中文摘要：

研究了混沌驱动永磁同步电机系统的故障识别问题,设计了一种小波支持向量机故障识别器。首先对故障恢复信号进行经验模态分解,得到若干个平稳的本征模函数,将本征模函数的能量特征作为输入构建小波支持向量机故障识别器。训练完成后,冻结小波支持向量机结构与内部参数,以白噪声模拟实际运行中的未知扰动,并以加入扰动的故障信号作为测试输入,利用小波支持向量机故障识别器进行故障识别。结果表明,基于小波支持向量机的故障识别器能够较好地识别故障信号,拟合误差均在1%以内。

英文摘要：

A research on fault identification of the permanent magnet synchronous motors driving under chaotic state is carried out, a fault identifier based on the wavelet support vector machine is established. After the empirical mode decomposition of the restored fault signals, serial stationary intrinsic mode functions are obtained, and their energy characteristics are used as inputs to establish a fault identifier based on the wavelet support vector machine. After training, the structure of the wavelet support vector machine and its internal parameters are fixed. The white noises usually simulate the unknown disturbances in practice. As the test inputs, the fault signals are mixed with white noises, and are identified by the fault identifier. The simulation results show that the fault identifier based on the wavelet support vector machine can identify the fault signals well, the fitting error is less than 1%.