Fault diagnosis of rolling bearing based on an improved convolutional neural network using SFLA
LI Yibing1,2,MA Jianbo1,2,JIANG Li1,2
1.School of Mechanical and Electronic Engineering, Wuhan University of Technology, Wuhan 430070, China;
2.Hubei Digital Manufacturing Key Laboratory, Wuhan 430070, China
Abstract:In order to solve the problems of the convolutional neural network (CNN) used in rolling bearings fault diagnosis, such as more training times and uncertain network structure, etc., an algorithm for optimizing CNN based on shuffled frog leaping algorithms (SFLA-CNN) was designed in this paper, and the rolling bearing fault diagnosis model based on this algorithm was proposed.The model uses SFLA’s powerful global optimization ability and local depth search ability to optimize the CNN structure, and then uses the CNN model with optimal structure to extract low-dimensional fault features directly from the original vibration signal and inputs it into the Softmax classifier for faults identification.Compared with the BP neural network and the CNN, the experimental results show that the SFLA-CNN algorithm has higher accuracy and less training time.
李益兵1,2,马建波1,2,江丽1,2. 基于SFLA改进卷积神经网络的滚动轴承故障诊断[J]. 振动与冲击, 2020, 39(24): 187-193.
LI Yibing1,2,MA Jianbo1,2,JIANG Li1,2. Fault diagnosis of rolling bearing based on an improved convolutional neural network using SFLA. JOURNAL OF VIBRATION AND SHOCK, 2020, 39(24): 187-193.
[1]Lei Y, Lin J, He Z, et al. A review on empirical mode decomposition in fault diagnosis of rotating machinery[J]. Mechanical Systems & Signal Processing, 2013,35(1-2):108-126.
[2]S. Nandi, H. A. Toliyat, X. Li. Condition Monitoring and Fault Diagnosis of Electrical Motors—a Review[J]. IEEE Transactions on Energy Conversion, 2005,20(4):719-729.
[3] Hinton G, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[C]. Science, 2006, 313(5786): 504-507
[4]Tra Viet, Kim Jaeyoung,Khan Sheraz Ali, et al.Bearing Fault Diagnosis under Variable Speed Using Convolutional Neural Networks and the Stochastic Diagonal Levenberg-Marquardt Algorithm[J]. Sensors, 2017,17(12): 1-16
[5] Dezun Zhao, Tianyang Wang, Felei Chu. Deep convolutional neural network based planet bearing fault classification[J]. Computers in Industry, 2019,107:59-66
[6]张西宁,向宙,唐春华.一种深度卷积自编码网络及其在滚动轴承故障诊断中的应用[J]. 西安交通大学学报,2018,52(07):1-8.
Zhang Xining, Xxiang Zhou, Tang Chunhua. A Deep Convolution Auto Encoding Neural Network and Its Application in Bearing Fault Diagnosis[J]. Journal of Xi’an Jiaotong University, 2018,52(07):1-8
[7] Wen Long, Li Xinyu,Gao Liang, et al. A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method[J]. IEEE Transactions on Industrial Electronics, 2018,65(07):5990-5998
[8]周奇才,刘星辰,赵烔,等.旋转机械一维深度卷积神经网络故障诊断研究[J]. 振动与冲击,2018,37(23):31-37.
Zhou Qicai, Liu Xingchen, Zhao Jiong, et al. Fault diagnosis for rotating machinery based on 1D depth convolutional neural network[J]. Journal of Vibration and Shock, 2018,37(23):31-37.
[9]李恒,张氢,秦仙蓉,等.基于短时傅里叶变换和卷积神经网络的轴承故障诊断方法[J]. 振动与冲击,2018,37(19):124-131
Li Heng, Zhang Qing, Qin Xianrong, et al. Fault diagnosis method for rolling bearings based on short-time Fourier transform and convolution neural network[J]. Journal of Vibration and Shock, 2018,37(19):124-131.
[10]王宇,魏秀业基于混合蛙跳优化神经网络的轴承故障诊断研究[J]. 机械传动, 2017,05(41):127-131
Wang Yu, Wei Xiuye. Study on Fault Diagnosis Method of Bearing based on Shuffled Frog Leaping Algorithm to Optimize the BP Neural Network[J]. Journal of Mechanical Transmission, 2017,05(41):127-131
[11] Scardapane Simone, Van Vaerenbergh Steven,TotaroSimone, et al. Kafnets: Kernel-based non-parametric activation functions for neural networks[J]. Neural Networks, 2019,110:19-32
[12]吴春志,江鹏程,冯辅周,等. 基于一维卷积神经网络的齿轮箱故障诊断[J]. 振动与冲击,2018,37(22):51-56.
Wu Chunzhi, Jiang Pengcheng, FengFuzhou, et al. Faults diagnosis method for gearboxes based on a 1-D convolutional neural network[J]. Journal of Vibration and Shock, 2018,37(22):51-56
[13] Duy-Tang Hoanga, Hee-Jun Kang. Rolling element bearing fault diagnosis using convolutionalneural network and vibration image[J]. Cognitive Systems Research, 2019,53:42-50
[14]Yushi Chen, Zhouhan Lin, Xing Zhao, et al. Deep Learning-Based Classification of Hyperspectral Data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 07(06):2094-2107
[15] Eusuff Muzaffar, Lansey Kevin, Pasha Fayzul. Shuffled frog-leaping algorithm: a memetic meta-heuristic for discrete optimization[J]. Engineering Optimization, 2006,38(02):129-154
[16] Zhao Zhuanzhe, Xu Qingsong,Jia Minping. Improved shuffled frog leaping algorithm-based BP neural network and its application in bearing early fault diagnosis[J]. Neural Computing and Applications, 2016, 27(02):375-385
[17]http://csegroups.case.edu/bearingdatacenter/pages/welcome-case-western-reserve-university-bearing-data-center-website.
[18] 李巍华,单外平,曾学琼. 基于深度信念网络的轴承故障分类识别[J]. 振动工程学报,2016,29(2):340-347
Li Weihua, Shan Waiping, Zeng Xueqiong. Bearing fault identification based on deep belief network[J]. Journal of Vibration Engineering, 2016,29(2):340-347.