太阳能学报

梯度动态选择看齐的DCFFC-FRNet风电滚动轴承故障诊断

PDF下载

杨富龙, 巩丽俊, 吴峰, 周津津, 杨庆, 张腾

太阳能学报 | 2026,47(6): 361-371

收起

太阳能学报 2026 , 47 (6) : 361 -371

梯度动态选择看齐的DCFFC-FRNet风电滚动轴承故障诊断

全屏

杨富龙, 巩丽俊, 吴峰, 周津津, 杨庆, 张腾

作者信息

GRADIENT DYNAMIC SELECTIVE ALIGNMENT FOR DCFFC-FRNET WIND TURBINE ROLLING BEARING FAULT DIAGNOSIS

Yang Fulong, Gong Lijun, Wu Feng, Zhou Jinjin, Yang Qing, Zhang Teng

Affiliations

doi: 10.19912/j.0254-0096.tynxb.2025-0147

文章导航

摘要

收起

提出一种梯度动态选择看齐（DSA）、双通道特征融合技术（DCFF）与深度学习相结合的风电滚动轴承故障诊断方法。首先,将采集到的一维时序数据采用递归图（RP）和马尔可夫转移场（MTF）转化为两种不同的二维图像数后据输入编码器重构为低维表示;然后,构建内嵌改进注意力机制FRNet的双通道特征融合卷积神经网络（DCFFC）提取深度特征信息,进行二级特征融合后完成特征分类;最后,利用解码器数据重构损失和特征提取网络分类损失构建梯度掩蔽矩阵,实现整个故障诊断过程梯度动态自适应。通过帕德伯恩数据集进行实验验证,结果表明该方法的诊断准确率为99%,能有效提取故障特征信息。

关键词

故障诊断 / 滚动轴承 / 风力发电机 / 卷积神经网络 / 梯度自适应

Abstract

收起

A fault diagnosis method for wind turbine rolling bearings is proposed, which combines the gradient dynamic selective alignment （DSA） method, dual-channel feature fusion technique （DCFF）, and deep learning. Firstly, the acquired one-dimensional time series data are transformed into two different two-dimensional image representations using recursive mapping （RP） and Markov transfer field （MTF）. These transformed images are then input into an encoder for reconstruction into a low-dimensional representation. Next, a dual-channel feature fusion convolutional neural network （DCFFC） is constructed, embedding an improved attention mechanism within FRNet to extract in-depth feature information. A second-level feature fusion is performed to complete the feature classification. Finally, a gradient masking matrix is constructed using the data reconstruction loss of the decoder and the feature extraction network classification loss to achieve gradient dynamic self-adaptation throughout the fault diagnosis process. Experimental validation using the Paderborn dataset demonstrates that the proposed method achieves a diagnostic accuracy of 99%, effectively extracting fault-specific diagnostic information.

Key words

fault diagnosis / rolling bearing / wind power generator / convolutional neural network / gradient adaptive

引用本文

杨富龙, 巩丽俊, 吴峰, 周津津, 杨庆, 张腾. 梯度动态选择看齐的DCFFC-FRNet风电滚动轴承故障诊断. 太阳能学报, 2026 , 47 (6) : 361 -371 . DOI: 10.19912/j.0254-0096.tynxb.2025-0147

Yang Fulong, Gong Lijun, Wu Feng, Zhou Jinjin, Yang Qing, Zhang Teng. GRADIENT DYNAMIC SELECTIVE ALIGNMENT FOR DCFFC-FRNET WIND TURBINE ROLLING BEARING FAULT DIAGNOSIS[J]. Acta Energiae Solaris Sinica, 2026 , 47 (6) : 361 -371 . DOI: 10.19912/j.0254-0096.tynxb.2025-0147

基金

收起

甘肃省重大科技项目（25ZDWA003）; 甘肃省联合科研基金（24JRRA829）; 甘肃省重点研发计划-工业领域项目（25YFGA033）

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1] 余萍, 宋紫琼, 曹洁, 等. 基于BNN-RA模型的风电机组轴承故障诊断研究[J]. 太阳能学报, 2025, 46(3): 643-651.
YU P, SONG Z Q, CAO J, et al.Research on fault diagnosis of wind turbine bearing based on BNN-RA model[J]. Acta energiae solaris sinica, 2025, 46(3): 643-651.
[2] 邢作霞, 张玥, 郭珊珊, 等. 基于改进卷积神经网络的风电机组叶片覆冰诊断方法研究[J]. 太阳能学报, 2025, 46(3): 661-667.
XING Z X, ZHANG Y, GUO S S, et al.Diagnosis of blade icing based on improved convolution neural network in wind turbine study[J]. Acta energiae solaris sinica, 2025, 46(3): 661-667.
[3] 邵海东, 肖一鸣, 颜深. 仿真数据驱动的改进无监督域适应轴承故障诊断[J]. 机械工程学报, 2023, 59(3): 76-85.
SHAO H D, XIAO Y M, YAN S.Simulation data-driven enhanced unsupervised domain adaptation for bearing fault diagnosis[J]. Journal of mechanical engineering, 2023, 59(3): 76-85.
[4] FU W L, JIANG X H, LI B L, et al.Rolling bearing fault diagnosis based on 2D time-frequency images and data augmentation technique[J]. Measurement science and technology, 2023, 34(4): 045005.
[5] WANG Z K, XU Z F, CAI C, et al.Rolling bearing fault diagnosis method using time-frequency information integration and multi-scale TransFusion network[J]. Knowledge-based systems, 2024, 284: 111344.
[6] HU B Q, LIU J, ZHAO R Z, et al.A new dual-channel convolutional neural network and its application in rolling bearing fault diagnosis[J]. Measurement science and technology, 2024, 35(9): 096130.
[7] YAO D C, ZHOU T, YANG J W, et al.Fault diagnosis of rolling bearings based on dynamic convolution and dual-channel feature fusion under variable working conditions[J]. Measurement science and technology, 2024, 35(6): 066110.
[8] 成洁, 李思燃. 基于递归图和局部非负矩阵分解的轴承故障诊断[J]. 工矿自动化, 2017, 43(7): 81-85.
CHENG J, LI S R.Bearing fault diagnosis based on recurrence plots and local non-negative matrix factorization[J]. Industry and mine automation, 2017, 43(7): 81-85.
[9] CUI L, TIAN X C, WEI Q Z, et al.A self-attention based contrastive learning method for bearing fault diagnosis[J]. Expert systems with applications, 2024, 238: 121645.
[10] BAI R X, MENG Z, XU Q S, et al.Fractional Fourier and time domain recurrence plot fusion combining convolutional neural network for bearing fault diagnosis under variable working conditions[J]. Reliability engineering & system safety, 2023, 232: 109076.
[11] WANG H T, LIU Z L, LI M J, et al.A gearbox fault diagnosis method based on graph neural networks and Markov transform fields[J]. IEEE sensors journal, 2024, 24(15): 25186-25196.
[12] WANG J X, WANG D Z, WANG S H, et al.Fault diagnosis of bearings based on multi-sensor information fusion and 2D convolutional neural network[J]. IEEE access, 2021, 9: 23717-23725.
[13] WANG Y, WANG Q R, ZHOU Y T.Improved Dual-channel CNN-BiLstm rolling bearing fault diagnosis study[C]//EEI 2022; 4th International Conference on Electronic Engineering and Informatics. Guiyang, China, 2023: 1-5.
[14] WANG D L, LI Y H, LU C, et al.Research on digital twin-assisted dual-channel parallel convolutional neural network-transformer rolling bearing fault diagnosis method[J]. Proceedings of the Institution of Mechanical Engineers, Part B: journal of engineering manufacture, 2024: 09544054241290573.

2026年第47卷第6期

PDF下载

347

引用本文

BibTeX

文章信息

doi: 10.19912/j.0254-0096.tynxb.2025-0147

接收时间：2025-01-17
首发时间：2026-07-17

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2025-01-17

基金

作者信息

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/tynxb/CN/10.19912/j.0254-0096.tynxb.2025-0147

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

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

BibTeX
EndNote
RefWorks
TxT