Industrial process fault diagnosis based on SSAE-IARO-BiLSTM

被引：0

作者：

Zhang, Ruicheng ^{[1
]}

Sun, Weiliang ^{[1
]}

Liang, Weizheng ^{[1
]}

机构：

[1] College of Electrical Engineering, North China University of Science and Technology, Tangshan

来源：

Zhendong yu Chongji/Journal of Vibration and Shock | 2024年 / 43卷 / 15期

关键词：

bidirectional long short-term memory (BiLSTM) network; fault diagnosis; improved artificial rabbit optimization (IARO); stacked sparse auto-encoder (SSAE);

D O I：

10.13465/j.cnki.jvs.2024.15.028

中图分类号：

学科分类号：

摘要：

Here, aiming at the problem of low fault diagnosis accuracy of industrial process, a fault diagnosis method based on a stacked sparse auto-encoder (SSAE) network and improved artificial rabbit algorithm-optimized bidirectional long short-term memory (IARO-BiLSTM) neural network was proposed. Firstly, the powerful feature extraction ability of SSAE network was used to reduce dimensions of original data. Secondly, Circle chaotic map was introduced to reach the purpose of enriching population, and weight coefficient and Levy flight mechanism were proposed to improve the position update formula of the artificial rabbit algorithm and the optimization ability of the artificial rabbit algorithm, and then optimize parameters of BiLSTM network. Finally, the optimized BiLSTM network was used to identify and classify faults. By selecting multiple groups of data sets for verification, the results showed that the fault diagnosis method based on SSAE-IARO-BiLSTM can correctly identify and classify faults of industrial process, and the diagnosis correct rate can reach more than 98%. © 2024 Chinese Vibration Engineering Society. All rights reserved.

引用

页码：244 / 250and260

共 21 条

[1]

Wang R.J., Zhan Y.J., Zhou H.F., Et al., A fault diagnosis method for three-phase rectifiers [J], International Journal of Electrical Power & Energy Systems, 52, pp. 266-269, (2013)

[2]

Wang L., Wei Y., Liu Y., Et al., Transformer fault identification method based on KPCA and IPFA-KELM [J], Control Engineering of China, 30, 7, pp. 1180-1189, (2023)

[3]

Zhang R., Liu L., Liang W., Torsional vibration prediction on tandem cold rolling mill based on SSAE-LSTM [J], Forging & Stamping Technology, 48, 4, pp. 193-198, (2023)

[4]

Zhang P., Shu X., Li X., Et al., LSTM-based fault diagnosis of AC electric machine system [J], Electric Machines and Control, 26, 3, pp. 109-116, (2022)

[5]

Xie J., Jiang Y., Wang L., RA-LSTM based bearing fault diagnosis method [J], Journal of Electronic Measurement and Instrument, 36, 6, pp. 213-219, (2022)

[6]

Nacer S.M., Nadia B., Abdelghani R., Et al., A novel method for bearing fault diagnosis based on BiLSTM neural networks [J], The International Journal of Advanced Manufacturing Technology, 125, 3-4, pp. 1477-1492, (2023)

[7]

Liu Z., Zhong Y., Interpretable bearing fault diagnosis based on CNN-BiLSTM [J], Modular Machine Tool & Automatic Manufacturing Technique, 9, pp. 59-63, (2022)

[8]

Attouri K., Mansouri M., Hajji M., Et al., Wind power converter fault diagnosis using reduced kernel PCA-based BiLSTM [J], Sustainability, 15, 4, (2023)

[9]

Wei J., Guo H., Damage identification of transmission tower based on BO-BiLSTM model [J], Journal of Vibration and Shock, 42, 1, pp. 238-248, (2023)

[10]

Lu X., Shi C., Application of the P-box theory and HGWO-SVM in the fault diagnosis of rolling bearings [J], Journal of Vibration and Shock, 40, 22, pp. 234-241, (2021)

← 1 2 3 →