAbstract=null), Reference(id=1266743829836226878, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Novac P E, Rodriguez L, Barland S. Integrating embedded neural networks and self-mixing interferometry for smart sensors design[C]//2024 IEEE Sensors Applications Symposium (SAS). 2024: 1-6., articleTitle=null, refAbstract=null), Reference(id=1266743829894947135, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=An Lei, Liu Bin. Measuring parameters of laser self-mixing interferometry sensor based on back propagation neural network[J]. Optics Express, 2022, 30(11): 19134-19144., articleTitle=null, refAbstract=null), Reference(id=1266743829949473088, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Siddiqui A A, Zabit U, Bernal O D. Fringe detection and displacement sensing for variable optical feedback-based self-mixing interferometry by using deep neural networks[J]. Sensors, 2022, 22: 9831., articleTitle=null, refAbstract=null), Reference(id=1266743830003999041, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Sawada A, Miyagawa T, Ebihara A, et al. Convolutional neural networks for time-dependent classification of variable-length time series[C]//Proceedings of the 2022 International Joint Conference on Neural Networks (IJCNN). 2022: 1-8., articleTitle=null, refAbstract=null), Reference(id=1266743830062719298, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Chagnon J, Hagenbuchner M, Tsoi A C, et al. On the effects of recursive convolutional layers in convolutional neural networks[J]. Neurocomputing, 2024, 591: 127767., articleTitle=null, refAbstract=null), Reference(id=1266743830142411075, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Walter B. Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling[J]. Journal of Statistical Planning and Inference, 2023, 224: 109-126., articleTitle=null, refAbstract=null), Reference(id=1266743830230491460, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Bin, Ruan Yuxi, Yu Yanguang. Determining system parameters and target movement directions in a laser self-mixing interferometry sensor[J]. Photonics, 2022, 9: 612., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1266743816196350163, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, xref=null, ext=[AuthorCompanyExt(id=1266743816204738772, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China), AuthorCompanyExt(id=1266743816217321685, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, companyId=1266743816196350163, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安工程大学 机电工程学院,西安 710048)])], figs=[ArticleFig(id=1266743824996000003, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.1, caption=Convolutional neural network architecture. SMI: laser self-mixing interferometry; ReLU: rectified linear unit, figureFileSmall=1Wa9f4cBh/5STdtMomT7MA==, figureFileBig=5B+xjuGgdTDZb0l4hI4KHw==, tableContent=null), ArticleFig(id=1266743825084080388, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图1, caption=卷积神经网络的网络架构(SMI: 激光自混合干涉;ReLU: 线性整流函数), figureFileSmall=1Wa9f4cBh/5STdtMomT7MA==, figureFileBig=5B+xjuGgdTDZb0l4hI4KHw==, tableContent=null), ArticleFig(id=1266743825193132293, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.2, caption=Schematic of the sliding time windows, figureFileSmall=rwTGTP4TOwuil3k01IHMDw==, figureFileBig=c4p3WaKpx2xR0H0VPHmnvA==, tableContent=null), ArticleFig(id=1266743825281212678, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图2, caption=卷积神经网络的网络滑动时间窗示意图, figureFileSmall=rwTGTP4TOwuil3k01IHMDw==, figureFileBig=c4p3WaKpx2xR0H0VPHmnvA==, tableContent=null), ArticleFig(id=1266743825352515847, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.3, caption=Three feature activations of the convolutional layers, figureFileSmall=4kxRsbpoIsK+BZV//wcrHA==, figureFileBig=Ip9gRWzWsGLHi95clSABjA==, tableContent=null), ArticleFig(id=1266743825432207624, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图3, caption=三层卷积层特征提取图, figureFileSmall=4kxRsbpoIsK+BZV//wcrHA==, figureFileBig=Ip9gRWzWsGLHi95clSABjA==, tableContent=null), ArticleFig(id=1266743825495122185, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.4, caption=Simulated vibration displacement of the object and corresponding SMI signals, figureFileSmall=c2C7yscKrpPJlbEXcRdggw==, figureFileBig=9FvygFi5E4BWZYE0eWzZGw==, tableContent=null), ArticleFig(id=1266743825574813962, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图4, caption=模拟物体的振动位移和对应的SMI信号, figureFileSmall=c2C7yscKrpPJlbEXcRdggw==, figureFileBig=9FvygFi5E4BWZYE0eWzZGw==, tableContent=null), ArticleFig(id=1266743825641922827, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.5, caption=Simulated SMI signals and reconstructed displacement results of the CNN training set, figureFileSmall=asf1tVzKlGzIq0gJbA8FdQ==, figureFileBig=8Kq1xacq1d+4PPfUeVwbUA==, tableContent=null), ArticleFig(id=1266743825704837388, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图5, caption=卷积神经网络训练集的SMI模拟信号与重构结果, figureFileSmall=asf1tVzKlGzIq0gJbA8FdQ==, figureFileBig=8Kq1xacq1d+4PPfUeVwbUA==, tableContent=null), ArticleFig(id=1266743825792917773, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.6, caption=Simulated SMI signals and reconstructed displacement results of the CNN testing set, figureFileSmall=yS2nqd0j1M6L6MokCjcHMg==, figureFileBig=/wHFUFc8M2+TtAA3vYj0Fw==, tableContent=null), ArticleFig(id=1266743825855832334, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图6, caption=卷积神经网络测试集的SMI模拟信号与重构结果, figureFileSmall=yS2nqd0j1M6L6MokCjcHMg==, figureFileBig=/wHFUFc8M2+TtAA3vYj0Fw==, tableContent=null), ArticleFig(id=1266743825939718415, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.7, caption=Scatter plots of regression fitting results of the convolutional neural network, figureFileSmall=hhHu06A9W9CkZ3Gvl5wm9A==, figureFileBig=R4HKYi0ohCBXxMc8pgarJg==, tableContent=null), ArticleFig(id=1266743826015215888, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图7, caption=卷积神经网络的回归拟合效果散点图, figureFileSmall=hhHu06A9W9CkZ3Gvl5wm9A==, figureFileBig=R4HKYi0ohCBXxMc8pgarJg==, tableContent=null), ArticleFig(id=1266743826099101969, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.8, caption=Schematic diagram of the experimental structure for laser self-mixing interference, figureFileSmall=45KEPX/leumAeryEO8vhbg==, figureFileBig=fNVwPYE3NPkxvei392mbng==, tableContent=null), ArticleFig(id=1266743826162016530, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图8, caption=激光自混合干涉实验结构示意图, figureFileSmall=45KEPX/leumAeryEO8vhbg==, figureFileBig=fNVwPYE3NPkxvei392mbng==, tableContent=null), ArticleFig(id=1266743826229125395, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.9, caption=Experimental setup for laser self-mixing interference, figureFileSmall=Xj/K+nj+0RIxOBSy32qW+Q==, figureFileBig=XCtf2Y7hRadIWi84P9ELrA==, tableContent=null), ArticleFig(id=1266743826380120340, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图9, caption=激光自混合干涉实验装置, figureFileSmall=Xj/K+nj+0RIxOBSy32qW+Q==, figureFileBig=XCtf2Y7hRadIWi84P9ELrA==, tableContent=null), ArticleFig(id=1266743826464006421, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.10, caption=Modulation voltage of PZT and experimental SMI signal, figureFileSmall=C3g7aq4JhqyGiaiKhCBAcw==, figureFileBig=d4UPankJidvvnKnxcplH0g==, tableContent=null), ArticleFig(id=1266743826556281110, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图10, caption=压电陶瓷的调制电压和实验SMI信号, figureFileSmall=C3g7aq4JhqyGiaiKhCBAcw==, figureFileBig=d4UPankJidvvnKnxcplH0g==, tableContent=null), ArticleFig(id=1266743826623389975, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.11, caption=Experimental SMI signals and normalized displacement reconstruction results of the CNN training set, figureFileSmall=QTYlGlV9TdQSWIPxXEoafg==, figureFileBig=F3iC39T1aIRaTP4fYEq8YQ==, tableContent=null), ArticleFig(id=1266743826690498840, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图11, caption=卷积神经网络训练集的SMI实验信号与归一化位移重构结果, figureFileSmall=QTYlGlV9TdQSWIPxXEoafg==, figureFileBig=F3iC39T1aIRaTP4fYEq8YQ==, tableContent=null), ArticleFig(id=1266743826753413401, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.12, caption=Experimental SMI signals and normalized displacement reconstruction results of the CNN testing set, figureFileSmall=JSEzokHJUG6zM/lhDJ/QfQ==, figureFileBig=7e4FKtPvjSWHAzw+dtJhCg==, tableContent=null), ArticleFig(id=1266743826828910874, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图12, caption=卷积神经网络测试集的SMI实验信号与归一化位移重构结果, figureFileSmall=JSEzokHJUG6zM/lhDJ/QfQ==, figureFileBig=7e4FKtPvjSWHAzw+dtJhCg==, tableContent=null), ArticleFig(id=1266743826963128603, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Fig.13, caption=Scatter plots of regression fitting results of the convolutional neural network, figureFileSmall=q0LHRq+E9d4tvfy7iLsB+w==, figureFileBig=YMx4j6p3+D9504k121DJHg==, tableContent=null), ArticleFig(id=1266743827076374812, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=图13, caption=卷积神经网络的回归拟合效果散点图, figureFileSmall=q0LHRq+E9d4tvfy7iLsB+w==, figureFileBig=YMx4j6p3+D9504k121DJHg==, tableContent=null), ArticleFig(id=1266743827156066589, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=EN, label=Table 1, caption=

Parameters used in numerical simulation

, figureFileSmall=null, figureFileBig=null, tableContent=
$ {{L}}_{{{\mathrm{ext}}}} $ (distance from the laser to the object)/mm $ {L} $ (cavity length of diode laser)/mmt (simulation time)/sA (vibration amplitude of external object)/$ \mu \mathrm{m} $
49.430.50.22
f (external object vibration frequency)/$ \mathrm{Hz} $ $ {\alpha } $ (linewidth enhancement factor)/C (feedback parameter)/ $ \lambda $ (wavelength of the laser diode)/nm
104.150.8635
), ArticleFig(id=1266743827273507102, tenantId=1146029695717560320, journalId=1266358635761254452, articleId=1266471245261459555, language=CN, label=表1, caption=

数值模拟中使用的参数

, figureFileSmall=null, figureFileBig=null, tableContent=
$ {{L}}_{{{\mathrm{ext}}}} $ (distance from the laser to the object)/mm $ {L} $ (cavity length of diode laser)/mmt (simulation time)/sA (vibration amplitude of external object)/$ \mu \mathrm{m} $
49.430.50.22
f (external object vibration frequency)/$ \mathrm{Hz} $ $ {\alpha } $ (linewidth enhancement factor)/C (feedback parameter)/ $ \lambda $ (wavelength of the laser diode)/nm
104.150.8635
)], attaches=null, journal=Journal(id=1266357945773080624, delFlag=0, nameCn=强激光与粒子束, nameEn=High Power Laser and Particle Beams, nameHistory1=null, nameHistory2=null, issn=1001-4322, eissn=null, cn=51-1311/O4, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=mmVSzpsbJpjM8AHqV4TWZw==, journalPrice=null, startedYear=null, abbrevIsoEn=High Power Laser and Particle Beams, journalRemark=null, publicationField=null, createdTime=1779852862067, updatedTime=1779853448289, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=H, firstLetterEn=H, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=mmVSzpsbJpjM8AHqV4TWZw==, picEn=l0y7ZNTRmMZ2CXsN3d9BHQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1266360404654580402, language=CN, name=强激光与粒子束, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1779853448308, updatedTime=1779853448308, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://manuscript.hplpb.com.cn/qjgylzs, submissionEditorUrl=http://manuscript.hplpb.com.cn/qjgylzs, submissionReviewUrl=http://manuscript.hplpb.com.cn/qjgylzs, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1266360404834935475, language=EN, name=High Power Laser and Particle Beams, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1779853448351, updatedTime=1779853448351, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://manuscript.hplpb.com.cn/qjgylzs, submissionEditorUrl=http://manuscript.hplpb.com.cn/qjgylzs, submissionReviewUrl=http://manuscript.hplpb.com.cn/qjgylzs, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1266358635761254452, websiteList=[Website(id=1266361614849692217, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1266358635761254452, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/qjgylzs/CN, language=CN, createTime=1779853736842, createBy=18614031015, updateTime=1779853814308, updateBy=18614031015, name=强激光与粒子束-中文, tplId=1146099689490845704, title=强激光与粒子束, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1266362063665386181, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361614849692217, code=articleTextType, value=kx, createTime=1779853843847, updateTime=1779853843847, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362063644414658, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361614849692217, code=banner, value=null, createTime=1779853843842, updateTime=1779853843842, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362063686357704, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361614849692217, code=grayFlag, value=0, createTime=1779853843852, updateTime=1779853843852, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362063640220353, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361614849692217, code=logo, value=https://castjournals.cast.org.cn/joweb/qjgylzs/CN/file/pic?fileId=EufB31AydCqs+AbRkXSL7g==, createTime=1779853843841, updateTime=1779853843841, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362063703134922, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361614849692217, code=minRunFlag, value=0, createTime=1779853843856, updateTime=1779853843856, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362063661191876, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361614849692217, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/qjgylzs/CN/file/pic, createTime=1779853843846, updateTime=1779853843846, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362063694746313, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361614849692217, code=silenceFlag, value=0, createTime=1779853843854, updateTime=1779853843854, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362063652803267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361614849692217, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1779853843844, updateTime=1779853843844, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362063673774790, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361614849692217, code=themeColor, value=null, createTime=1779853843849, updateTime=1779853843849, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362063677969095, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361614849692217, code=themeStyle, value=null, createTime=1779853843850, updateTime=1779853843850, creator=18614031015, updator=18614031015)]), Website(id=1266361615055213122, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1266358635761254452, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/qjgylzs/EN, language=EN, createTime=1779853736890, createBy=18614031015, updateTime=1779853809277, updateBy=18614031015, name=强激光与粒子束-英文, tplId=1146101810881728533, title=High Power Laser and Particle Beams, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1266362029007852215, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361615055213122, code=articleTextType, value=kx, createTime=1779853835584, updateTime=1779853835584, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362028986880692, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361615055213122, code=banner, value=null, createTime=1779853835579, updateTime=1779853835579, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362029028823738, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361615055213122, code=grayFlag, value=0, createTime=1779853835589, updateTime=1779853835589, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362028978492083, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361615055213122, code=logo, value=https://castjournals.cast.org.cn/joweb/qjgylzs/EN/file/pic?fileId=EufB31AydCqs+AbRkXSL7g==, createTime=1779853835577, updateTime=1779853835577, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362029045600956, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361615055213122, code=minRunFlag, value=0, createTime=1779853835593, updateTime=1779853835593, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362028999463606, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361615055213122, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/qjgylzs/EN/file/pic, createTime=1779853835582, updateTime=1779853835582, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362029037212347, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361615055213122, code=silenceFlag, value=0, createTime=1779853835591, updateTime=1779853835591, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362028991074997, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361615055213122, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1779853835580, updateTime=1779853835580, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362029012046520, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361615055213122, code=themeColor, value=null, createTime=1779853835585, updateTime=1779853835585, creator=18614031015, updator=18614031015), WebsiteProps(id=1266362029020435129, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1266361615055213122, code=themeStyle, value=null, createTime=1779853835587, updateTime=1779853835587, creator=18614031015, updator=18614031015)])], journalTitle=强激光与粒子束, weixinUrl=null, journalUrl=https://www.hplpb.com.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=High Power Laser and Particle Beams, journalPhotoCn=mmVSzpsbJpjM8AHqV4TWZw==, journalPhotoEn=l0y7ZNTRmMZ2CXsN3d9BHQ==, journalFirstLetter=H, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/qjgylzs/CN/10.11884/HPLPB202638.250370, detailUrlEn=https://castjournals.cast.org.cn/joweb/qjgylzs/EN/10.11884/HPLPB202638.250370, pdfUrlCn=https://castjournals.cast.org.cn/joweb/qjgylzs/CN/PDF/10.11884/HPLPB202638.250370, pdfUrlEn=https://castjournals.cast.org.cn/joweb/qjgylzs/EN/PDF/10.11884/HPLPB202638.250370, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于卷积神经网络的激光自混合干涉微位移重构
收藏切换
PDF下载
李鑫涛 , 刘晖 , 乔硕 , 杨一帆 , 吕杨 , 刘霞 , 熊玲玲
强激光与粒子束 | 强激光物理与技术 2026,38(4): 041001-1-041001-11
收起
收藏切换
强激光与粒子束 | 强激光物理与技术 2026, 38(4): 041001-1-041001-11
基于卷积神经网络的激光自混合干涉微位移重构
全屏
李鑫涛 , 刘晖 , 乔硕, 杨一帆, 吕杨, 刘霞, 熊玲玲
作者信息
  • 西安工程大学 机电工程学院,西安 710048

通讯作者:

刘晖,
Laser self-mixing interference micro displacement reconstruction based on convolutional neural network
Xintao Li , Hui Liu , Shuo Qiao, Yifan Yang, Yang Lv, Xia Liu, Lingling Xiong
Affiliations
  • School of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710048, China
出版时间: 2026-04-15 doi: 10.11884/HPLPB202638.250370
文章导航
收藏切换

提出了一种基于卷积神经网络(CNN)的半导体激光自混合干涉(SMI)微位移重构方法,将SMI信号分段并以窗口平均位移作为标签输入卷积神经网络,实现了物体微米量级位移的直接重构,避免了位移重构过程中复杂的SMI信号相位解包裹计算过程。所使用的卷积神经网络由三组卷积层、池化层和线性整流函数组成,其中卷积层用于提取SMI信号中的局部位移特征,池化层用于压缩SMI信号中的特征信息并增强抗干扰能力,线性整流函数有助于突出SMI信号中的关键位移特征。在理论仿真中,将具有10 dB噪声的SMI信号输入至已训练完成的卷积神经网络中,直接输出物体重构微位移的均方根误差为$ 5.3\times {10}^{-8}$;在实验中,将包含系统噪声的SMI信号输入已训练完成的卷积神经网络中,直接输出物体重构微位移的均方根误差为$ 2.1\times {10}^{-7} $。理论仿真与实际实验结果均表明,卷积神经网络通过分析SMI信号的时序片段,能够实现半导体激光自混合干涉信号的微米量级位移重构。

激光自混合干涉  /  微位移重构  /  卷积神经网络  /  特征提取  /  半导体激光器
Background

Laser self-mixing interferometry (SMI) is a highly sensitive and non-contact technique widely used for micro-displacement measurement. However, traditional displacement reconstruction methods typically involve complex phase unwrapping calculations, which increases computational difficulty and limits the efficiency of signal processing in practical applications.

Purpose

This study aims to propose a novel micro-displacement reconstruction method for semiconductor laser SMI based on convolutional neural networks (CNN). The objective is to achieve direct and accurate reconstruction of micron-scale displacement while bypassing the tedious phase unwrapping process.

Methods

The proposed method involves segmenting the SMI signal and using the window-averaged displacement as the label for training the CNN. The architecture of the network consists of three sets of convolutional layers, pooling layers, and Rectified Linear Unit (ReLU) functions. Specifically, the convolutional layers are utilized to extract local displacement features from the SMI signal, the pooling layers are designed to compress feature information and enhance noise immunity, and the ReLU functions help highlight critical displacement features within the signal.

Results

In theoretical simulations, SMI signals with 10 dB noise were input into the trained CNN, resulting in a displacement reconstruction RMSE of 5.3 × 108. In experimental tests, SMI signals containing system noise were processed by the network, yielding a reconstructed displacement RMSE of 2.1 × 107. The simulation and experimental results demonstrate consistent performance.

Conclusions

Both theoretical and experimental results indicate that the convolutional neural network can effectively achieve micron-level displacement reconstruction by analyzing the temporal segments of SMI signals. This method provides an efficient alternative for semiconductor laser self-mixing interference systems by eliminating the need for complex phase-based algorithms.

laser self-mixing interference  /  displacement reconstruction  /  convolutional neural network  /  feature extraction  /  semiconductor laser
李鑫涛, 刘晖, 乔硕, 杨一帆, 吕杨, 刘霞, 熊玲玲. 基于卷积神经网络的激光自混合干涉微位移重构. 强激光与粒子束, 2026 , 38 (4) : 041001-1 -041001-11 . DOI: 10.11884/HPLPB202638.250370
Xintao Li, Hui Liu, Shuo Qiao, Yifan Yang, Yang Lv, Xia Liu, Lingling Xiong. Laser self-mixing interference micro displacement reconstruction based on convolutional neural network[J]. High Power Laser and Particle Beams, 2026 , 38 (4) : 041001-1 -041001-11 . DOI: 10.11884/HPLPB202638.250370
随着科技的飞速发展,激光自混合干涉技术已经成为现代工程领域中不可或缺的重要手段[1-5]。在这项技术中,激光器发出的光束被外部物体反射后,再次进入激光器并与腔内的驻波自混合,引起激光输出功率的变化。进而通过观察输出波形即可获知被测物体运动状态。相比于传统测量方法,激光自混合技术具有高精度、高灵敏度、便于携带、非接触、耐受温度范围广等优势[6-11],所以其在微小振动测量、精密位移检测、航空航天等领域展现出巨大的应用潜力[12-15]
在实际应用中,研究者们更集中于提出提高SMI信号位移重构精度的方法[16-19]。东北石油大学的韩玉祥采用马赫-曾德尔干涉仪进行调幅/调频信号转换,利用多次希尔伯特变换进行相位解包裹,实现了SMI信号的位移重构[16]。天津理工大学的张宝峰提出了基于VMD与小波阈值的滤波方法,将SMI信号分解为k个固有模态函数(IMF),对IMF进行小波阈值处理并通过相位解包裹进行位移重构[17];西安理工大学寇科利用全相位谱分析法来估计SMI信号的相位,经过全相位谱处理,在频域中将呈现独立的谱峰,对反射物体进行谱峰搜索,来重构物体位移曲线[18];福州大学的陈恩果提出一种调幅积分重构方法,通过将SMI信号与一个高频正弦载波相乘,将SMI信号的频谱搬移到该载波的频谱上,最后通过同步挤压小波变换(SWT)进行时频变换后采用多普勒积分重建法重构目标位移[19]
这些方法虽然在一定程度上提高了位移重构的精度,但信号处理过程涉及多步操作,例如滤波、频谱分析、相位解包裹等,而每一步都会不可避免地削弱或丢失原始SMI信号中的特征信息。这导致在处理非平稳、噪声较大的SMI信号时存在特征提取有限、位移重构误差累计等问题。
近年来,卷积神经网络(CNN)因其强大的特征学习能力和端到端的建模优势,已在语音识别、图像识别、时序信号预测等诸多领域取得突破性进展[20-22]。在无需构造滤波器和特征提取函数的前提下,能够直接从SMI信号中提取位移信息特征[23-25]。法国蔚蓝海岸大学的PE Novac设计了一个基于SMI信号测量和嵌入神经网络的集成传感器模型,通过模数转换器和STM32l476RG微控制器实现对SMI信号的位移重建[23];湘潭大学的安磊提出了一种基于反向传播神经网络的激光自混合干涉传感器参数测量方法,用于同时估计光反馈因子和线宽增强因子,实现了在不同反馈强度下对SMI信号的参数预测与位移重构[24];法国图卢兹大学的Bernal设计了一种基于Yolov5神经网络的自动边缘标记方法,实现对SMI信号的位移重构[25]
上述研究采用整段SMI信号一次性训练的方法,而日本庆应义塾大学的Sawada等人的研究指出,若将长时序信号一次性输入卷积神经网络,会由于全局池化层忽略输入信号的时间顺序,导致CNN无法充分捕捉超过卷积层感受野范围的长时序信号特征的相关性[26]
本文提出一种通过将SMI信号分段并以窗口平均位移作为标签进行训练的方法,可以更精确地提取SMI信号特征,实现高精度位移重构。仿真实验表明,当输入信噪比为10 dB的SMI信号时,网络输出的位移重构信号均方根误差仅为$ 5.3\times {10}^{-8} $;实际实验中重构结果的最大误差为$ 2.1\times {10}^{-7} $
卷积神经网络结构包括卷积层、激活函数、池化层及全连接层。卷积层是CNN的算法核心,其主要功能是对输入信号进行局部区域特征提取[27]。一维卷积操作的数学表达式为
$ {y}_{i}=\displaystyle\sum \limits_{j=0}^{k-1}{x}_{i+j} {w}_{j}+b $
式中:$ {y}_{i} $表示输出序列中第i个位置的值;k表示卷积核的大小;j表示卷积核内部的索引(从0到k−1),即当前卷积窗口中的第j个元素;$ {x}_{i+j} $表示输入信号在第$ i+j $个位置的取值;$ {w}_{j} $为卷积核在第j个位置的权重;b为偏置项。该操作可实现特征在时间或空间维度上的局部提取,适用于非平稳信号分析。为了增强网络的非线性表达能力,卷积操作后引入ReLU(Rectified Linear Unit)激活函数处理。ReLU激活函数可有效缓解卷积神经网络训练过程中的梯度消失问题,并提升模型的训练效率和稳定性[27],定义为
$ {h}_{i}={\mathrm{ReLU}}\left({y}_{i}\right)=\mathrm{max} (0,{y}_{i}) $
式中:$ {h}_{i} $表示 ReLU函数激活的第i个输出。ReLU函数可有效避免梯度消失问题,提高深层网络的训练稳定性和计算效率。在卷积层与激活函数之后,网络配合最大池化层(Max Pooling) [27]进行下采样操作以降低特征图维度并减少参数数量,其表达式为
$ {Y}_{i}=\max\{{h}_{i,}{h}_{i+1},\cdots ,{h}_{i+p+1}\} $
式中:p表示池化窗口的大小;$ {Y}_{i} $为池化后的输出。
为了使 CNN 能够更准确地拟合输入与输出的映射关系,需要根据损失函数对每一个卷积层的参数计算梯度。通过梯度下降法,根据损失函数公式和参数更新公式计算更新后的wb的值。损失函数公式和参数更新公式定义为
$ \mathcal{L}=\dfrac{1}{N}\displaystyle\sum \limits_{i=1}^{N}{[f\left({x}_{i}\right)-{{y}_{i}}]}^{2} $
$ {w}_{{\mathrm{new}}}=w-\eta \Bigg(\dfrac{\partial \mathcal{L}}{\partial {w}_{{\mathrm{old}}}}\Bigg) $
$ {b}_{{\mathrm{new}}}=b-\eta \Bigg(\dfrac{\partial \mathcal{L}}{\partial {b}_{{\mathrm{old}}}}\Bigg) $
式中:$ \mathcal{L} $为损失函数的值;N为训练样本总数;$ f(x) $表示卷积神经网络输出函数;$ {w}_{{\mathrm{new}}} $$ {b}_{{\mathrm{new}}} $为更新后的卷积核权重和偏置项,$ \eta $表示梯度下降法中控制参数的学习率。
在卷积层、激活函数与池化层提取到的特征基础上,CNN通过全连接层将特征信息映射到输出空间,实现对输出波形的最终预测。全连接层的数学表达式为
$ {Z}_{i}=\displaystyle\sum \limits_{q=1}^{M}{W}_{iq}{Y}_{q}+b $
式中:M表示池化层输出特征的总数;q表示全连接层输入特征的索引,对应池化层输出的每个特征值;$ {W}_{iq} $表示第i个输出节点与第q个输入特征的权重;$ {Y}_{q} $表示池化层输出的第q个特征;$ {Z}_{i} $表示全连接层的第i个输出。
在激光自混合干涉微位移测量中,原始SMI信号通常表现出非线性、非平稳和周期性模糊等复杂特性。传统滤波方法难以对其特征进行全面建模,而CNN具备从原始数据中自动学习特征表示的能力,可构建从SMI信号到微位移波形的非线性映射模型。相比手工提取特征的方法,CNN在面对SMI信号复杂的噪声干扰时表现出更好的稳定性。本文提出的微位移重构方法基于一维卷积神经网络,以原始SMI信号作为输入,输出对应的重构位移。
卷积神经网络由三组卷积层、池化层和ReLU函数构成,如图1所示。三层卷积结构能够在保证模型复杂度适中的前提下,逐级提取特征信息。更浅的网络结构会导致特征提取能力不足,而更深的网络在本文任务规模下并未带来明显性能提升,反而增加了过拟合风险[26]。卷积层通过局部感知机制提取SMI信号的时域特征:为了防止网络初始阶段提取噪声的无关细节导致过拟合,第一层卷积使用16个卷积核,作用于原始SMI信号,主要用于提取自混合干涉条纹波形峰谷值的局部特征;第二层卷积采用32个卷积核,在保持计算效率的同时,进一步提取相邻干涉条纹在幅值、间隔和形态上与振动位移的相关性;第三层卷积设置64个卷积核以提高卷积神经网络在深层对复杂特征的提取能力,结合前两层的特征,学习SMI信号在一个时间窗内整体变化趋势对振动位移的影响。三层池化层在各阶段对特征进行降采样与压缩。最后输入全连接层,实现对位移信息的映射,最终输出对应的重构位移信号[28]
本文所使用的卷积神经网络模型以SMI信号上每200个相邻的采样点组成的一维序列作为输入,输出为该时间窗内对应的位移平均值。如图2所示,图2(a)为输入卷积神经网络的SMI信号,图中虚线框表示长度为200个采样点的时间窗,沿时间序列向右滑动;图2(b)为卷积神经网络输出的重构位移,图中虚线框表示图2(a)中对应时间窗内的平均位移。该模型充分利用卷积神经网络对局部特征的建模能力,可实现对高噪声、非平稳SMI信号中位移信息的有效提取。
为进一步展示各层卷积神经网络对SMI信号的特征提取效果,本文分别给出了三组卷积层输出的特征图,如图3所示。图3(a)图3(c)分别对应第一、第二和第三层卷积层的输出特征图,对应反映了卷积神经网络在不同卷积层逐步抽取局部细节、主要趋势及整体轮廓等时序特征。该特征图的逐层变化过程表明,卷积神经网络能够从复杂的SMI信号中逐步提取出有助于位移重构的时序特征。
图4(a)为模拟的物体振动的正弦位移曲线,其振幅为2 μm,周期为0.1 s。基于SMI理论模型[29],根据表1所示仿真参数模拟SMI信号,结果如图4(b)所示。其中虚线为时间间隔为0.05 s的分割线,在t等于0.05 s,0.10 s和0.15 s时刻处,物体振动方向发生变化。SMI信号每个周期内有16个波峰和16个波谷,可用半波长条纹计数法进行初步的位移重构,计算得到振幅约为1.96 μm。
为构建包含噪声干扰的SMI样本序列,把图4(b)所示的仿真SMI信号加入信噪比为10 dB的高斯白噪声,具有10 dB信噪比高斯白噪声的SMI信号如图4(c)所示。将图4(c)所示信号按时间序列划分为两个部分,前75%作为训练集用于模型训练(如图5(a)所示),代入式(1)中的$ {x}_{i} $,将图4(c)所示信号的前75%代入式(1)中的$ {y}_{i} $,由式(1)~式(7)训练出适用于图4(c)所示的含噪SMI信号的卷积神经网络。
将训练集输入已训练完成的卷积神经网络,得到的预测重构位移信号如图5(b)所示;同时,将图4(c)所示信号的后25%作为测试集(如图6(a)所示)输入卷积神经网络。图6(b)表示卷积神经网络在测试集上输出的预测位移信号。
为了进一步评估卷积神经网络对SMI信号微位移重构的整体拟合效果,图7展示了模型输出的预测值与仿真值的对应关系散点图。图中横坐标表示模型输出的重构位移值,纵坐标表示仿真重构位移值,虚线表示理想拟合线($ y=x $),用于参考预测值与仿真值的一致性。图7(a)为训练集的结果,图7(b)为测试集的结果。
图7中可以看出,散点在训练集与测试集中均紧密分布在理想的对角线附近,表明模型输出的预测位移与仿真位移之间具有较高的一致性。在训练集中,散点分布集中,几乎覆盖理想拟合线,说明卷积神经网络在学习阶段对输入的SMI信号的特征拟合程度较高。测试集中整体分布趋势仍保持良好,未出现明显离群点。
为了定量描述预测重构位移与仿真位移之间的偏离程度,本文采用均方根误差作为评价指标,均方根误差(RMSE)公式定义为
$ {\mathrm{RMSE}}=\sqrt{\dfrac{1}{N}\displaystyle\sum \limits_{i=1}^{N}{{{(H}_{i}}-{{y}_{i}})}^{2}} $
式中:$ {H}_{i} $i点处的预测重构位移值。计算得出,训练集重构位移的均方根误差为1.4×108,测试集重构位移的均方根误差为5.3×108。这表明卷积神经网络在训练与测试阶段对于SMI信号均能实现从整体趋势、波形细节及相位跳变点处的高精度拟合。
本文中的自混合干涉实验结构图如图8所示,其中PD为光电探测器,用于检测激光强度变化,r1r2分别表示激光器内腔的两个反射镜的反射率。从激光器内腔出射的激光经由外腔至压电陶瓷表面反射,反射光再沿原路返回至激光器内腔,光电探测器监测激光输出强度并经由跨阻放大器放大,数据采集卡采集信号并送至计算机。实验装置如图9所示,包含三个模块,分别为:模拟振动源、光束传输、数据采集。选用波长为650 nm的半导激光器作为光源,发射出的光被压电陶瓷(PZT)反射,使用压电控制器(Thorlabs KPZ101)驱动PZT产生微位移$ \Delta {L}_{{\mathrm{ext}}} $,激光二极管控制器(Thorlabs LDC205C)驱动电流用于设置半导体激光器工作电流,机械平台用于调节外腔长度,本实验外腔长度设置为49.4 mm。SMI信号经过电流-电压电路转换并放大,由数据采集卡(NI USB-6341)进行数据采集,最终在计算机上实时显示SMI信号波形。
PZT设定的调制电压如图10(a)所示,归一化后的实验SMI信号结果如图10(b)所示,受到了大量随机噪声干扰,在反馈光相位跳变点处噪声尤其明显。
图10(b)所示信号按时间序列划分为两个部分,前75%作为训练集用于模型训练(如图11(a)所示),代入式(1)中的$ {x}_{i} $,将图10(b)所示信号的前75%代入式(1)中的$ {y}_{i} $,由式(1)~式(7)训练出适用于图10(b)所示的实验SMI信号的卷积神经网络。
将训练集输入已训练完成的卷积神经网络,得到的预测重构位移信号如图11(b)所示;同时,将图10(b)所示信号的后25%作为测试集(如图12(a)所示)输入卷积神经网络。图12(b)表示卷积神经网络在测试集上输出的预测位移信号。
为了进一步评估卷积神经网络对SMI信号微位移重构的整体拟合效果,图13展示了模型输出的预测值与仿真值的对应关系散点图。图中横坐标表示模型输出的预测重构位移值,纵坐标表示归一化的PZT位移值,虚线表示理想拟合线($ y=x $),用于参考预测值与仿真值的一致性。图13(a)为训练集的结果,图13(b)为测试集的结果。
PZT驱动电压和PZT位移成正比,归一化PZT电压值和归一化PZT位移也成正比。从图中可以看出,散点在训练集与测试集中均紧密分布于理想的对角线上,说明卷积神经网络预测的归一化重构位移曲线能够很好地和真实的归一化PZT位移曲线吻合,进一步验证了模型在实验数据应用中的稳定性。由公式(8)计算得出,实验SMI信号的重构位移预测结果与调制电压之间的均方根误差为$ {2.1\times 10}^{-7} $
本文提出了一种基于卷积神经网络的激光自混合干涉信号微位移重构方法。该方法充分发挥了卷积神经网络在特征提取与建模方面的优势,舍弃了传统位移重构方法中复杂的步骤,可以直接从噪声干扰较强的SMI信号中准确还原物体振动位移信息。在仿真实验中,该方法在信噪比较低的条件下仍表现出较高的重构精度,重构微位移的均方根误差仅为$ 5.3\times {10}^{-8} $。在实际实验验证中,重构微位移的均方根误差为$ 2.1\times {10}^{-7} $。实验结果进一步表明,基于卷积神经网络的微位移重构算法在复杂条件下依然具备较高的精度,适用于噪声环境下的高精度微位移测量。
参考文献 引证文献
排序方式:
1
Guo Changying, Wang Qi. Laser self-mixing interference displacement signal filtering method based on empirical mode decomposition and wavelet threshold[J]. Measurement Science and Technology, 2024, 35: 045201.
2
Li Qinyu, Li Quan, Wei Xia, et al. Laser self-mixing interferometry for direct displacement reconstruction using deep learning[J]. Optics & Laser Technology, 2025, 192: 113423.
3
Liu Hui, Li Xintao, You Yaqiang, et al. Wiener filtering in wavelet domain on laser self-mixing interference for micro-displacement reconstruction[J]. Photonics, 2025, 12: 40.
4
Skripal A V, Dobdin S Y, Inkin M G, et al. Measurement of distance by the maximum frequency of the interference signal with harmonic deviation of the wavelength of the self-mixing laser[J]. Technical Physics, 2024, 69(5): 1400-1406.
5
曹雪, 冯立娜, 王秀芳, 等. 基于差分的激光自混合光栅干涉位移测量[J]. 吉林大学学报(信息科学版), 2023, 41(4): 583-589
Cao Xue, Feng Lina, Wang Xiufang, et al. Displacement measurement of self-mixing grating interferometer based on difference[J]. Journal of Jilin University (Information Science Edition), 2023, 41(4): 583-589
6
张玉杰, 徐雷, 管钰晴, 等. 基于平面反射式全息光栅的激光自混合纳米位移测量研究[J]. 红外与激光工程, 2023, 52: 20220676
Zhang Yujie, Xu Lei, Guan Yuqing, et al. Research on laser self-mixing Nano-displacement measurement based on plane reflective holographic grating[J]. Infrared and Laser Engineering, 2023, 52: 20220676
7
彭婉妮, 牛海莎, 潘雨婷, 等. 基于全光纤激光自混合干涉技术的石英玻璃热光系数测量[J]. 光电子·激光, 2022, 33(6): 578-584
Peng Wanni, Niu Haisha, Pan Yuting, et al. Measurement of thermo-optical coefficient of quartz glass based on all-fiber laser self-mixing interference technology[J]. Journal of Optoelectronics·Laser, 2022, 33(6): 578-584
8
张晨, 陈涛, 赵宇. 基于激光自混合干涉技术的单个微纳颗粒探测[J]. 激光与光电子学进展, 2020, 57: 192803
Zhang Chen, Chen Tao, Zhao Yu. Single micro-Nano particle detection based on laser self-mixing interference technology[J]. Laser & Optoelectronics Progress, 2020, 57: 192803
9
蔡家轩, 楚卫东. 基于THz-QCL自混合干涉的运动传感[J]. 太赫兹科学与电子信息学报, 2022, 20(10): 985-990
Cai Jiaxuan, Chu Weidong. Motion sensing based on Self-Mixing interferometry with THz-QCL[J]. Journal of Terahertz Science and Electronic Information Technology, 2022, 20(10): 985-990
10
Yu Lian, Yang Yu, Liu Bin, et al. Laser self-mixing interference: optical fiber coil sensors for acoustic emission detection[J]. Photonics, 2023, 10: 958.
11
Xie Yan, Wang Yingxin, Li Lianhe, et al. Realization of high depth resolution using two-beam self-mixing interferometry with a terahertz quantum cascade laser[J]. Optics Communications, 2023, 545: 129737.
12
Jha A, Cenkeramaddi L R, Royo S. Generalized multi-cavity laser self-mixing interferometry based on scattering theory[J]. Optics Express, 2023, 31(10): 16508-16522.
13
Liu Hui, You Yaqiang, Li Sijia, et al. Denoising of laser self-mixing interference by improved wavelet threshold for high performance of displacement reconstruction[J]. Photonics, 2023, 10: 943.
14
尤亚强, 李鑫涛, 刘晖, 等. 基于小波阈值滤波和S-G滤波相结合的激光自混合干涉微位移重构[J]. 强激光与粒子束, 2024, 36: 081002
You Yaqiang, Li Xintao, Liu Hui, et al. Micro displacement reconstruction of laser self mixing interference based on wavelet threshold filtering and S-G filtering[J]. High Power Laser and Particle Beams, 2024, 36: 081002
15
吴军, 陈杨, 赵君伟, 等. 基于激光自混合原理的涡轮叶片转速与叶尖间隙动态同步测量方法[J]. 仪器仪表学报, 2023, 44(11): 13-21
Wu Jun, Chen Yang, Zhao Junwei, et al. Dynamic synchronous measurement method of turbine blade speed and blade tip clearance based on laser self-mixing principle[J]. Chinese Journal of Scientific Instrument, 2023, 44(11): 13-21
16
韩玉祥, 丛至诚, 高丙坤, 等. 基于激光自混合干涉调频信号的位移测量实验[J]. 激光与红外, 2022, 52(5): 695-699
Han Yuxiang, Cong Zhicheng, Gao Bingkun, et al. Displacement measurement experiment based on laser self mixing interference frequency modulation signal[J]. Laser & Infrared, 2022, 52(5): 695-699
17
Zhao Yan, Zhang Baofeng, Han Lianfu. Laser self-mixing interference displacement measurement based on VMD and phase unwrapping[J]. Optics Communications, 2020, 456: 124588.
18
樊毓臻, 寇科, 王晛, 等. 线性调频激光自混合干涉双通道微位移测量方法研究[J]. 仪器仪表学报, 2023, 44(10): 22-29
Fan Yuzhen, Kou Ke, Wang Xian, et al. Study on the dual-channel displacement measurement method using linearly tuned laser self-mixing interference[J]. Chinese Journal of Scientific Instrument, 2023, 44(10): 22-29
19
Huang Yidan, Lai Wenzong, Chen Enguo. Displacement sensing for laser self-mixing interferometry by amplitude modulation and integral reconstruction[J]. Sensors, 2024, 24: 3785.
20
Awad A, Eldosoky M A A, Soliman A M, et al. Automatic diagnosis of hyperkinetic dysphonia from speech recordings based on deep learning approaches[J]. Engineering Research Express, 2025, 7: 035263.
21
Liu Ying, Xue Jiahao, Li Daxiang, et al. Image recognition based on lightweight convolutional neural network: recent advances[J]. Image and Vision Computing, 2024, 146: 105037.
22
Farajollahi A, Fakhrabadi M M S. Convolutional neural networks to predict dispersion surfaces-based properties of acoustic metamaterials with arbitrary-shaped unit cells[J]. Results in Engineering, 2025, 26: 104905.
23
Novac P E, Rodriguez L, Barland S. Integrating embedded neural networks and self-mixing interferometry for smart sensors design[C]//2024 IEEE Sensors Applications Symposium (SAS). 2024: 1-6.
24
An Lei, Liu Bin. Measuring parameters of laser self-mixing interferometry sensor based on back propagation neural network[J]. Optics Express, 2022, 30(11): 19134-19144.
25
Siddiqui A A, Zabit U, Bernal O D. Fringe detection and displacement sensing for variable optical feedback-based self-mixing interferometry by using deep neural networks[J]. Sensors, 2022, 22: 9831.
26
Sawada A, Miyagawa T, Ebihara A, et al. Convolutional neural networks for time-dependent classification of variable-length time series[C]//Proceedings of the 2022 International Joint Conference on Neural Networks (IJCNN). 2022: 1-8.
27
Chagnon J, Hagenbuchner M, Tsoi A C, et al. On the effects of recursive convolutional layers in convolutional neural networks[J]. Neurocomputing, 2024, 591: 127767.
28
Walter B. Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling[J]. Journal of Statistical Planning and Inference, 2023, 224: 109-126.
29
Liu Bin, Ruan Yuxi, Yu Yanguang. Determining system parameters and target movement directions in a laser self-mixing interferometry sensor[J]. Photonics, 2022, 9: 612.
2026年第38卷第4期
PDF下载
20
9
引用本文
BibTeX
文章信息
doi: 10.11884/HPLPB202638.250370
  • 接收时间:2025-10-28
  • 首发时间:2026-05-27
  • 出版时间:2026-04-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-10-28
  • 修回日期:2025-12-30
  • 录用日期:2025-12-30
基金
作者信息
    西安工程大学 机电工程学院,西安 710048

通讯作者:

刘晖,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/qjgylzs/CN/10.11884/HPLPB202638.250370
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏