摘要
结合小波变换和神经网络二者之间的优点,提出基于小波神经网络的负载模式识别的方法。其中小波函数代替非时变一般神经元隐层函数,用于提高网络对系统输入输出之间复杂关系的映射能力,相对于传统的模式识别方法,用小波变换对采集信号进行预处理,大大减少了神经网络的输入数目,从而简化了神经网络的结构和减少了它的训练时间。对实例电路识别结果表明,该方法能正确识别各种负载类型,准确率高。
Combining the time—frequency location and multiple·scale analyzation of wavelet transform(WT)with the nonlinear mapping and generalizing of neural network,a method of fault diagnosis in analogue circuits is proposed.Wavelet function is used to raise the mapping capability of network to the complex relation between the system input and output,and dynamical compensation is used to improve the modeling accuracy.Using wavelet decomposition to process the response drastically reduce the number of input fed to the neural network,simplifying its architecture and mininizing its training and processing time.Simulation results show that proposed fault diagnosis approach is feasible.
出处
《电气技术》
2008年第2期47-49,共3页
Electrical Engineering
关键词
小波变换
神经网络
负载识别
神经元
wavelet transform
neural network
recognizing the electrical appliances
neuron
