基于LSTM和CNN的高速柱塞泵故障诊断

魏晓良; 潮群; 陶建峰; 刘成良; 王立尧

doi:10.7527/S1000-6893.2020.23876

航空学报 >

2021 , Vol. 42 >Issue 3: 423876 - 423876

DOI: https://doi.org/10.7527/S1000-6893.2020.23876

材料工程与机械制造

基于LSTM和CNN的高速柱塞泵故障诊断

魏晓良 ,
潮群 ,
陶建峰 ,
刘成良 ,
王立尧

展开

上海交通大学机械系统与振动国家重点实验室, 上海 200240

收稿日期: 2020-02-14

修回日期: 2020-02-29

网络出版日期: 2020-05-21

基金资助

国家重点研发计划基金（2017YFD0700602）；中国博士后科学基金（2019M660086）

收起

Cavitation fault diagnosis method for high-speed plunger pumps based on LSTM and CNN

WEI Xiaoliang ,
CHAO Qun ,
TAO Jianfeng ,
LIU Chengliang ,
WANG Liyao

Expand

State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200240, China

Received date: 2020-02-14

Revised date: 2020-02-29

Online published: 2020-05-21

Supported by

National Key R&D Program of China (2017YFD0700602); China Postdoctoral Science Foundation (2019M660086)

Fold

摘要

针对高速轴向柱塞泵容易发生空化，且目前空化故障诊断方法存在依赖手工特征提取、鲁棒性不高的问题，提出了一种基于长短时记忆（LSTM）和一维卷积神经网络（1D-CNN）相结合的空化故障诊断方法。搭建了柱塞泵故障实验台，采集柱塞泵在不同空化等级下的壳体振动信号。利用LSTM和1D-CNN搭建的分类模型对不同进口压力情况下的振动信号进行空化等级识别。实验结果表明：提出的方法能够准确地识别出4类不同的空化等级，准确率高达99.5%，同时在不附加降噪方法的情况下，具有良好的鲁棒性，在0 dB信噪比的情况下，识别准确率高达87.3%。

关键词： 高速轴向柱塞泵; 空化等级识别; 长短时记忆; 卷积神经网络; 故障诊断

本文引用格式

魏晓良 , 潮群 , 陶建峰 , 刘成良 , 王立尧 . 基于LSTM和CNN的高速柱塞泵故障诊断[J]. 航空学报, 2021 , 42(3) : 423876 -423876 . DOI: 10.7527/S1000-6893.2020.23876

Abstract

Aiming at the cavitation of high-speed axial piston pumps and the drawbacks of conventional cavitation diagnosis methods such as relying on manual feature extraction and lack of robustness, this paper proposes a new method based on the combination of Long Short-Term Memory (LSTM) and one-Dimensional Convolutional Neural Network (1D-CNN). A test bench for axial piston pumps is built to collect the vibration signals of the pump housing at different cavitation levels. The classification network constructed by LSTM and CNN is used to identify the cavitation levels based on the vibration signals under different inlet pressure conditions. The experimental results show that the proposed method can accurately identify four different types of cavitation levels and that the accuracy rate can reach 99.5%. Furthermore, it has good robustness without the contribution of a noise reduction method. In the case of 0 dB signal to noise rate, the recognition accuracy is up to 87.3%.

Key words： high-speed axial piston pumps; cavitation intensity identification; long short-term memory (LSTM); convolutional neural network (CNN); fault diagnosis

参考文献

[1] CHAO Q, ZHANG J H, XU B, et al. Centrifugal effects on cavitation in the cylinder chambers for high-speed axial piston pumps[J]. Meccanica, 2019, 54(6):815-829.
[2] 孙泽刚. 斜盘式轴向柱塞泵缸体及配流盘抗空化研究[D]. 成都:西南交通大学, 2017:33-45. SUN Z G. Research on the anti-cavitation of the cylinder and valve plate of swash plate axial piston pump[D]. Chengdu:Southwest Jiaotong University, 2017:33-45(in Chinese).
[3] 潮群. EHA轴向柱塞泵高速化若干关键技术研究[D]. 杭州:浙江大学, 2019:107-127. CHAO Q. Research on some key technologies of high-speed rotation for axial piston pumps used in EHAs[D]. Hangzhou:Zhejiang University, 2019:107-127(in Chinese).
[4] 欧阳小平, 王天照, 方旭. 高速航空柱塞泵研究现状[J]. 液压与气动, 2018(2):1-8. OUYANG X P, WANG T Z, FANG X. Research status of the high speed aircraft piston pump[J]. Chinese Hydraulics & Pneumatics, 2018(2):1-8(in Chinese).
[5] 明廷锋, 曹玉良, 贺国, 等. 流体机械空化检测研究进展[J]. 武汉理工大学学报(交通科学与工程版), 2016, 40(2):219-227. MING T F, CAO Y L, HE G, et al. Research progress of cavitation detection of fluid machinery[J]. Journal of Wuhan University of Technology(Transportation Science & Engineering), 2016, 40(2):219-226(in Chinese).
[6] LIU R, YANG B, ZIO E, et al. Artificial intelligence for fault diagnosis of rotating machinery:A review[J]. Mechanical Systems and Signal Processing, 2018, 108:33-47.
[7] MCKEE K K, FORBES G, MAZHAR I, et al. A single cavitation indicator based on statistical parameters for a centrifugal pump[C]//Proceedings of the 7th World Congress on Engineering Asset Management (WCEAM 2012). Berlin:Springer, 2015:473-481.
[8] AZIZI R, ATTARAN B, HAJNAYEB A, et al. Improving accuracy of cavitation severity detection in centrifugal pumps using a hybrid feature selection technique[J]. Measurement, 2017, 108:9-17.
[9] SHERVANI-TABAR M T, ETTEFAGH M M, LOTFAN S, et al. Cavitation intensity monitoring in an axial flow pump based on vibration signals using multi-class support vector machine[J]. Proceedings of the Institution of Mechanical Engineers, Part C:Journal of Mechanical Engineering Science, 2018, 232(17):3013-3026.
[10] BORDOLOI D J, TIWARI R. Identification of suction flow blockages and casing cavitation in centrifugal pumps by optimal support vector machine techniques[J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2017, 39(8):2957-2968.
[11] KUMAR P A, SHRUTI R J, RAJIV T. Prediction of flow blockages and impending cavitation in centrifugal pumps using support vector machine (SVM) algorithms based on vibration measurements[J]. Measurement, 2018, 130:44-56.
[12] SIANO D, PANZA M A. Diagnostic method by using vibration analysis for pump fault detection[J]. Energy Procedia, 2018, 148:10-17.
[13] KOTB A, ABDULAZIZ A M. Cavitation detection in variable speed pump by analyzing the acoustic and vibration spectrums[J]. Engineering, 2015, 7(10):706.
[14] HINTON G, DENG L, YU D, et al. Deep neural networks for acoustic modeling in speech recognition[J]. IEEE Signal Processing Magazine, 2012, 29(6):82-97.
[15] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436.
[16] ZHANG W, LI C H, PENG G L, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical Systems and Signal Processing, 2018, 100:439-453.
[17] JIA F, LEI Y G, LU N, et al. Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization[J]. Mechanical Systems and Signal Processing, 2018, 110:349-367.
[18] WEN L, LI X Y, GAO L, et al. A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics, 2017, 65(7):5990-5998.
[19] XU C J, GUAN J J, BAO M, et al. Pattern recognition based on time-frequency analysis and convolutional neural networks for vibrational events in φ-OTDR[J]. Optical Engineering, 2018, 57(1):016103.
[20] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780
[21] 王鑫, 吴际, 刘超, 等. 基于LSTM循环神经网络的故障时间序列预测[J]. 北京航空航天大学学报, 2018, 44(4):772-784. WANG X, WU J, LIU C, et al. Exploring LSTM based recurrent neural network for failure time series prediction[J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(4):772-784(in Chinese).
[22] 于洋, 何明, 刘博, 等. 基于TL-LSTM的轴承故障声发射信号识别研究[J]. 仪器仪表学报, 2019, 40(5):51-59. YU Y, HE M, LIU B, et al. Research on acoustic emission signal recognition of bearing fault based on TL-LSTM[J]. Chinese Journal of Scientific Instrument, 2019, 40(5):51-59(in Chinese).
[23] SAINATH T N, VINYALS O, SENIOR A, et al. Convolutional, long short-term memory, fully connected deep neural networks[C]//2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Piscataway, NJ:IEEE, 2015:4580-4584.
[24] ORDÓÑEZ F J, ROGGEN D. Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition[J]. Sensors, 2016, 16(1):115.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献