Multi-sensor Information Fusion Fault Diagnosis Based on Improved Evidence Theory

Abstract

Abstract:

Aiming at conflict evidence resulting from uncertainty of sensor signals, a new multi-sensor information fusion fault diagnosis approach was proposed based on improved evidence theory. Firstly, a method to create original evidence was put forward using genetic neural network, where genetic algorithm was used to optimize neural network parameters so as to enhance the training speed. Secondly, vector space and direction similarity were defined and classification rule function was built to distinguish conflict evidence and similar evidence. Credibility modified conflict evidence to decrease the conflict effect from uncertainty. Finally, gear pump fault tests prove the validity of improved method, whose diagnosis precision is higher than that of single sensor diagnosis evidently. The threshold setup increases the flexibility and applicability.

Key words: evidence theory, genetic neural network, conflicting evidence, fault diagnosis

摘要：

针对传感器信号不确定会产生冲突证据的问题,提出了一种基于改进证据理论的多传感器信息融合故障诊断方法。提出了基于遗传神经网络的原始证据生成方法，利用遗传算法优化神经网络参数，提高网络训练速度;定义了向量空间和方向相似度，利用分类准则函数区分冲突证据和相似证据，通过可信度修正冲突证据，降低了因不确定性产生的冲突对合成结果的影响。通过齿轮泵故障实验验证了改进方法的有效性,改进方法的诊断正确率明显高于单一传感器的诊断正确率，并通过设置适当的阈值提高了方法的灵活性和适用性。

关键词: 证据理论, 遗传神经网络, 冲突证据, 故障诊断

CLC Number:

TP391

Liu Xiliang, Chen Guiming, Li Fangxi, Zhang Qian. Multi-sensor Information Fusion Fault Diagnosis Based on Improved Evidence Theory[J]. China Mechanical Engineering, 2014, 25(10): 1341-1345.

刘希亮, 陈桂明, 李方溪, 张倩. 基于改进证据理论的多传感器信息融合故障诊断[J]. 中国机械工程, 2014, 25(10): 1341-1345.

References

[1]Dempster A P.Upper and Lower Probabilities Induced by a Multi-valued Mapping[J].Ann. Mathematical Statistics, 1967, 38(4):325-339.
[2]Shafer G.A Mathematical Theory of Evidence[M].Princeton:Princeton Univ. Pr.,1976.
[3]艾波,胡军,张早校,等.含缺陷蒸汽发生器管道爆破压力预测的遗传-神经网络算法[J].西安交通大学学报,2011,45(9):84-89.
Ai Bo,Hu Jun,Zhang Zaoxiao,et al.GA-BP Algorithm Based on Burst Pressure Prediction of Steam Generator Trbing[J]. Journal of Xi’an JiaoTong University,2011,45(9):84-89.
[4]Luo Jianfei,Lin Weitie,Cai Xiaolong,et al.Optimization of Fermentation Media for Enhancing Nitrite-oxidizing Activity by Artificial Neural Network Coupling Genetic Algorithm[J].Chinese Journal of Chemical Engineering,2012,20(2):950-957.
[5]饶泓,扶名福,谢明祥,等.基于决策级信息融合的设备故障诊断方法研究[J].中国机械工程,2009,20(4):433-437.
Rao Hong,Fu Mingfu,Xie Mingxiang,et al.Research on the Equipment Fault Diagnosis on the Basis of Decision Level Information Fusion[J].China Mechanical Engineering,2009,20(4):433-437.
[6]陈果,陈立波,宋兰琪.一种磨损故障融合诊断新方法及其应用[J].机械科学与技术,2009,28(9):1157-1161.
Chen Guo,Chen Libo,Song Lanqi.A New Approach to Fusion Diagnosis of Wear Fault and Its Application[J].Mechanical Science and Technology for Aerospace Engineer,2009,28(9):1157-1161.
[7]王檀彬,陈无畏,焦俊,等.多传感器融合的智能车辆导航研究[J].中国机械工程,2009,20(11):1381-1385.
Wang Tanbin,Chen Wuwei,Jiao Jun,et al.Study on Navigation of Intelligent Vehicles Based on Multi-sensor Fusion[J]. China Mechanical Engineering,2009,20(11):1381-1385.
[8]Murphy C K.Combining Belief Functions When Evidence Conflicts[J].Decision Support Systems,2000,29(1):1-9.
[9]孙全,叶秀清,顾伟康.一种新的基于证据理论的合成公式[J].电子学报,2000,28(8):117-119.
Sun Quan,Ye Xiuqing,Gu Weikang.A New Combination Rules of Evidence Theory[J].Acta Electronica Sinica, 2000, 28(8): 117-119.
[10]邓勇,施文康,朱振福.一种有效处理冲突证据的组合方法[J].红外与毫米波学报,2004,23(1):27-32.
Deng Yong,Shi Wenkang,Zhu Zhenfu.Efficient Combination Approach of Conflict Evidence[J].Journal Infrared Millimeter Waves, 2004,23(1):27-32.
[11]熊彥铭,杨战平,屈新芬.基于模型修正的冲突证据组合新方法[J].控制与决策,2011,26(6):883-887.
Xiong Yanming,Yang Zhanping,Qu Xinfen.Novel Combination Method of Conflict Evidence Based on Evidential Model Modification[J].Control and Decision,2011,26(6):883-887.

[1]	LUO Ji-Sai, XU De-Ge, SHI Mei-Li. Gearbox Fault Diagnosis with Rotating Speed Fluctuation Based on SVD and Chirplet Path Pursuit Algorithm [J]. J4, 201016, 21(16): 1947-1951.
[2]	ZHENG Jinde, WANG Xinglong, PAN Haiyang, TONG Jinyu, LIU Qingyun. Rolling Bearing Fault Diagnosis Method Based on Adaptive Autogram [J]. China Mechanical Engineering, 2021, 32(07): 778-785，792.
[3]	CHEN Huanguo, LIU Peijun, YU Hang, XIAO Xue. Identification of Fault Degree of Oil Filter Blockage in Electro-hydraulic Actuator Based on an Improved PCA-SOM [J]. China Mechanical Engineering, 2021, 32(07): 799-805.
[4]	DING Jiaxin ;WANG Zhenya ;YAO Ligang ;CAI Yongwu. Rolling Bearing Fault Diagnosis Based on GCMWPE and Parameter Optimization SVM [J]. China Mechanical Engineering, 2021, 32(02): 147-155.
[5]	YANG Luhang1;LI Baoqing1;WANG Ping2,3;WANG Jian2,3;YANG Yu1. Fault Diagnosis Method of Rolling Bearings Based on Probability Output Flexible Convex Hull [J]. China Mechanical Engineering, 2021, 32(01): 40-46.
[6]	WAN Shuting;PENG Bo;WANG Xiaolong. Early Fault Diagnosis Method of Rolling Bearings Based on DTD Transform-SCS Method [J]. China Mechanical Engineering, 2020, 31(23): 2829-2836.
[7]	MENG Zong;LIU Zihan;LYU Meng. Fault Diagnosis for Rolling Bearings Based on Improved Singular Value Decomposition and Spectral Kurtosis [J]. China Mechanical Engineering, 2020, 31(20): 2420-2428.
[8]	WANG Zhenya;YAO Ligang. Rolling Bearing Fault Diagnosis Method Based on Generalized Refined Composite Multiscale Sample Entropy and Manifold Learning [J]. China Mechanical Engineering, 2020, 31(20): 2463-2471.
[9]	LIU Xin1;GONG Min1;ZHOU Zhenhua1;LI Baotong2;DONG Jianye1. An Efficient Mechanical Structure Reliability Analysis Method Based on Evidence Theory [J]. China Mechanical Engineering, 2020, 31(17): 2031-2037.
[10]	CAI Yanping;FAN Yu;CHEN Wan;ZHANG Jinming. Applications of Improved Time-frequency Analysis and Feature Fusion in Fault Diagnosis of IC Engines [J]. China Mechanical Engineering, 2020, 31(16): 1901-1911.
[11]	JIANG Shaofei;WU Tianji;PENG Xiang;LI Jiquan;LI Zhi;SUN Tao. Data Driven Fault Diagnosis Method Based on XGBoost Feature Extraction [J]. China Mechanical Engineering, 2020, 31(10): 1232-1239.
[12]	CHEN Xuefeng, GUO Yanjie, XU Caibin, SHANG Hongbing. Review of Fault Diagnosis and Health Monitoring for Wind Power Equipment [J]. China Mechanical Engineering, 2020, 31(02): 175-189.
[13]	LIU Yang;LIU Xiaobo;LIANG Shan. Aeroengine Rotor Fault Diagnosis Based on Fourier Decomposition Method [J]. China Mechanical Engineering, 2019, 30(18): 2156-2163.
[14]	LI Congzhi;ZHENG Jinde;PAN Haiyang;LIU Qingyun. Fault Diagnosis Method of Rolling Bearings Based on Refined Composite Multiscale Dispersion Entropy and Support Vector Machine [J]. China Mechanical Engineering, 2019, 30(14): 1713-1719,1726.
[15]	LIU Zhaolun1,2;ZHANG Chunlan2;WU You2;WANG Haiyu2;LIU Bin1,2. An Incremental Bayesian Algorithm on Fault Diagnosis of Grate Coolers [J]. China Mechanical Engineering, 2019, 30(10): 1163-1171.