A rolling bearing fault diagnosis method based on improved Aquila optimization algorithm to optimize LSTM

PDF(3876 KB)

Journal of Vibration and Shock ›› 2024, Vol. 43 ›› Issue (23) : 144-154.

WANG Yan1, WANG Xinfa1, WANG Yanfeng1, GU Xiaoguang2, SUN Junwei1

Author information +

History +

Abstract

Aiming at the problem that Aquila optimizer (AO) is prone to local optimization and the accuracy of long short-term memory (LSTM) network is affected by parameters, a model of LSTM neural network based on improved Aquila optimizer （IAO） algorithm is proposed and applied to the fault diagnosis of rolling bearings. Firstly, the hypercube strategy is introduced to optimize the initial mass of the population, and the adaptive spiral strategy is designed to balance the global search ability and local search ability of AO algorithm, and the ability of AO algorithm to jump out of the local optimal is enhanced by using Gaussian mutation strategy. Then, the weights and thresholds of LSTM are optimized by the proposed IAO algorithm, and a rolling bearing fault diagnosis model based on IAO-LSTM network is constructed. Finally, the experimental results of Case Western Reserve University (CWRU) bearing data set and Paderborn University (PU) bearing data set show that compared with other fault diagnosis models, the IAO-optimized LSTM model has higher classification accuracy and can effectively identify various fault types of rolling bearings.

Key words

fault diagnosis / Aquila optimizer algorithm / adaptive spiral search / hypercube strategy / LSTM neural network;

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

WANG Yan1, WANG Xinfa1, WANG Yanfeng1, GU Xiaoguang2, SUN Junwei1. A rolling bearing fault diagnosis method based on improved Aquila optimization algorithm to optimize LSTM[J]. Journal of Vibration and Shock, 2024, 43(23): 144-154

References

[1] Yan X A, Jia M P, Zhang W, et al. Fault diagnosis of rolling element bearing using a new optimal scale morphology analysis method [J]. ISA Trans. 2018, 73:165–180.
[2] 边旭,田璧菀,靳世久.基于机器学习的在轨航天器泄漏源实时定位方法研究[J].振动与冲击,2023,42(15):319-324.
BIAN Xu, TIAN Bi-wan, JIN Shi-jiu. Research on real-time location method of leakage source for in-orbit spacecraft based on Machine Learning [J]. Journal of Vibration and Shock,2023,42(15):319-324.
[3] Yang Y G, Nie W F. Earth orientation parameters prediction based on the hybrid SSA + LS SVM model [J]. Measurement Science and Technology. 2022,33:1-15.
[4] Ping W, Hu G H, et al. Blob properties in I-mode and ELM-free H-mode compared to L-mode on EAST [J]. Plasma Science and Technology. 2023; 25:60-69.
[5] Wang S H, Xiang J W, Zhong Y T, et al. A data indicator-based deep belief networks to detect multiple faults in axial piston pumps [J]. Mech Syst Signal Process.2018,112:154–170.
[6] 李昕燃,靳伍银.基于改进麻雀算法优化支持向量机的滚动轴承故障诊断研究[J].振动与冲击,2023,42(06):106-114.
LI Xin-ran, JIN Wu-yin. Research on rolling bearing Fault Diagnosis Based on Improved Sparrow Algorithm and Optimized support Vector Machine [J]. Journal of Vibration and Shock, 2019,42(06):106-114.
[7] Noh S H. Analysis of gradient vanishing of RNNs and performance comparison [J]. Information. 2021,12:1-11.
[8] 王继选,胡润志,管一等.基于RFOA优化GRNN的水电机组振动预测[J].振动与冲击,2021,40(21):120-126
WANG Ji-xuan, HU Run-zhi, GUAN Yi, et al. Vibration prediction of hydropower unit based on RFOA-GRNN [J]. Journal of Vibration and Shock, 2021,40(21):120-126.
[9] An Y Y, Zhang K. Rolling bearing fault diagnosis method base on periodic sparse attention and LSTM [J]. IEEE Sensors Journal. 2022,22:12044-12053.
[10] Zou P, Hou B C. Bearing fault diagnosis method based on EEMD and LSTM [J]. International Journal Of Computers Communications. 2020,15:1-14.
[11] Gu K, Zhang Y. DWT-LSTM-based fault diagnosis of rolling bearings with multi-sensors [J]. Electronics. 2021,10:1-13.
[12] Zheng J B, Liao J. End-to-end continuous / discontinuous feature fusion method with attention for rolling bearing fault diagnosis [J]. Sensors. 2022, 22:1-16.
[13] Seyedzadeh S, Rahimian F P, Rastogi P. Tuning machine learning models for prediction of building energy loads [J]. Sustain Cities Soc. 2019, 47:1-18.
[14] 杨海明. 基于改进天鹰算法的ENN神经网络模型优化压力容器参数研究[D].太原科技大学,2024.
YANG Hai-ming. Research on optimization of pressure vessel parameters by ENN neural network model based on improved Tianying algorithm [D]. Taiyuan University of Science and Technology,2024.
[15] 张健忠. 基于改进天鹰优化算法结合LSTM的混凝投药预测研究[D].昆明理工大学,2023.
ZHANG Jian-zhong. Prediction of coagulant administration based on improved Tianying optimization algorithm combined with LSTM [D]. Kunming University of Science and Technology,2023.
[16] Abualigah L, Yousri D, Elaziz M A, et al. Matlab code of Aquila optimizer: a novel meta-heuristic optimization algorithm [J]. Computers Industrial Engineering. 2021; 157:1-37.
[17] 张金,陈克坚,曾永平等.基于改进拉丁超立方抽样的高墩铁路桥梁地震可靠度分析方法[J].铁道学报,2024,1:1-11.
ZHANG Jin, CHEN Ke-jian, ZENG Yong-ping et al. Seismic reliability Analysis method for high-pier railway Bridges based on improved Latin Hypercube sampling [J]. Journal of Railways,2024,1:1-11.
[18] Li M, Xu G, Fu Y, et al. Improved whale optimization algorithm based on variable spiral position update strategy and adaptive inertia weight[J]. Journal of Intelligent & Fuzzy Systems, 2022, 42(3): 1501-1517.
[19] 郑直,张华钦,潘月.基于改进鲸鱼算法优化LSTM的滚动轴承故障诊断[J].振动与冲击,2021,40(07):274-280.
ZHENG Zhi, ZHANG Hua-qin, Pan Yue. Fault Diagnosis of Rolling Bearings Based on Improved Whale Algorithm for LSTM Optimization [J]. Journal of Vibration and Shock,2021,40(07):274-280.
[20] Jamil M, Yang X S, Zepernick H J. Test functions for global optimization: a comprehensive survey [J]. Swarm Intelligence and Bio-Inspired Computation. 2013, 8:193–222.
[21] 陈卓,田洋阳,马田田等.基于天鹰优化器（AO）算法的气田管网布局优化[J].当代化工,2022,51(12):2898-2902.
CHEN Zhuo, TIAN Yang-yang MA Tian-tian, et al. Gas field pipe network layout optimization based on Tian ying Optimizer (AO) algorithm [J]. Contemporary chemical industry. 2022,12:1-7.
[22] 李雅梅,孟嗣博,陈雪莲.多策略改进的天鹰优化算法及其应用[J].计算机应用研究,2023,40(05):1352-1359.
Li Ya-mei, MENG Si-bo, CHEN Xue-lian. Improved Aquila
multi-strategy optimization algorithm and its application [J].
Computer application research. 2023; 2:1352-1359.
[23] 李红月,高英杰,朱文昌.IAO优化SVM的电机滚动轴承故障诊断[J].电子测量技术,2022,45(10):126-132.
LI Hong-yue, GAO Ying-jie, Zhu Wen-chang . IAO optimization of rolling bearing fault diagnosis of the SVM [J]. Journal of electronic measurement technology. 2022; 10: 126-132.
[24] 刘福康,杨光永,王林等.基于IAO-MCKD的电机轴承故障诊断[J].组合机床与自动化加工技术,2022,(08):71-74.
LIU Fu-kang, Yang Guang-yong, Wang Lin. Fault Diagnosis of Motor Bearing Based on IAO-MCKD [J]. Modular Machine Tool & Automatic Manufacturing Technology. 2022; 8:71-74.
[25] Avci C, Tekinerdogan B, Catal C. Analyzing the performance of long short-term memory architectures for malware detection models [J]. Concurrency And Computation-Practice. 2023,35:1-15.
[26] Ma J, Wang X. Compound fault diagnosis of rolling bearing based on ACMD, Gini index fusion and AO-LSTM[J]. Symmetry, 2021, 13: 2386.
[27] Sun H, Cao X, Wang C, et al. An interpretable anti-noise network for rolling bearing fault diagnosis based on FSWT[J]. Measurement, 2022, 190: 1-15.