摘要
柴油机作为动力装置的关键设备,对其进行实时地故障检测和诊断具有重大的意义;因此,提出了一种基于小波包分解和改进人工免疫神经网络的柴油机故障诊断方法;首先,对柴油机缸盖振动信号采用小波阈值法进行降噪,再采用小波包分解获得故障诊断特征向量,并将其作为BP神经网络的输入以训练网络,最后,采用改进的人工免疫算法对BP神经网络的各参数进行优化,以获得最终的BP神经网络故障诊断模型;柴油机气阀故障诊断实例表明:文中的柴油机故障诊断模型能正确地实现故障诊断,且与其它方法相比,训练误差仅为0.0001,具有诊断精度高和诊断时间短的优点。
The diesel engine is the key device of a lot of the power equipment, and it is significant to detect and diagnose its fault in-- time. Therefore, a fault diagnosis method for diesel engine based on wavelet packet decomposition and the improved artificial immune neural network. Firstly, the wavelet threshold method is used to reduce the noise for the vibration signal of the diesel engine, then the wavelet packet decomposition is used to obtain the fault characteristic vector as the input of the BP network, finally, the improved artificial immune algorism is used to optimize the parameters of the BP network to get the final fault diagnosis model. The instance of diesel engine shows the method in this paper can realize the fault diagnosis, and compared with other methods, it has the training error 0. 0001 with high diagnosis accuracy and short diagnosis time.
出处
《计算机测量与控制》
北大核心
2013年第8期2080-2082,2086,共4页
Computer Measurement &Control
关键词
柴油机
故障诊断
BP算法
人工免疫
diesel engine
fault diagnose
BP algorism
artificial immune
