电源学报

基于独立分类器GAN的AGV电池故障诊断

PDF下载

高颖 ¹ , 祁媚 ² , 王敏 ¹

电源学报 | 故障诊断与可靠性 2026,24(7): 335-348

收起

电源学报 |故障诊断与可靠性 2026 , 24 (7) : 335 -348

基于独立分类器GAN的AGV电池故障诊断

全屏

[Author(id=1322531973139125164, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=gaoying1983sz@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322531973214622638, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, authorId=1322531973139125164, language=EN, stringName=Ying GAO, firstName=Ying, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=¹, address=^1.School of Mechanical and Electrical Engineering, Suzhou Vocational University, Suzhou 215104, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322531973550166959, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, authorId=1322531973139125164, language=CN, stringName=高颖, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=¹, address=^1.苏州市职业大学机电工程学院，苏州　215104, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322531971138442149, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, xref=1., ext=[AuthorCompanyExt(id=1322531971146830758, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, companyId=1322531971138442149, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^1.School of Mechanical and Electrical Engineering, Suzhou Vocational University, Suzhou 215104, China), AuthorCompanyExt(id=1322531971159413671, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, companyId=1322531971138442149, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^1.苏州市职业大学机电工程学院，苏州　215104)])]), Author(id=1322531973625664433, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=qimei0916@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322531973969597363, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, authorId=1322531973625664433, language=EN, stringName=Mei QI, firstName=Mei, middleName=null, lastName=QI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=², address=^2.School of Information Science and Technology, Northwest University, Xi’an 710127, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322531974057677748, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, authorId=1322531973625664433, language=CN, stringName=祁媚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=², address=^2.西北大学信息科学与技术学院，西安　710127, bio={"content":"

祁媚（1988—　），女，博士，讲师。研究方向：激光器，机器学习。E-mail：qimei0916@163.com。

"}, bioImg=null, bioContent=

祁媚（1988—　），女，博士，讲师。研究方向：激光器，机器学习。E-mail：qimei0916@163.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322531971222328232, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, xref=2., ext=[AuthorCompanyExt(id=1322531971444626345, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, companyId=1322531971222328232, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^2.School of Information Science and Technology, Northwest University, Xi’an 710127, China), AuthorCompanyExt(id=1322531971453014954, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, companyId=1322531971222328232, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^2.西北大学信息科学与技术学院，西安　710127)])]), Author(id=1322531974124786614, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wangmin@jssvc.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322531974514856888, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, authorId=1322531974124786614, language=EN, stringName=Min WANG, firstName=Min, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=¹, address=^1.School of Mechanical and Electrical Engineering, Suzhou Vocational University, Suzhou 215104, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322531974825235385, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, authorId=1322531974124786614, language=CN, stringName=王敏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=¹, address=^1.苏州市职业大学机电工程学院，苏州　215104, bio={"content":"

王敏（1986—　），女，硕士，副教授。研究方向：机电一体化技术。E-mail：wangmin@jssvc.edu.cn。

"}, bioImg=null, bioContent=

王敏（1986—　），女，硕士，副教授。研究方向：机电一体化技术。E-mail：wangmin@jssvc.edu.cn。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322531971138442149, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, xref=1., ext=[AuthorCompanyExt(id=1322531971146830758, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, companyId=1322531971138442149, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^1.School of Mechanical and Electrical Engineering, Suzhou Vocational University, Suzhou 215104, China), AuthorCompanyExt(id=1322531971159413671, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531969993397154, companyId=1322531971138442149, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^1.苏州市职业大学机电工程学院，苏州　215104)])])]

高颖¹, 祁媚², 王敏¹

作者信息

^1.苏州市职业大学机电工程学院，苏州　215104

^2.西北大学信息科学与技术学院，西安　710127

通讯作者:

高颖（1983—　），女，通信作者，硕士，高级工程师。研究方向：传感检测技术，测控技术。E-mail：gaoying1983sz@163.com。

作者简介:

祁媚（1988—　），女，博士，讲师。研究方向：激光器，机器学习。E-mail：qimei0916@163.com。

王敏（1986—　），女，硕士，副教授。研究方向：机电一体化技术。E-mail：wangmin@jssvc.edu.cn。

Fault Diagnosis of AGV Battery Based on Separate Classifier GAN

Ying GAO¹, Mei QI², Min WANG¹

Affiliations

^1.School of Mechanical and Electrical Engineering, Suzhou Vocational University, Suzhou 215104, China

^2.School of Information Science and Technology, Northwest University, Xi’an 710127, China

出版时间: 2026-07-30 doi: 10.13234/j.issn.2095-2805.2026.7.335

文章导航

摘要

收起

针对自动导引车AGV（automatic guided vehicle）动力电池故障诊断中因样本稀疏性与类别不平衡导致的模型性能退化问题，提出一种结合梯度惩罚和独立分类器的生成对抗网络GPSC-GAN（gradient penalization and separate classifier-generative adversarial network）。首先，通过引入带梯度惩罚的瓦瑟斯坦（Wasserstein）距离优化判别器损失函数，约束生成样本与真实电池故障特征的分布差异，提升模型训练稳定性。其次，设计1个独立分类器模块，解耦分类与判别功能，生成多模式高质量故障样本以构建平衡数据集。在AGV电池故障数据集上的实验结果表明，GPSC-GAN生成样本的结构相似性指数度量SSIM（structural similarity index measure）与最大均值差异MMD（maximum mean difference）分别达到0.5和0.2，较WGAN-GP、ACGAN、SMOTE、ADASYN、Diffusion GAN和StyleGAN-T模型提升25%~66%。融合生成样本后，故障诊断模型的F1分数达到0.938，精确率与召回率分别达到94.6%和93.0%，优于其他6种对比方法，验证了其在复杂工业场景下的高效性与鲁棒性。

关键词

自动导引车 / 电池 / 故障诊断 / 生成对抗网络 / 梯度惩罚

Abstract

收起

In order to address the model performance degradation caused by sample sparsity and class imbalance in multimode fault diagnosis of automatic guided vehicle (AGV) power batteries, a generative adversarial network incorporating gradient penalty and an independent classifier (GPSC-GAN) was proposed. First, the discriminator loss function was optimized through the introduction of Wasserstein distance with gradient penalty, whereby the distribution divergence between generated samples and real battery fault features was constrained to enhance training stability. Second, an independent classifier module was designed to decouple classification and discrimination functions, enabling high-quality multimode fault samples to be generated for constructing a balanced dataset. Experimental results on AGV battery fault datasets demonstrated that the generated samples achieved structural similarity index measure (SSIM) and maximum mean difference (MMD) values of 0.5 and 0.2 respectively, showing 25% to 66% improvements compared with WGAN-GP, ACGAN, SMOTE, ADASYN, Diffusion GAN and StyleGAN-T models. After integrating synthetic samples, the F1-score of the fault diagnosis model was enhanced to 0.938, with precision and recall rates reaching 94.6% and 93.0% respectively. These metrics outperformed six other comparative methods, verifying the proposed method’s efficiency and robustness in complex industrial scenarios.

Key words

AGV / battery / fault diagnosis / generative adversarial network / gradient penalty

引用本文

高颖, 祁媚, 王敏. 基于独立分类器GAN的AGV电池故障诊断. 电源学报, 2026 , 24 (7) : 335 -348 . DOI: 10.13234/j.issn.2095-2805.2026.7.335

Ying GAO, Mei QI, Min WANG. Fault Diagnosis of AGV Battery Based on Separate Classifier GAN[J]. Journal of Power Supply, 2026 , 24 (7) : 335 -348 . DOI: 10.13234/j.issn.2095-2805.2026.7.335

基金

收起

江苏高校“青蓝工程”资助项目(202205000004)
苏州市职业大学“青蓝工程”资助项目(202105000013)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

孙孝飞, 郭捷, 魏灿名, 等. 3C智能制造工厂的AGV智慧物料传输与调度综述[J]. 中南大学学报(自然科学版), 2025, 56(2): 514-535. Sun Xiaofei, Guo Jie, Wei Canming, et al. Review of AGV smart material transmission and dispatching in 3C smart manufacturing factories[J]. Journal of Central South University (Science and Technology), 2025, 56(2): 514-535. (in Chinese)

[2]

李峥峰, 张东方, 丁其聪, 等. 考虑AGV运输和机器转速的作业车间绿色调度研究[J]. 机电工程, 2024, 41(2): 327-336. Li Zhengfeng, Zhang Dongfang, Ding Qicong, et al. Green scheduling of job shop considering AGV transporttation and machine speed[J]. Mechanical & Electrical Engineering Magazine, 2024, 41(2): 327-336. (in Chinese)

[3]

田帅辉, 皇甫城阳, 邓学平. AGV调度优化的应用场景、关键因素和研究方法综述[J]. 重庆邮电大学学报(自然科学版), 2024, 36(2): 337-350. Tian Shuaihui, Huangfu Chengyang, Deng Xueping. Review of application scenarios, key factors, and research methods of AGV scheduling optimization[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2024, 36(2): 337-350. (in Chinese)

[4]

陈石明, 范烨, 刘晶. 智能电网内规模化分布式电池储能系统的调频控制方法[J]. 电源学报, 2025, 23(1): 120-131. Chen Shiming, Fan Ye, Liu Jing. Frequency modulation control method for large-scale distributed battery energy storage systems in smart grid[J]. Journal of Power Supply, 2025, 23(1): 120-131. (in Chinese)

[5]

石海鹏, 刁凤新, 袁浩, 等. 特殊环境下锂电池失效研究进展[J]. 电源学报, 2024, 22(5): 286-293. Shi Haipeng, Diao Fengxin, Yuan Hao, et al. Progress in failure analysis of lithium-based batteries under harsh environmental conditions[J]. Journal of Power Supply, 2024, 22(5): 286-293. (in Chinese)

[6]

王健俊, 陈豪, 付元承. 基于集成学习与数据驱动的电动汽车动力电池多维度故障预警[J]. 汽车安全与节能学报, 2024, 15(3): 368-378. Wang Jianjun, Chen Hao, Fu Yuancheng. Data-driven fault early warning of electric vehicle power battery based on ensemble learning from multiple dimensions[J]. Journal of Automotive Safety and Engergy, 2024, 15(3): 368-378. (in Chinese)

[7]

刘俊宏. 数据驱动在电力储能设备声纹识别和监测诊断中的应用[J]. 储能科学与技术, 2024, 13(8): 2835-2837. Liu Junhong. Application of data-driven technology in voiceprint recognition and monitoring diagnosis of power energy storage equipment[J]. Energy Storage Science and Technology, 2024, 13(8): 2835-2837. (in Chinese)

[8]

任义, 孙明丽, 栾方军, 等. 基于特征插值TSCTransMix-CapsNet的轴承故障分类模型[J]. 机电工程, 2025, 42(4): 607-617. Ren Yi, Sun Mingli, Luan Fangjun, et al. Bearing fault classification model based on feature interpolation TSCTransMix-CapsNet[J]. Mechanical & Electrical Engineering Magazine, 2025, 42(4): 607-617. (in Chinese)

[9]

刘迪洋, 张清华, 胡勤. 基于深度学习的轴承故障小样本扩容及智能诊断[J]. 机床与液压, 2025, 53(4): 10-18. Liu Diyang, Zhang Qinghua, Hu Qin. Deep learning-based small sample expansion and intelligent diagnosis of bearing faults[J]. Machine Tool & Hydraulics, 2025, 53(4): 10-18. (in Chinese)

[10]

Mao Wentao, Feng Wushi, Liang Xihui. A novel deep output kernel learning method for bearing fault structural diagnosis[J]. Mechanical Systems and Signal Processing, 2019, 117: 293-318.

[11]

时培明, 梁凯, 赵娜, 等. 基于深度学习特征提取和粒子群支持向量机状态识别的齿轮智能故障诊断[J]. 中国机械工程, 2017, 28(9): 1056-1061, 1068. Shi Peiming, Liang Kai, Zhao Na, et al. Intelligent fault diagnosis for gears based on deep learning feature extraction and particle swarm optimization SVM state identification[J]. China Mechanical Engineering, 2017, 28(9): 1056-1061, 1068. (in Chinese)

[12]

Wang Jingang, Liu Ya, Tian Tian. Fault diagnosis method of wind turbine gearbox based on fusion multispectrogram and improved CNN neural network[C]//2022 5th International Conference on Energy, Electrical and Power Engineering (CEEPE). Chongqing, China, 2022: 513-517.

[13]

Lü Pin, Zheng Pai, Yu Wenbing, et al. A novel multi-view sampling-based meta self-paced learning approach for class-imbalanced intelligent fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 3527512.

[14]

Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144.

[15]

刘雪锋, 李京忠, 王现辉. 基于全局优化GAN的不平衡数据故障诊断[J]. 机械设计与制造, 2024(3): 11-17. Liu Xuefeng, Li Jingzhong, Wang Xianhui. Fault diagnosis of unbalanced databased on global optimization GAN[J]. Machinery Design & Manufacture, 2024(3): 11-17. (in Chinese)

[16]

李洁, 张震豪, 董亚冰, 等. 基于生成对抗网络的电动汽车电池数据增强和故障诊断[J]. 汽车技术, 2023(8): 1-6. Li Jie, Zhang Zhenhao, Dong Yabing, et al. Electric vehicle battery data augmentation and fault diagnosis based on generative adversarial networks[J]. Automobile Technology, 2023(8): 1-6. (in Chinese)

[17]

徐慧兵, 李道伦, 查文舒. 基于梯度惩罚Wasserstein生成对抗网络的数字岩心重建[J]. 合肥工业大学学报(自然科学版), 2024, 47(11): 1559-1563. Xu Huibing, Li Daolun, Zha Wenshu. 3D digital core reconstruction based on gradient penalized Wasserstein generative adversarial networks[J]. Journal of Hefei University of Technology (Natural Science), 2024, 47(11): 1559-1563. (in Chinese)

[18]

Tong Qingbin, Lu Feiyu, Feng Ziwei, et al. A novel method for fault diagnosis of bearings with small and imbalanced data based on generative adversarial networks[J]. Applied Sciences, 2022, 12(14): 7346.

[19]

Li Wei, Zhong Xiang, Shao Haidong, et al. Multi-mode data augmentation and fault diagnosis of rotating machinery using modified ACGAN designed with new frame-work[J]. Advanced Engineering Informatics, 2022, 52: 101552.

[20]

Gulrajani I, Ahmed F, Arjovsky M, et al. Improved training of Wasserstein GANs[C]//Proceedings of Advances in Neural Information Processing Systems. Long Beach, CA, USA, 2017: 5767-5777.

[21]

Wang Zhou, Bovik A C, Sheikh H R, et al. Image quality assessment: From error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.

[22]

Duan Feng, Zhang Shuai, Yan Yinze, et al. An oversampling method of unbalanced data for mechanical fault diagnosis based on MeanRadius-SMOTE[J]. Sensors, 2022, 22(14): 5166.

[23]

Guan Shan, Yang Haiqi, Wu Tongyu. Transformer fault diagnosis method based on TLR-ADASYN balanced dataset[J]. Scientific Reports, 2023, 13: 23010.

[24]

Yao Feifan, Zhang Huiying, Gong Yifei, et al. A study of enhanced visual perception of marine biology images based on diffusion-GAN[J]. Complex & Intelligent Sy-stems, 2025, 11(5): 227.

[25]

Sauer A, Karras T, Laine S, et al. StyleGAN-T: Unlocking the power of GANs for fast large-scale text-toimage synthesis[C]//Proceedings of Machine Learning Research, Edmonton, Canada, 2023: 30105-30118.

2026年第24卷第7期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.13234/j.issn.2095-2805.2026.7.335

接收时间：2025-05-27
首发时间：2026-10-29
出版时间：2026-07-30

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2025-05-27
修回日期：2025-08-01
录用日期：2025-08-16

基金

“Qing Lan Project” of Jiangsu Province(202205000004)

江苏高校“青蓝工程”资助项目(202205000004)

“Qing Lan Project” of Suzhou Vocational University(202105000013)

苏州市职业大学“青蓝工程”资助项目(202105000013)

作者信息

^1.苏州市职业大学机电工程学院，苏州　215104

^2.西北大学信息科学与技术学院，西安　710127

通讯作者:

高颖（1983—　），女，通信作者，硕士，高级工程师。研究方向：传感检测技术，测控技术。E-mail：gaoying1983sz@163.com。

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2026.7.335

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