基于SSAE-IARO-BiLSTM的工业过程故障诊断研究

张瑞成,孙伟良,梁卫征

振动与冲击 ›› 2024, Vol. 43 ›› Issue (15) : 244-250.

PDF(1099 KB)
PDF(1099 KB)
振动与冲击 ›› 2024, Vol. 43 ›› Issue (15) : 244-250.
论文

基于SSAE-IARO-BiLSTM的工业过程故障诊断研究

  • 张瑞成,孙伟良,梁卫征
作者信息 +

Industrial process fault diagnosis based on SSAE-IARO-BiLSTM

  • ZHANG Ruicheng, SUN Weiliang, LIANG Weizheng
Author information +
文章历史 +

摘要

针对工业过程故障诊断精度低的问题,提出了一种基于栈式稀疏自编码网络(stacked sparse Auto-encoder network,SSAE)和改进人工兔算法优化双向长短时记忆神经网络(improved artificial rabbit algorithm optimized bidirectional long short-term memory neural network,IARO-BiLSTM)的故障诊断方法。首先,利用SSAE网络强大的特征提取能力,实现对原始数据进行降维处理;其次,引入Circle混沌映射以达到丰富种群数量的目的,提出权重系数和Levy飞行机制改进人工兔算法的位置更新公式,提高人工兔算法的寻优能力,进而对BiLSTM网络的参数进行优化。最后,利用优化后的BiLSTM网络实现对故障的识别和分类。通过选取多组数据集进行验证,结果表明,基于SSAE-IARO-BiLSTM故障诊断方法能够准确地对故障进行识别和分类,且诊断准确率可达98%以上。

Abstract

Aiming at the problem of inaccuracy fault diagnosis of industrial processes, a fault diagnosis method based on a stacked sparse Auto-encoder network (SSAE) and improved artificial rabbit algorithm optimized Bidirectional Long Short-Term memory neural network (IARO-BiLSTM) was proposed. Firstly, the powerful feature extraction ability of the SSAE network was used to reduce the dimension of the original data. Secondly, the Circle chaotic map is introduced to achieve the purpose of enriching the population, and the weight coefficient and Levy flight mechanism are proposed to improve the position update formula of the artificial rabbit algorithm, improve the optimization ability of the artificial rabbit algorithm, and then optimize the parameters of the BiLSTM network. Finally, the optimized BiLSTM network was used to identify and classify faults. By selecting multiple sets of data sets for verification, the results show that the fault diagnosis method based on SSAE-IARO-BiLSTM can accurately identify and classify the fault, and the diagnosis accuracy can reach more than 98%.

关键词

故障诊断 / 人工兔算法 / 双向长短时记忆网络 / 栈式稀疏自编码器

Key words

fault diagnosis / Artificial rabbits optimization / Bi-directional long and short-term memory networks / stacked sparse autoencoder

引用本文

导出引用
张瑞成,孙伟良,梁卫征. 基于SSAE-IARO-BiLSTM的工业过程故障诊断研究[J]. 振动与冲击, 2024, 43(15): 244-250
ZHANG Ruicheng, SUN Weiliang, LIANG Weizheng. Industrial process fault diagnosis based on SSAE-IARO-BiLSTM[J]. Journal of Vibration and Shock, 2024, 43(15): 244-250

参考文献

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, 2013, 52: 266-269. 2. 王利福,魏玉琪,刘屹,江泽.基于KPCA与IPFA-KELM的变压器故障识别方法[J].控制工程,2023,30(07):1180-1189. Wang Lifu, Wei Yuqi, Liu Yi, Jiang Ze. Transformer Fault Identification Method Based on KPCA and IPFA-KELM [J]. Control Engineering of China, 2023, 30(07):1180-1189. 3. 张瑞成,刘力菲,梁卫征.基于SSAE-LSTM模型的冷连轧机扭振预测[J].锻压技术,2023,48(04):193-198. Zhang Ruicheng, Liu Lifei, Liang Weizheng, Torsional vibration prediction on tandem cold rolling mill based on SSAE-LSTM [J]. Forging & Stamping Technology, 2023, 48(04): 193-198. 4. 张鹏,束小曼,厉雪衣等.基于LSTM的交流电机系统故障诊断方法研究[J].电机与控制学报,2022,26(03):109-116. Zhang Peng, Shu Xiaoman, Li Xueyi, et al. LSTM-based fault diagnosis of AC electric machine system [J]. Electric Machines and Control, 2022,26(03): 109-116. 5. 谢锦阳,姜媛媛,王力.基于RA-LSTM的轴承故障诊断方法[J].电子测量与仪器学报,2022,36(06):213-219. Xie Mianyan, Jiang Yuanyuan, Wang Li. RA-LSTM based bearing fault diagnosis method [J]. Journal of Electronic Measurement and Instrument, 2022, 36(06): 213-219. 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, 2023, 125(3-4): 1477-1492. 7. 刘之航,钟玉华.基于CNN-BiLSTM的可解释性轴承故障诊断[J].组合机床与自动化加工技术,2022(09):59-63. Liu Zhihang, Zhong Yuhua. Interpretable Bearing Fault Diagnosis Based on CNN-BiLSTM [J]. Modular Machine Tool & Automatic Manufacturing Technique, 2022(09): 59-63. 8. Attouri K, Mansouri M, Hajji M, et al. Wind Power Converter Fault Diagnosis Using Reduced Kernel PCA-Based BiLSTM [J]. Sustainability, 2023, 15(4): 3191. 9. 魏佳恒,郭惠勇.基于贝叶斯优化BiLSTM模型的输电塔损伤识别[J].振动与冲击,2023,42(01):238-248. Wei Jiaheng, Guo Huiyong. Damage identification of transmission tower based on BO-BiLSTM model [J]. Journal of Vibration and Shock, 2023, 42(01): 238-248. 10. 路小娟,石成基.一种基于概率盒—HGWO优化SVM的滚动轴承故障诊断方法[J].振动与冲击,2021,40(22):234-241. Lu Xiaojuan, Shi Chengji. Application of the P-box theory and HGWO-SVM in the fault diagnosis of rolling bearings[J]. Journal of Vibration and Shock, 2021, 40(22): 234-241. 11. Xu X, Liu C, Zhao Y, et al. Short‐term traffic flow prediction based on whale optimization algorithm optimized BiLSTM Attention [J]. Concurrency and Computation: Practice and Experience, 2022, 34(10): e6782. 12. Wang L, Cao Q, Zhang Z, et al. Artificial rabbits optimization: A new bio-inspired meta-heuristic algorithm for solving engineering optimization problems [J]. Engineering Applications of Artificial Intelligence, 2022, 114: 105082. 13. Gülmez B. Stock price prediction with optimized deep LSTM network with artificial rabbits optimization algorithm[J]. Expert Systems with Applications, 2023, 227: 120346. 14. Hu G, Jing W, Houssein E H. Elite-based feedback boosted artificial rabbits-inspired optimizer with mutation and adaptive group: a case study of degree reduction for ball NURBS curves[J]. Soft Computing, 2023, 27(22): 16919-16957. 15. Cao Q, Wang L, Zhao W, et al. Vibration State Identification of Hydraulic Units Based on Improved Artificial Rabbits Optimization Algorithm[J]. Biomimetics, 2023, 8(2): 243. 16. 赵霞,张君毅,龙倩倩.基于Circle混沌映射的ISSA-ELM神经网络室内可见光定位方法[J].光学学报,2023,43(02):33-42. Zhao Xia, Zhang Junyi, Long Qianqian. Indoor Visible Light Positioning Method Using ISSA-ELM Neural Network Based on Circle Chaotic Mapping [J]. Acta Optica Sinica, 2023, 43(02): 33-42. 17. 张玉,卢子广,卢泉等.基于Levy飞行改进鸟群算法的光伏直流微电网优化配置研究[J].太阳能学报,2021,42(05):214-220. Zhang Yu, Lu Ziguang, Lu quan, et al. Research On Optimal Configuration Of Photovoltaic Dc Microgrid Based On Levy Flight Improved Bird Swarm Algorithm [J]. Acta Energiae Solaris Sinica, 2021, 42(05): 214-220. 18. 周围,孟凡钦,汪芮等.基于改进粒子群优化算法的气体源定位研究[J].传感器与微系统,2023,42(07):36-39. Zhou Wei, Meng Fanqin, Wang Rui, et al. Research on gas source localization based on improved PSO algorithm [J]. Transducer and Microsystem Technologies, 2023, 42(07): 36-39. 19. 张瑞成,白晓泽,董砚等.基于SSAE-LSTM神经网络的风电变流器开路故障诊断[J].可再生能源,2023,41(03):361-369. Zhang Ruicheng, Bai Xiaoze, Dong Yan, et al. Wind power converter fault diagnosis based on SSAE-LSTM network [J]. Renewable Energy Resources,2023, 41(03): 361-369. 20. 宋雪玮,赵吉文,董菲等.基于PSO-LSSVM的永磁同步直线电机局部退磁故障识别[J].中国电机工程学报,2019,39(08):2426-2435+25. Song Xuewei, Zhao Jiwen, Dong Fei, et al. Local Demagnetization Fault Recognition of Permanent Magnet Synchronous Linear Motor Based on PSO-LSSVM [J]. Proceedings of the CSEE, 2019, 39(08): 2426-2435+25. 21. 赵志宏,李晴,杨绍普等.基于BiLSTM与注意力机制的剩余使用寿命预测研究[J].振动与冲击,2022,41(06):44-50+196. Zhao Zhihong, Li Qing, Yang Shaopu, et al. Remaining useful life prediction based on BiLSTM and attention mechanism [J]. Journal of Vibration and Shock, 2022,41(06): 44-50+196.

PDF(1099 KB)

144

Accesses

0

Citation

Detail

段落导航
相关文章

/