摘要
提出了一种基于分形理论和神经网络技术的柴油机振动诊断方法,首先对柴油机的振动信号进行小波降噪,然后提取相应的不同迭代阶数的广义分形维数,并将其作为RBF神经网络的输入参数,以运行工况作为输出参数训练神经网络模型.训练后的神经网络可以利用测量的振动信号来判断柴油机的故障状况.实验及仿真结果表明:采用的小波降噪技术可以较好地再现振动信号特征,有效提高故障识别率;同时基于分形和神经网络技术的诊断方法在柴油机故障诊断中是有效可行的,对于单个故障的正确识别率达到了100%,具有较高的工程适用性,对其他复杂机械的振动诊断同样具有参考价值.
A new fault diagnosis method for diesel engine based on the fractal theory and neural network was proposed. Firstly, we use the wavelet theory to reduce noises in the vibration signals and then pick up the generalized fractal dimensions with different iterative steps. They will be the input parameters of the RBF neural network, the output ones are the five kinds of running status. After being trained, the model of neural network can identify the faults by the vibration signals. According to the experiment and simulation result, the wavelet noise reduction can reproduce the vibration signals clearly and improve the fault identification. The method of fault identification based on the fractal theory and neural network was demonstrated to be efficient and feasible, and it can identify the faults correctly. This method has preferable engineering applicability and the referenced value to other vibration diagnosis of complex machines.
出处
《华中科技大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2005年第9期68-70,共3页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
关键词
柴油机
分形理论
神经网络
故障诊断
diesel engine
fractal theory
neural network
fault diagnosis
