锻压技术

基于Deform 3D的风机主轴空心轴预制坯成形优化

英文标题：Propagation path identification on faults in finishing rolling process based on HMM and BN

作者：梁卫征1 崔凯鑫2 张瑞成1

分类号：TP277

出版年,卷(期):页码：2023,48(12):163-169

摘要：

针对故障传播路径识别领域中基于数据的方法会造成变量间存在大量冗余连接的问题和基于知识的方法会造成变量间信息丢失的问题，提出隐马尔科夫模型与贝叶斯网络相结合的故障传播路径识别新方法。首先，将带钢热连轧过程知识构建为定性贝叶斯网络结构，通过主成分分析方法对带钢热连轧过程中的数据进行降维处理，以得到训练模型所需的观测序列；然后，根据降维后的正常历史数据及其对数似然值，建立贝叶斯网络进行传播路径识别所需的条件概率表；最后，将故障数据及其对数似然值作为贝叶斯网络进行识别故障传播路径的似然证据。实验结果表明，该方法能精准定位发生故障的6个变量，没有出现误诊和漏检的现象，且能准确识别故障的传播路径。

For the problems that there were a large number of redundant connections between the variables caused by data-based methods and the information loss between the variables caused by knowledge-based methods in the field of the propagation path identification on faults, a new method for the propagation path identification on faults that combined Hidden Markov Model (HMM) and Bayesian Network (BN) was proposed. First, the knowledge of the hot strip rolling process was constructed as a qualitative BN structure, and the dimensionality of the data in the hot strip rolling process was reduced by the principal component analysis method to obtain the observation sequence required for training model. Then, based on the normal historical data after dimensionality reduction and its log-likelihood value, the conditional probability table was established for BN to identify the propagation path. Finally, the fault data and their log-likelihood values were used as the likelihood evidence for BN to identify the fault propagation path. The experimental results show that this method can accurately locate the six variables where the fault occurs, without any misdiagnosis or missed detection, and can accurately identify the propagation path of faults.

基金项目：

河北省自然科学基金资助项目（F2018209201）；唐山市科技局科技计划项目（22130213G）；唐山市人才资助项目（B202302009）

作者简介：梁卫征（1982-），女，硕士，副教授 E-mail：330892162@qq.com 通信作者：张瑞成（1975-），男，博士，教授 E-mail：rchzhang@126.com

参考文献：

[1]Taqvi S A A, Zabiri H, Tufa L D, et al. A review on data-driven learning approaches for fault detection and diagnosis in chemical processes[J]. Chembioeng Reviews, 2021, 8(3):239-259.

[2]Ding S X. Data-driven Design of Fault Diagnosis and Fault-tolerant Control Systems [M]. London：Springer, 2014.

[3]Soleimani M, Campean F, Neagu D. Diagnostics and prognostics for complex systems: A review of methods and challenges[J]. Quality and Reliability Engineering International，2021, 37(8):3746-3778.

[4]Windmann S. Data-driven fault detection in industrial batch processes based on a stochastic hybrid process model[J]. IEEE Transactions on Automation Science and Engineering: A Publica-tion of the IEEE Robotics and Automation Society，2022,19(4) ：3888-3902.

[5]Sun Q L, Zhou Y, Li M D. Bearing operating state evaluation based on improved HMM[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2020,34(6)： 2059016.1-2059016.16.

[6]Dong L, Li W M, Wang C H, et al. Gyro motor fault classification model based on a coupled hidden Markov model with a minimum intra-class distance algorithm[J]. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, 2019, 234(5):646-661.

[7]Suo B, Zeng C, Cheng Y S, et al. An evidence theory-based algorithm for system reliability evaluation under mixed aleatory and epistemic uncertainties[J]. International Journal of Nonlinear Sciences and Numerical Simulation, 2014, 15(3/4):189-196.

[8]Liu Z K, Lyu K L, Zheng C, et al. A fault diagnosis method for rolling element bearings based on ICEEMDAN and Bayesian network[J]. Journal of Mechanical Science and Technology, 2022, 36(5):2201-2212.

[9]Cai B P, Liu Y H, Liu Z K, et al. Application of bayesian networks in quantitative risk assessment of subsea blowout preventer operations[J]. Risk Analysis, 2013, 33(7):1293-1311.

[10]Khakzad N. Application of dynamic Bayesian network to risk analysis of domino effects in chemical infrastructures[J]. Reliability Engineering & System Safety, 2015, 138:263-272.

[11]Wu W S, Yang C F, Chang J C, et al. Risk assessment by integrating interpretive structural modeling and Bayesian network, case of offshore pipeline project[J]. Reliability Engineering & System Safety, 2015, 142:515-524.

[12]Hanninen M, Banda O A V, Kujala P. Bayesian network model of maritime safety management[J]. Expert Systems with Applications, 2014, 41(17):7837-7846.

[13]马亮. 复杂工业过程质量相关故障的根源诊断与传播路径辨识[D]. 北京:北京科技大学, 2019.

Ma L. Root Cause Diagnosis and Propagation Path Identification of Quality-related Faults for Complex Industrial Processes[D]. Beijing:University of Science and Technology Beijing, 2019.

服务与反馈：

【文章下载】【加入收藏】