基于模型诊断技术的神经网络实现方法

马纪明; 万蔚; 王法岩

基于模型诊断技术的神经网络实现方法

1.
北京航空航天大学中法工程师学院, 北京 100191
2. 北京航空航天大学可靠性与系统工程学院, 北京 100191

详细信息

中图分类号: TP277
计量
- 文章访问数: 1530
- HTML全文浏览量: 122
- PDF下载量: 665
- 被引次数: 0
出版历程
- 收稿日期: 2012-02-13
- 网络出版日期: 2013-02-28

Realization of model-based fault diagnosis with artificial neural network

1.
Sino-French Engineering School, Beijing University of Aeronautics and Astronautics, Beijing 100191, China
2. School of Reliability and Systems Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 针对基于模型的故障诊断流程中故障检测和故障识别两个关键问题,提出了一种基于神经网络的实现方法.首先利用BP神经网络进行参数估计,并结合系统模型进行故障检测;然后采用ART2神经网络进行数据聚类,并基于聚类结果进行系统故障识别;最后,设计实现了基于BP/ART2神经网络的故障诊断系统.基于BP神经网络的参数估计方法可以准确地估计诊断对象在不同状态下的参数,为故障检测提供有效依据;基于ART2神经网络的数据聚类不仅可以识别对象的已知故障类型,还可以识别出未知故障,对先验信息较少的系统进行故障识别更具有效性.通过永磁直流电机故障诊断案例的应用,证明方法能具有一定的工程实用性.
- 故障检测 /
- BP神经网络 /
- ART2神经网络 /
- 参数估计 /
- 数据聚类
Abstract: Based on artificial neural network, a method for fault detection and fault identification was proposed, which can be used during the model-based fault diagnosis (MBFD) process. Firstly, back-propagation (BP) neural network was presented for parameter estimation, combing with the system model, the faults can be detected. Then the adaptive resonance theory (ART2) neural network was used for data clustering, and based on the clustering results, the faults will be identified. Finally, a fault diagnostic system was developed based on BP&ART2 neural network. The presented BP-based parameters estimation method can estimate the parameters under different states accurately, which is important for the fault detection. ART2-based data clustering method can distinguish both the known and unknown fault modes, which is much efficient when diagnosing the system without enough priori information. A brushless direct current motor was selected as the application case, simulation result has proved that the presented method is available to estimate the motor parameters, detect and identify some typical faults, such as brushes position offset and armature open.
- fault detection /
- back-propagation (BP) neural network /
- adaptive resonance theory (ART2) neural network /
- parameter estimation /
- data cluster

HTML全文

参考文献(1)

[1] Rolf Isermann. Fault-diagnosis applications: model-based condition monitoring: actuators, drives, machinery, plants, sensors, and fault-tolerant system [M]. Germany: Springer, 2010 [2] 夏虹,刘永阔,谢春丽,等. 设备故障诊断技术[M]. 哈尔滨:哈尔滨工业大学出版社,2010:4-5 Xia Hong, Liu Yongkuo, Xie Chunli, et al. The fault diagnosis technology of equipment[M]. Harbin: Harbin Institute of Technology Press, 2010:4-5 (in Chinese) [3] Venkatasubramanian V, Rengaswamy R, Yin K, et al. A review of process fault detection and diagnosis partI: quantitative model-based methods[J]. Computers and Chemical Engineering, 2003,27(3):293-311 [4] Venkatasubramanian V, Rengaswamy R, Kavuri S N. A review of process fault detection and diagnosis part II: qualitative models and search strategies[J]. Computers and Chemical Engineering, 2003, 27(3):313-326 [5] Zhang Huaguang, Wang Zhanshan, Liu Derong.Global asymptotic stability of recurrent neural networks with multiple time-varying delays[J]. IEEE Transactions on Neural Networks, 2008, 19 (5):855-873 [6] 周东华, 胡艳艳. 动态系统的故障诊断技术[J]. 自动化学报, 2009, 35(6):748-758 Zhou Donghua, Hu Yanyan. Fault diagnosis technology of dynamic system[J]. AAS, 2009, 35(6) :748-758(in Chinese) [7] 顾颖. 一类非线性时滞系统的参数故障检测和估计[J]. 大连交通大学学报, 2010,31(2):95-97 Gu Ying. Parameter fault detection and estimation of a class of nonlinear systems with time-delay[J]. Journal of Dalian University, 2010,31(2):95-97(in Chinese) [8] Wu J D, Wang Y H, Bai M R. Development of an expert system for fault diagnosis in scooter engine platform using fuzzy-logic inference[J]. Expert Systems with Applications: An International Journal,2007,33(4):1063-1075 [9] Zhang Xu,Zhao Dongmei, Qiu Chen, et al. The power grid fault diagnosis based on the abnormal changes of the grid structure and the dynamic fault tree[J]. Applied Mechanics and Materials, 2011,48:1282-1285 [10] 阮晓钢. 神经计算科学——在细胞的水平上模拟脑功能[M]. 北京:国防工业出版社,2006:119-120,301 Ruan Xiaogang. Neural computing science-modeling brain function at the cellular level[M]. Beijing: Nation Defense Industry Press, 2006:119-120,301 (in Chinese) [11] 王占山, 张恩林, 张化光,等. 基于Hopfield神经网络的非线性系统故障估计方法[J]. 南京航空航天大学学报, 2011,43(s):19-22 Wang Zhanshan, Zhang Enlin, Zhang Huaguang, et al. Fault estimation approach for a class of nonlinear systems based on Hopfield neural network[J]. Journal of Nanjing University of Aeronautics & Astronautics, 2011,43(s):19-22(in Chinese) [12] Carpenter G A, Grossberg S. The ART of adaptive pattern recognition by a self-organizing neural network[J]. Computer, 1988,21(3):77-88 [13] 邱国平,邱明. 永磁直流电机实用设计及应用技术[M]. 北京:机械工业出版社, 2009:13-54 Qiu Guoping, Qiu Ming. Practical design and applied technology of permanent magnet DC motor[M]. Beijing: China Machine Press, 2009:13-54(in Chinese) [14] 廖晓钟, 刘向东. 自动控制系统[M]. 北京:北京理工大学出版社, 2005:9 Liao Xiaozhong, Liu Xiangdong. Automatic control system[M]. Beijing: Beijing Institute of Technology Press, 2005:9(in Chinese)

施引文献

资源附件(0)

访问统计