Abstract:Operation reliability assessment of the specified equipment is an “individual problem”. In this paper, based on the characteristics of large and rich equipment operation data, from the perspective of evidence theory, combined with deep convolution auto encoder, a deep support evidence statistics method is proposed, which can be used to evaluate the operational reliability of mechanical equipment without prior knowledge such as failure sample information or distribution function. In the traditional feature acquisition process, a lot of manual intervention or prior knowledge is needed. Deep Sparse Auto Encoder (DSAE) is used to achieve automatic evidence acquisition, based on the idea of support vector data description (SVDD), the dynamic change process between calibration and process evidence is compared statistically, and finally the operation reliability evaluation of a specific equipment is completed. The reliability of aviation bearing is verified by the test results, which show that the reliability obtained by this method can better reflect the “individual character” of bearing.
肖文荣1,2,陈法法1,陈保家1. 基于深度支持证据统计的轴承运行可靠性评估[J]. 振动与冲击, 2022, 41(5): 60-66.
XIAO Wenrong1,2, CHEN Fafa1, CHEN Baojia1. Bearing operation reliability evaluation based on deep support evidence statistics. JOURNAL OF VIBRATION AND SHOCK, 2022, 41(5): 60-66.
[1] Zio E. Reliability engineering: Old problems and new challenges[J]. Reliability Engineering & System Safety, 2009, 94(2):125-141.
[2] 郑龙,杜永浩,邢立宁等.基于退化数据与marker数据综合的产品可靠性建模分析[J].控制与决策,2020,35(02):461-468.
ZHENG Long, DU Yonghao, XING Lining, et al. Product reliability modeling and analysis using degradation and marker data[J]. Control and Decision, 2020, 35(02):461-468.
[3] 张云,于广,王立平等.基于性能退化数据的数控转台单子样可靠性分析[J].清华大学学报(自然科学版), 2020,60(04):299-305.
ZHANG Yun, YU Guang, WANG Liping, et al. Performance degradation data based NC rotary table reliability predictions using a single sample[J]. Journal of Tsinghua University(Science and Technology), 2020,60(04):299-305.
[4]王新刚,杨禄杰,张鑫垚等.基于刚度退化的振动传递路径系统的可靠性分析[J].振动与冲击,2020,39(20):266-273.
WANG Xingang, YANG Lujie, ZHANG Xinyao, et al. Reliability sensitivity analysis of a vibration transfer path system based on stiffness degeneration[J]. Journal of Vibration and Shock, 2020, 39(20):266-273.
[5] 于繁华, 刘仁云, 张义民,等. 机械零部件动态可靠性稳健优化设计的群智能算法[J]. 吉林大学学报(工), 2017, 47(6):1903-1908.
YU Fanhua, LIU Renyun, ZHANG Xiaoli, et al. Swarm Intelligence Algorithm of Dynamic Reliability-based Robust Optimization Design of Mechanic Components[J]. Journal of Jilin University(Engineering), 2017, 47(6): 1903-1908.
[6] 贾庆轩, 李彤, 陈钢,等. 基于多层映射模型的空间机械臂运动可靠性影响因素灵敏度分析[J]. 机械工程学报, 2017, 53(11):10-19.
JIA Qingxuan, LI Tong, CHEN Gang, et al. Sensitivity Analysis on Factors Influencing Motion Reliability of Space Manipulator Based on Multilayer Mapping Model[J]. Journal of Mechanical Engineering, 2017, 53(11):10-19.
[7] 秦荦晟, 陈晓阳, 沈雪瑾. 小样本下基于竞争失效的轴承可靠性评估[J]. 振动与冲击, 2017, 36(23):248-254.
Reliability assessment of bearings based on competing failure under small sample data[J]. Journal of Vibration and Shock, 2017, 36(23):248-254.
[8] Dai W, Chi Y, Lu Z, et al. Research on Reliability Assessment of Mechanical Equipment Based on the Performance–Feature Model[J]. Applied Sciences, 2018, 8(9): 1619.
[9] 何正嘉, 曹宏瑞, 訾艳阳,等. 机械设备运行可靠性评估的发展与思考[J]. 机械工程学报, 2014, 50(2):171-186.
HE Zhengjia, CAO Hongrui, ZI Yanyang, et, al. Developments and Thoughts on Operational Reliability Assessment of Mechanical Equipment[J]. Journal of Mechanical Engineering, 2014, 50(2):171-186.
[10] 林云, 李一兵. 灰色关联和证据理论在故障识别中的应用和改进[J].应用基础与工程科学学报, 2011, 19(02): 314-322.
LIN Yun, LI Yibing. Application and Improvement of Gray Correlation and Evidence Theory in Fault Recognition[J]. Journal of Basic Science and Engineering, 2011, 19(02): 314-322.
[11] Dempster A P. Upper and lower probabilities induced by a multivalued mapping[J]. The Annals of Mathematical Statistics, 1967, 38(2): 325-339.
[12] 赵聪聪,赵颖慧,白杨,刘玉梅.基于可拓学和SVDD的轴箱轴承故障监测[J]. 振动与冲击,2020,39(04):63-68.
ZHAO Congcong ZHAO Yinghui BAI Yang, et al. Fault monitoring for axlebox bearing based on extenics and support vector data description[J]. Journal of Vibration and Shock, 2020, 39(04): 63-68.
[13] Tax DM, Duin RP. Support vector data description[J]. Machine learning, 2004, 54 (1): 45-66.
[14] David M. Tax. One-class classification; Concept-learning in the absence of counter-examples[J]. ASCI dissertation series, 2001, 65.
[15] 叶壮, 余建波. 基于多通道一维卷积神经网络特征学习的齿轮箱故障诊断方法[J]. 振动与冲击, 2020, 39(20): 55-66.
YE Zhuang, YU Jianbo. Gearbox fault diagnosis based on feature learning of multi-channel one-dimensional convolutional neural network, Journal of Vibration and Shock, 2020, 39(20): 55-66.
[16] 胡昭华, 宋耀良.基于Autoencoder网络的数据降维和重构[J].电子与信息学报, 2009, 31 (5) :1189-1192.
HU Zhaohua, SONG Yaoliang. Dimensionality reduction and reconstruction of data based on autoencoder network[J]. Journal of Electronics & Information Technology, 2009, 31 (5) :1189-1192.
[17] Yang X, Liu C Y, Wang Z W, et al.Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI[J].Medical Image Analysis, 2017, 42:212-227.
[18] Qiu H, Lee J, Lin J, et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics[J]. Journal of Sound & Vibration, 2006, 289(4–5):1066-1090.
[19] 姜洪开, 窦丹丹, 何正嘉. 基于自适应第二代小波的超声回波信号特征识别[J].西北工业大学学报, 2011, 29(01): 93-96.
JIANG Hongkai, DOU Dangdang, HE Zhangjia. A New Method for Identifying Ultrasonic Echo Signal Features Using Adaptive Second Generation Wavelet, Journal of Northwestern Polytechnical University, 2011, 29(01): 93-96.