基于二分类NMF网络的执行器故障状态评估

doi:10.16182/j.issn1004731x.joss.20-0319

摘要/Abstract

摘要： 针对反馈控制回路中,控制器的调节能力会在一定程度上掩盖执行器的性能下降的问题,提出一种基于二分类非负矩阵网络的故障状态评估算法,实现执行器的在线故障状态监控,包括故障分类和退化评估。该方法提取样本的局部静态特征,建立了分类器模型以形成网络;并且引入相似度来描述样本之间的动态特征。为实现执行器故障状态评估,融合网络输出的静态距离与动态变化,构建了故障判别指标和退化指标。通过双容水箱液位串级控制实验和基于DAMADICS平台的单回路仿真实验,证明了该算法的有效性。

关键词: 执行器, 非负矩阵分解, 故障诊断, 退化评估

Abstract: In the feedback control loop, the adjustment ability of controller covers up the performance degradation of the actuator to some degree. A fault state evaluation algorithm based on a two-class non-negative matrix network is proposed to implement online fault state monitoring of the actuator, including fault classification and degradation assessment. The local static features of the samples are extracted, and a classifier model is established to form a network. The similarity is introduced to describe the dynamic characteristics between samples. To fulfill the actuator fault status assessment, the static distance and dynamic changes of the network output are merged to construct the fault discrimination index and degradation index. The effectiveness of the algorithm is proved by the experiment of double-tank tank liquid level cascade control and the single loop simulation based on DAMADICS platform.

Key words: actuator, non-negative matrix factorization, fault diagnosis, degradation assessment

中图分类号:

王印松, 孙天舒. 基于二分类NMF网络的执行器故障状态评估[J]. 系统仿真学报, 2021, 33(8): 1882-1891.

Wang Yinsong, Sun Tianshu. Actuator Fault Status Evaluation Based on Two-Class NMF Network[J]. Journal of System Simulation, 2021, 33(8): 1882-1891.

参考文献

[1] Shi H, Li P, Su C, et al.Robust Constrained Model Predictive Fault-tolerant Control for Industrial Processes with Partial Actuator Failures and Interval Time-varying Delays[J]. Journal of Process Control (S0959-1524), 2019, 75: 187-203.
[2] Jia Q, Zhang Y, Chen W.Simultaneous Fault Detection and Isolation Based on Transfer Semi-nonnegative Matrix Factorization[J]. Ind. Eng. Chem. Res (S0888-5885), 2019, 58(19): 8184-8194.
[3] Lee D D, Seung H S.Algorithms for Non-negative Matrix Factorization[C]// Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2000: 556-562.
[4] Ding C, Li T, Jordan M I.Convex and Semi-nonnegative Matrix Factorizations[J]. IEEE Trans Pattern Anal Mach Intell (S0162-8828), 2010, 32(1): 45-55.
[5] 何俊, 杨世锡, 甘春标. 一类滚动轴承振动信号特征提取与模式识别[J]. 振动, 测试与诊断, 2017, 37(6): 1181-1186, 1281.
He Jun, Yang Shixi, Gan Chunbiao.Feature Extraction and Pattern Recognition of Vibration Signals in a Rolling Bearing[J]. Journal of Vibration, Meaturement & Diagnosis, 2017, 37(6): 1181-1186, 1281.
[6] 全聪, 李晨亮, 吴黎兵. 基于二阶段迭代的非负矩阵分解的分类模型[J]. 武汉大学学报(理学版), 2020, 66(2): 190-196.
Quan Cong, Li Chenliang, Wu Libing.2-STGNMF: Supervised 2-Stage Iterative Nonnegative Matrix Factorization Model for General Classification[J]. Journal of Wuhan University(Natural Science Edition), 2020, 66(2): 190-196.
[7] 刘国庆, 卢桂馥, 张强. 一种稀疏图正则化的非负低秩矩阵分解算法[J]. 重庆邮电大学学报(自然科学版), 2020, 32(2): 295-303.
Liu Guoqing, Lu Guifu, Zhang Qiang.A Non-negative Low-rank Matric Factorization Algorithm for Regularization of Sparse Graphs[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2020, 32(2): 295-303.
[8] 黄鹏飞, 孔祥兵, 景海涛. 一种改进的高光谱解混非负矩阵分解初始化方法[J]. 激光与光电子学进展, 2020, 57(6): 219-226.
Huang Pengfei, Kong Xiangbing, Jing Haitao.Improved Hyperspectral Unmixed Initialization Method based on Non-negative Matrix Factorization[J]. Laser & Optoelectronics Progress, 2020, 57(6): 219-226.
[9] 高茂庭, 王正欧. 几种文本特征降维方法的比较分析[J]. 计算机工程与应用, 2006(30): 157-159.
Gao Maoting, Wang Zheng'ou.Comparing Dimension Reduction Methods of Text Feature Matrix[J]. Computer Engineering and Applications, 2006(30): 157-159.
[10] 李煜, 何世钧. 基于投影梯度的非负矩阵分解盲信号分离算法[J]. 计算机工程, 2016, 42(2): 104-107, 112.
Li Yu, He Shijun.Blind Signal Separation Algorithm for Non-negative Matrix Factorization based on Projected Gradient[J]. Computer Engineering, 2016, 42(2): 104-107, 112.
[11] 殷海青, 刘红卫. 一种基于L1稀疏正则化和非负矩阵分解的盲源信号分离新算法[J]. 西安电子科技大学学报, 2010, 37(5): 835-841.
Yin Haiqing, Liu Hongwei.New Blind Source Separation Algorithm based on L1 Sparse Regularization and Nonnegative Matrix Factorization[J]. Journal of Xidian University, 2010, 37(5): 835-841.
[12] 朱晓洁. 基于稀疏性非负矩阵分解的滚动轴承复合故障诊断[J]. 中国工程机械学报, 2018, 16(6): 553-558.
Zhu Xiaojie.Fault Diagnosis of Bear's Compound Fault Based on Sparse No-negative Matrix Factorization[J]. Chinese Journal of Construction Machinery, 2018, 16(6): 553-558.
[13] 牛玉广, 王世林, 林忠伟, 等. 基于多元统计过程监控的锅炉过程故障检测[J]. 动力工程学报, 2017, 37(10): 829-836.
Niu Yuguang, Wang Shilin, Lin Zhongwei, et al.Fault Detection of Industrial Processes Based on Multivariate Statistical Process Monitoring[J]. Journal of Chinese Society of Power Engineering, 2017, 37(10): 829-836.
[14] 成洁, 李思燃. 基于递归图和局部非负矩阵分解的轴承故障诊断[J]. 工矿自动化, 2017, 43(7): 81-85.
Cheng Jie, Li Siran.Bearing Fault Diagnosis based on Recurrence Plots and Local Non-negative Matrix Factorization[J]. Industry and Mine Automation, 2017, 43(7): 81-85.
[15] Rai A, Upadhyay S H.The Application of Semi-nonnegative Matrix Factorization for Detection of Incipient Faults in Bearings[J]. Proc Inst Mech Eng Part C J Mech Eng Sci (S0954-4062), 2019, 233(13): 4543-4555.