对失效传感器具备鲁棒性的故障诊断方法

doi:10.3785/j.issn.1008-973X.2024.07.018

浙江大学学报(工学版)

2024, Vol. 58

Issue (7): 1488-1497 DOI: 10.3785/j.issn.1008-973X.2024.07.018

机械工程、能源工程

对失效传感器具备鲁棒性的故障诊断方法

马现伟1(

),范朝辉2,聂为之3,*(

),李东4,朱逸群5

1. 天津大学未来技术学院，天津 300072
2. 军事科学院战略评估咨询中心，北京 100091
3. 天津大学电气自动化与信息工程学院，天津 300072
4. 天津大学智能与计算学部，天津 300050
5. 国网天津市电力公司营销服务中心计量中心，天津 300160

Robust fault diagnosis method for failure sensors

Xianwei MA1(

),Chaohui FAN2,Weizhi NIE3,*(

),Dong LI4,Yiqun ZHU5

1. School of Future Technology, Tianjin University, Tianjin 300072, China
2. Strategic Assessments and Consultation Institute, Academy of Military Science, Beijing 100091, China
3. School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
4. College of Intelligence and Computing, Tianjin University, Tianjin 300050, China
5. Metrology Center, State Grid Tianjin Marketing Service Center, Tianjin 300160, China

全文: PDF(1181 KB) HTML

摘要：

针对传感器失效对故障诊断效果的影响，提出带有退化特征惩罚机制的故障诊断方法(FDCFP). 利用卷积神经网络提取局部特征，使用Transformer编码器进一步融合全局信息，缓解局部传感器失效对特征学习的影响. 引入自注意力掩码对传感器失效引入的特征伪关联性进行惩罚，使编码器更关注未受失效影响的传感器数据. 掩码在自注意力层参与权重计算，以较低的复杂度代价提高含有失效数据模型的鲁棒性. 在CWRU、PU、SEU和XJTU-SY数据集上进行FDCFP的性能验证，当数据失效比例为0.7时，FDCFP在CWRU、PU和XJTU-SY数据集上的故障诊断准确率相较于现有方法分别提升了5.9%、3.1%和3.7%.

关键词： 传感器失效; 故障诊断; 深度学习; 注意力机制; Transformer

Abstract:

A fault diagnosis method with corrupted feature penalties (FDCFP) was proposed to address the impact of sensor failure on fault diagnosis. The convolutional neural network was used to extract local features, and the Transformer encoder was used to further fuse global information, alleviating the influence of local sensor failures on feature learning. The self-attention masks were employed to penalize the pseudo-correlation between features introduced by the sensor failure, making the encoder attentive to the parts of the sensor data unaffected by failures. The masks were weighted at the self-attention layer to improve the model’s robustness to sensor failures in the presence of faulty data at a low complexity cost. The performance of the proposed method was verified in datasets such as CWRU, PU, SEU, and XJTU-SY. Compared to existing methods, the FDCFP achieved accuracy improvements of 5.9%, 3.1%, and 3.7% respectively on the CWRU, PU, and XJTU-SY datasets at a 0.7 data failure ratio.

Key words: sensor failure fault diagnosis deep learning attention mechanism Transformer

收稿日期: 2023-06-12 出版日期: 2024-07-01

CLC:

TP 181

基金资助: 国家重点研发计划资助项目（2020YFB1711700）.

通讯作者: 聂为之 E-mail: hsienwei_ma@tju.edu.cn;weizhinie@tju.edu.cn

作者简介: 马现伟（1999—），男，硕士生，从事故障诊断研究. orcid.org/0009-0005-4234-1641. E-mail：hsienwei_ma@tju.edu.cn

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	作者相关文章
	马现伟
	范朝辉
	聂为之
	李东
	朱逸群

引用本文:

马现伟,范朝辉,聂为之,李东,朱逸群. 对失效传感器具备鲁棒性的故障诊断方法[J]. 浙江大学学报(工学版), 2024, 58(7): 1488-1497.

Xianwei MA,Chaohui FAN,Weizhi NIE,Dong LI,Yiqun ZHU. Robust fault diagnosis method for failure sensors. Journal of ZheJiang University (Engineering Science), 2024, 58(7): 1488-1497.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2024.07.018 或 https://www.zjujournals.com/eng/CN/Y2024/V58/I7/1488

图 1 带有退化特征惩罚机制的故障诊断方法的模型架构

表 1 特征提取模块的一维卷积神经网络参数

图 2 掩码自注意力计算流程

图 3 不同传感器失效比例下的注意力权重分布

图 4 CWRU数据集在不同传感器失效比例下的信号分布

图 5 不同传感器失效比例下连续缺失长度分布直方图

表 2 不同故障诊断方法在4个数据集上的故障诊断准确率

图 6 4个数据集上传感器失效对不同故障诊断方法性能的影响

图 7 掩码自注意力对故障诊断准确率的影响

表 3 不同故障诊断方法的复杂度和实时性

1	WANG J, XU C, ZHANG J, et al Big data analytics for intelligent manufacturing systems: a review[J]. Journal of Manufacturing Systems, 2022, 62: 738- 752 doi: 10.1016/j.jmsy.2021.03.005
2	ZHAO Y, LI T, ZHANG X, et al Artificial intelligence-based fault detection and diagnosis methods for building energy systems: advantages, challenges and the future[J]. Renewable and Sustainable Energy Reviews, 2019, 109: 85- 101 doi: 10.1016/j.rser.2019.04.021
3	ASKARIAN M, ESCUDERO G, GRAELLS M, et al Fault diagnosis of chemical processes with incomplete observations: a comparative study[J]. Computers and Chemical Engineering, 2016, 84: 104- 116 doi: 10.1016/j.compchemeng.2015.08.018
4	RAZAVI-FAR R, SAIF M, PALADE V, et al An integrated framework for diagnosing process faults with incomplete features[J]. Knowledge and Information Systems, 2022, 64: 75- 93 doi: 10.1007/s10115-021-01625-w
5	陈嘉宁, 杨翾, 叶承晋, 等基于缺失数据修复的变压器在线故障诊断方法[J]. 电力系统保护与控制, 2019, 47 (15): 86- 92 CHEN Jianing, YANG Xuan, YE Chengjin, et al On-line fault diagnosis method for power transformer based on missing data repair[J]. Power System Protection and Control, 2019, 47 (15): 86- 92 doi: 10.7667/PSPC20191512
6	LIU R, MENG G, YANG B Y, et al Dislocated time series convolutional neural architecture: an intelligent fault diagnosis approach for electric machine[J]. IEEE Transactions on Industrial Informatics, 2017, 13 (3): 1310- 1320 doi: 10.1109/TII.2016.2645238
7	DEVLIN J, CHANG M, LEE K, et al. BERT: pre-training of deep bidirectional Transformers for language understanding [C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies . Minneapolis: Association for Computational Linguistics, 2019: 4171–4186.
8	LI B, HU Y, NIE X, et al. DropKey for Vision Transformer [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Vancouver: IEEE, 2023: 22700–22709.
9	WU Z, WU L, MENG Q, et al. UniDrop: a simple yet effective technique to improve Transformer without extra cost [C]// Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies . [S.l.]: Association for Computational Linguistics, 2021: 3865–3878.
10	FENG Z, LIANG M, CHU F Recent advances in time–frequency analysis methods for machinery fault diagnosis: a review with application examples[J]. Mechanical Systems and Signal Processing, 2013, 38 (1): 165- 205 doi: 10.1016/j.ymssp.2013.01.017
11	钟凯. 基于多元统计分析的故障检测与诊断研究[D]. 大连: 大连理工大学, 2020. ZHONG Kai. Multivariate statistical analysis based fault detection and diagnosis [D]. Dalian: Dalian University of Technology, 2020.
12	SINGH V, GANGSAR P, PORWAL R, et al Artificial intelligence application in fault diagnostics of rotating industrial machines: a state-of-the-art review[J]. Journal of Intelligent Manufacturing, 2021, 34 (3): 931- 960
13	VOS K, PENG Z, JENKINS C, et al Vibration-based anomaly detection using LSTM/SVM approaches[J]. Mechanical Systems and Signal Processing, 2022, 169: 108752 doi: 10.1016/j.ymssp.2021.108752
14	李兵, 韩睿, 何怡刚, 等改进随机森林算法在电机轴承故障诊断中的应用[J]. 中国电机工程学报, 2020, 40 (4): 1310- 1319 LI Bing, HAN Rui, HE Yigang, et al Applications of improved random forest algorithm in fault diagnosis of motor bearings[J]. Proceedings of the CSEE, 2020, 40 (4): 1310- 1319
15	ZHU Z, LEI Y, QI G, et al A review of the application of deep learning in intelligent fault diagnosis of rotating machinery[J]. Measurement, 2023, 206: 112346 doi: 10.1016/j.measurement.2022.112346
16	CUI M, WANG Y, LIN X, et al Fault diagnosis of rolling bearings based on an improved stack autoencoder and support vector machine[J]. IEEE Sensors Journal, 2021, 21 (4): 4927- 4937 doi: 10.1109/JSEN.2020.3030910
17	GUO X, SHEN C, CHEN L Deep fault recognizer: an integrated model to denoise and extract features for fault diagnosis in rotating machinery[J]. Applied Sciences, 2017, 7 (1): 41
18	WEN L, LI X, GAO L, et al A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics, 2018, 65 (7): 5990- 5998 doi: 10.1109/TIE.2017.2774777
19	WANG P, ANANYA, YAN R, et al Virtualization and deep recognition for system fault classification[J]. Journal of Manufacturing Systems, 2017, 44: 310- 316 doi: 10.1016/j.jmsy.2017.04.012
20	CHEN X, ZHANG B, GAO D Bearing fault diagnosis base on multi-scale CNN and LSTM model[J]. Journal of Intelligent Manufacturing, 2021, 32: 971- 987 doi: 10.1007/s10845-020-01600-2
21	AN Z, LI S, WANG J, et al A novel bearing intelligent fault diagnosis framework under time-varying working conditions using recurrent neural network[J]. ISA Transactions, 2020, 100: 155- 170 doi: 10.1016/j.isatra.2019.11.010
22	LIU H, ZHOU J, ZHENG Y, et al Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders[J]. ISA Transactions, 2018, 77: 167- 178 doi: 10.1016/j.isatra.2018.04.005
23	ZHAO R, WANG D, YAN R, et al Machine health monitoring using local feature-based gated recurrent unit networks[J]. IEEE Transactions on Industrial Electronics, 2018, 65 (2): 1539- 1548 doi: 10.1109/TIE.2017.2733438
24	BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate [C]// 3rd International Conference on Learning Representations . San Diego: [s.n.], 2015.
25	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems . La Jolla: [s.n.], 2017: 6000–6010.
26	KHAN S, NASEER M, HAYAT M, et al Transformers in vision: a survey[J]. ACM Computing Surveys, 2022, 54 (10s): 200
27	PEI X, ZHENG X, WU J Rotating machinery fault diagnosis through a transformer convolution network subjected to transfer learning[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 2515611
28	王誉翔, 钟智伟, 夏鹏程, 等基于改进Transformer的复合故障解耦诊断方法[J]. 浙江大学学报: 工学版, 2023, 57 (5): 855- 864 WANG Yuxiang, ZHONG Zhiwei, XIA Pengcheng, et al Compound fault decoupling diagnosis method based on improved Transformer[J]. Journal of Zhejiang University: Engineering Science, 2023, 57 (5): 855- 864
29	CHE Z, URUSHOTHAM S, CHO K, et al Recurrent neural networks for multivariate time series with missing values[J]. Scientific Reports, 2018, 8: 6085 doi: 10.1038/s41598-018-24271-9
30	SONG L, GONG D, LI Z, et al. Occlusion robust face recognition based on mask learning with pairwise differential siamese network [C]// 2019 IEEE/CVF International Conference on Computer Vision . Seoul: IEEE, 2019: 773–782.
31	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition [C]// IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas: IEEE, 2016: 770–778.
32	SMITH W A, RANDALL R B, et al Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study[J]. Mechanical Systems and Signal Processing, 2015, 64/65: 100- 131 doi: 10.1016/j.ymssp.2015.04.021
33	LESSMEIER C, KIMOTHO J K, ZIMMER D, et al. Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: a benchmark data set for data-driven classification [C]// European Conference of the Prognostics and Health Management Society . [S.l.]: Prognostics and Health Management Society, 2016.
34	SHAO S, MCALEER S, YAN R, et al Highly accurate machine gault diagnosis using deep transfer learning[J]. IEEE Transactions on Industrial Informatics, 2019, 15 (4): 2446- 2455 doi: 10.1109/TII.2018.2864759
35	WANG B, LEI Y, LI N, et al A hybrid prognostics approach for estimating remaining useful life of rolling element bearings[J]. IEEE Transactions on Reliability, 2020, 69 (1): 401- 412 doi: 10.1109/TR.2018.2882682
36	LIN W, TSAI C Missing value imputation: a review and analysis of the literature (2006–2017)[J]. Artificial Intelligence Review, 2020, 53: 1487- 1509 doi: 10.1007/s10462-019-09709-4
37	郭毅博, 牛猛, 王海迪, 等基于生成对抗网络的飞机燃油数据缺失值填充方法[J]. 浙江大学学报: 理学版, 2021, 48 (4): 402- 409 GUO Yibo, NIU Meng, WANG Haidi, et al An aircraft fuel data missing value filling method with generative adversarial network[J]. Journal of Zhejiang University: Science Edition, 2021, 48 (4): 402- 409

[1]	吴书晗,王丹,陈远方,贾子钰,张越棋,许萌. 融合注意力的滤波器组双视图图卷积运动想象脑电分类[J]. 浙江大学学报(工学版), 2024, 58(7): 1326-1335.
[2]	李林睿,王东升,范红杰. 基于法条知识的事理型类案检索方法[J]. 浙江大学学报(工学版), 2024, 58(7): 1357-1365.
[3]	杨军,张琛. 基于边界点估计与稀疏卷积神经网络的三维点云语义分割[J]. 浙江大学学报(工学版), 2024, 58(6): 1121-1132.
[4]	李运堂,李恒杰,张坤,王斌锐,关山越,陈源. 基于新型编码解码网络的复杂输电线识别[J]. 浙江大学学报(工学版), 2024, 58(6): 1133-1141.
[5]	宋娟,贺龙喜,龙会平. 基于深度学习的隧道衬砌多病害检测算法[J]. 浙江大学学报(工学版), 2024, 58(6): 1161-1173.
[6]	韩康,战洪飞,余军合,王瑞. 基于空洞卷积和增强型多尺度特征自适应融合的滚动轴承故障诊断[J]. 浙江大学学报(工学版), 2024, 58(6): 1285-1295.
[7]	邢志伟,朱书杰,李彪. 基于改进图卷积神经网络的航空行李特征感知[J]. 浙江大学学报(工学版), 2024, 58(5): 941-950.
[8]	刘毅,陈一丹,高琳,洪姣. 基于多尺度特征融合的轻量化道路提取模型[J]. 浙江大学学报(工学版), 2024, 58(5): 951-959.
[9]	魏翠婷,赵唯坚,孙博超,刘芸怡. 基于改进Mask R-CNN与双目视觉的智能配筋检测[J]. 浙江大学学报(工学版), 2024, 58(5): 1009-1019.
[10]	钟博,王鹏飞,王乙乔,王晓玲. 基于深度学习的EEG数据分析技术综述[J]. 浙江大学学报(工学版), 2024, 58(5): 879-890.
[11]	范康,钟铭恩,谭佳威,詹泽辉,冯妍. 联合语义分割和深度估计的交通场景感知算法[J]. 浙江大学学报(工学版), 2024, 58(4): 684-695.
[12]	宦海,盛宇,顾晨曦. 基于遥感图像道路提取的全局指导多特征融合网络[J]. 浙江大学学报(工学版), 2024, 58(4): 696-707.
[13]	罗向龙,王亚飞,王彦博,王立新. 基于双向门控式宽度学习系统的监测数据结构变形预测[J]. 浙江大学学报(工学版), 2024, 58(4): 729-736.
[14]	宋明俊,严文,邓益昭,张俊然,涂海燕. 轻量化机器人抓取位姿实时检测算法[J]. 浙江大学学报(工学版), 2024, 58(3): 599-610.
[15]	钱庆杰,余军合,战洪飞,王瑞,胡健. 基于DL-BiGRU多特征融合的注塑件尺寸预测方法[J]. 浙江大学学报(工学版), 2024, 58(3): 646-654.

Viewed

Full text

Abstract

Cited

Shared

Discussed