基于电流频谱和RBF神经网络的异步电动机故障诊断方法分析与研究.docVIP

摘 要 由于现代科学的进步和生产系统的不断发展，电机在生产中发挥着越来越重要的作用。异步电机以其结构简单、价格低廉、可靠性高、维护方便而在工农业中取得了广泛的应用。随着现代工业系统的飞速发展，电机的单机容量不断增加，所驱动的负载也越来越复杂。电机故障不仅会损坏电机本身，重时还会使电机突然停机、生产线崩溃，造成巨大的经济损失和灾难性后果。为了将故障所造成的损失降低至最小程度，迫切要求对电动机故障进行检测。电动机故障检测是通过应用先进的技术手段，对RBF神经网络的结构和特点进行了相关的介绍，建立基于RBF神经网络的故障诊断结构，并利用故障样本数据对网络进行训练，从而实现了对故障的诊断。 ABSTRACT Owing to the progress of modern science and product system, electrical engineer plays a more and more important role in modern production .Asynchronous motors are widely used in the industrial and agricultural production because of its simple structure, low price, high reliability and convenient maintenance. With the rapid development of the modern industrial system, the capacity of a single motor is keeping increasing and the load is also becoming more complicated now. A motor fault can not only cause damage to the motor, but also can result in unscheduled machine downtime and the shutdown of a production line, which will cause heavy financial losses and catastrophic fault. In order to reduce the fault to a minimum extent, there is an urgent call for motor fault detection. Motor fault detection uses the application of advanced technical instrument, the study of practical and efficient motor fault diagnosis system is very important for the production of safe operation. Firstly, the design introduces the structure and the basic principles of the asynchronous motor, as well as the common fault. And then a summary description of broken rotor bars and end ring cracks, the failure characteristics of air-gap eccentricity signal frequency component mechanism. Then the spectrum of current in electrical fault diagnosis in a brief description of the role of the system to introduce the principle of Fourier transform, and next signals to the stator current FFT transform, to draw current frequency spectrum, and frequency spectrum analysis of failure criterion and thus the diagnosis of motor failure. Finally, RBF neural network structure and characteristics of the relevant presen