Abstract：Low reliability of variable frequency drive is due to switch faults occurred in the inverter. The paper investigates the use of spectral estimation and neural network for fault detection and diagnosis in inverter-fed motor drives. Comparing voltage signal of actual and ideal inverter without faults, an equation for estimating spectral residual is derived. The spectral residual of the signal is obtained in real time by using complex recursive least square algorithm. A simple fault decision strategy is proposed and fault occurred in the inverter is detected in real time. Being treated spectral residual properly, relative spectral residual is obtained. Multilayer perceptron neural network is used to isolate switch faults combing with spectral estimation. The simulation result shows that the method can detect and isolate the faults effectively.
崔博文, 任章. 基于谱估计的三相逆变器故障诊断[J]. 电工技术学报, 2009, 24(11): 192-198.
Cui Bowen, Ren Zhang. Fault Detection and Diagnosis of Inverter Based on Spectral Estimation and Neural Network. Transactions of China Electrotechnical Society, 2009, 24(11): 192-198.
[1] Araujo de Ribeiro R L, Jacobina C B, Silva da E R C, et al. Fault detection of open-switch damage in voltage-fed PWM motor drive systems[J]. IEEE Transactions on Power Electronics, 2003, 18(2): 587- 593. [2] Awadallah M A, Morcos M M, Gopalakrishnan S, et al. Detection of stator short circuits in VSI-fed brushless DC motors using wavelet transform[J]. IEEE Transactions on Energy Conversion, 2006, 21(1): 1-8. [3] 赵争鸣, 闵勇．电机-控制集成系统的高故障容限研究[J]．中国电机工程学报, 1999, 19(3)：22-25． Zhao Zhengming, Min Yong．High fault tolerance for AC motors integrated with control system[J]. Proceedings of the CSEE, 1999, 19(3): 22-25. [4] 肖岚, 李睿.逆变器并联系统功率管开路故障诊断研究[J].中国电机工程学报, 2006, 26(4): 99-104. [5] Wallace A K, Spee R. The simulation of brushless DC drivefailures[C]. PESC Record-IEEE Power Electronics Specialists Conference, 1988:199-206. [6] Spee R, Wallace A K. Remedial strategies for brushless DC drive failures[J]. IEEE Transactions on Industry Applications, 1990, 26(2): 259-266. [7] Peuget R, Courtine S, Rognon J P. Fault detection and isolation on a PWM inverter by knowledge-based model[J]. IEEE Transactions on Industry Applications, 1998, 34(6): 1318-1326. [8] 彭力, 白丹, 康勇, 等. 三相逆变器不平衡抑制研究[J]. 中国电机工程学报, 2004, 24(5)：174-178. [9] 张宇, 段善旭, 康勇, 等. 基于瞬时对称分量的三相逆变器特性分析[J]．中国电机工程学报, 2005, 25(17)：16-20. [10] 崔博文, 任章, 陈剑, 等. 逆变器供电的电动机变频调速系统实时故障检测[J]. 电机与控制学报, 2006, 10(1): 52-56. [11] 崔博文, 陈剑, 陈心昭, 等. 复参数最小二乘估 计[J]. 安徽大学学报(自然科学版), 2005, 29(3): 5-10. [12] 陈如清. 两种基于神经网络的故障诊断方法[J]．中国电机工程学报, 2005, 25(16)：16-20. [13] 陈长征, 栗青, 刘一芳, 等．汽轮发电机组故障智能诊断方法研究[J]．中国电机工程学报, 2002, 22(5)：121-124． Chen Changzheng, Li Qing, Liu Yifang, et al. Intelligent fault diagnosis method for turbo-generator unit[J]. Proceedings of the CSEE, 2002, 22(5): 121-124. [14] 张智星, 孙春在, 水谷英二[日]. 神经—模糊和软计算[M]. 张平安, 高春华译. 西安：西安交通大学出版社, 2000.
2009, Vol. 24 
