Fault Diagnosis Method of Piston Pump Based on Meta-Learning with Few Samples

HU Hongjun; YANG Xiwang; HUANG Jinying

Journal of North University of China(Natural Science Edition) > 2024 > 45(5): 592-600.

HU Hongjun, YANG Xiwang, HUANG Jinying. Fault Diagnosis Method of Piston Pump Based on Meta-Learning with Few Samples[J]. Journal of North University of China(Natural Science Edition), 2024, 45(5): 592-600.

Citation:

PDF (1812 KB)

Fault Diagnosis Method of Piston Pump Based on Meta-Learning with Few Samples

1. School of Computer Science andTechnology, North University of China;
2. School of Mechanical Engineering, North University of China

More Information

Received Date: December 31, 2023

Graphical Abstract

Abstract

Abstract

Addressing the issues of limited fault samples for piston pumps, weak fault signals under noise interference, and traditional deep learning’s heavy reliance on vast amounts of training data, we proposed a novel few-shot fault diagnosis approach for piston pumps based on model-agnostic meta-learning（MAML） with few samples. Firstly, the collected one-dimensional vibration signal was decomposed using improved complete ensemble empirical mode decomposition with adaptive noise（ICEEMDAN）, resulting in intrinsic mode function（IMF） components. Subsequently, sensitive components rich in fault information were selected to enhance the feature information within the vibration signal. Secondly, a multi-channel one-dimensional convolutional model was established, incorporating a channel interaction feature encoder equipped with an efficient channel attention mechanism. This design aimed to focus on the mutual fault information among different channels, thereby effectively extracting general diagnostic knowledge applicable to multiple diagnostic meta-tasks. Finally, the one-dimensional convolutional model served as the base model, which was trained through the MAML method to obtain optimal initial model parameters. Following this, the optimally initialized model could quickly adapt to new operating conditions with limited piston pump fault samples, thereby realizing few-shot fault diagnosis for piston pumps.The performance of the proposed model was validated using experimental data from piston pump tests.Experimental results demonstrate that the proposed method achieves an accuracy rate of over 90% across various diagnostic tasks under few-sample conditions.
- model agnostic meta-learning,
- few samples,
- attention mechanism,
- piston pump

FullText(HTML)

References (21)

References

[1]	高强,向家伟,汤何胜.基于增强聚类分割与L-峭度的Teager能量算子解调诊断轴向柱塞泵故障[J].机械工程学报,2018, 54(18):1-10.GAO Qiang, XIANG Jiawei, TANG Hesheng. Axial piston pump fault diagnosis with Teager energy operator demodulation using improved clustering-based segmentation and L-kurtosis[J]. Journal of Mechanical Engineering, 2018, 54(18):1-10.(in Chinese)
[2]	李春林,熊建斌,苏乃权,等.深度学习在故障诊断中的应用综述[J].机床与液压,2020, 48(13):174-184.LI Chunlin, XIONG Jianbin, SU Naiquan, et al.Application review of deep learning in fault diagnosis[J]. Machine Tools and Hydraulics, 2020, 48(13):174-184.(in Chinese)
[3]	ZHANG Tianci, CHEN Jinglong, LI Fudong, et al.Intelligent fault diagnosis of machines with small&imbalanced data:A state-of-the-art review and possible extensions, ISA Transactions[J]. 2022, 119:152-171.
[4]	FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C]//International Conference on Machine Learning,PMLR, 2017:1126-1135.
[5]	HOU X, XU J, WU J, et al. Cross domain adaptation of crowd counting with model-agnostic meta-learning[J]. Applied Sciences, 2021, 11(24):12037.
[6]	KANG J W, LIU R Q, LI L T, et al. Domain-invariant speaker vector projection by model-agnostic meta-learning[DB/OL].(2020-05-25)[2024-01-01]. http://arxiv.org/abs/2005. 11900.
[7]	FALLAH A, MOKHTARI A, OZDAGLAR A.Provably convergent policy gradient methods for model-agnostic meta-reinforcement learning[DB/OL].(2020-02-12)[2024-01-01]. http://arxiv. org/abs/2002. 05135v1.
[8]	ZHAO Z B, LI T F, WU J Y, et al. Deep learning algorithms for rotating machinery intelligent diagnosis:An open source benchmark study[J]. ISA Transactions, 2020, 107(10):224-255.
[9]	LIN J, SHAO H, ZHOU X, et al. Generalized MAML for few-shot cross-domain fault diagnosis of bearing driven by heterogeneous signals[J]. Expert Systems with Applications, 2023, 230:120696.
[10]	LUO J, SHAO H, LIN J, et al. Meta-learning with elastic prototypical network for fault transfer diagnosis of bearings under unstable speeds[J]. Reliability Engineering&System Safety, 2024, 245:110001.
[11]	颜丙生,刘兆亮,刘自然.小样本下基于元学习的跨机械部件故障诊断[J].组合机床与自动化加工技术,2022(10):136-140.YAN Bingsheng, LIU Zhaoliang, LIU Zirang.Research on fault diagnosis method of cross meachanical components based on meta learning under small sample[J]. Combined Machine Tools and Automated Processing Technology, 2022(10):136-140.(in Chinese)
[12]	LIU S, HUANG J, MA J, et al. Class-incremental continual learning model for plunger pump faults based on weight space meta-representation[J]. Mechanical Systems and Signal Processing, 2023, 196:110309.
[13]	卢欣欣,马骏,张英聪.基于连续小波变换和无模型元学习的小样本汽车行星齿轮箱故障诊断[J].机械传动,2022, 46(9):159-164.LU Xinxin, MA Jun, ZHANG Yingcong. Fault diagnosis of small sample automobile planetary gearboxes based on continuous wavelet transform and model agnostic meta learning[J]. Journal of Mechanical Transmission, 2022, 46(9):159-164.(in Chinese)
[14]	LI C, LI S, WANG H, et al. Attention-based deep meta-transfer learning for few-shot fine-grained fault diagnosis[J]. Knowledge-Based Systems, 2023,264:110345.
[15]	杨青,董岩松,吴东升,等.基于MTLSAM模型的小样本变工况轴承故障诊断[J].组合机床与自动化加工技术,2023(2):78-81.YANG Qing, DONG Yansong, WU Dongsheng,et al. Bearing fault diagnosis under variable working conditions based on MTLSAM model under small sample conditions[J]. Combined Machine Tools and Automated Processing Technology, 2023(2):78-81.(in Chinese)
[16]	祝钧桃,姚光乐,张葛祥,等.深度神经网络的小样本学习综述[J].计算机工程与应用,2021, 57(7):22-33.ZHU Juntao, YAO Guangle, ZHANG Gexiang,et al. Survey of few shot learning of deep neural network[J]. Computer Engineering and Applications,2021, 57(7):22-33.(in Chinese)
[17]	HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018:7132-7141.
[18]	ZHAO M, ZHONG S, FU X, et al. Deep residual shrinkage networks for fault diagnosis[J]. IEEE Transactions on Industrial Informatics, 2019, 16(7):4681-4690.
[19]	刘生政,张琳,曾祥辉,等.基于MED-EEMD和ELM的轴向柱塞泵松靴故障诊断研究[J].机电工程,2020, 37(3):241-246.LIU Shengzheng, ZHANG Lin, ZENG Xianghui,et al. Loose sliper fault diagbosis of axial piston pump based on MED-EEMD and ELM.[J]. Journal of Mechanical&Electrical Engineering, 2020, 37(3):241-246.(in Chinese)
[20]	马宏伟,张大伟,曹现刚,等.基于EMD的振动信号去噪方法研究[J].振动与冲击,2016, 35(22):38-40.MA Hongwei, ZHANG Dawei, CAO Xiangang,et al. Research on vibration signal denoising method based on EMD[J]. Journal of Vibration and Shock,2016, 35(22):38-40.(in Chinese)
[21]	窦慧,张凌茗,韩峰,等.卷积神经网络的可解释性研究综述[J].软件学报,2024, 35(1):159-184.DOU Hui, ZHANG Lingming, HAN Feng, et al.Survey on convolutional neural network interpretability[J]. Journal of Software, 2024,35(1):159-184.(in Chinese)