基于遗传神经网络的矿井通风机故障诊断研究

Study on Fault Diagnosis of Mine Ventilator Based on Genetic Neural Network

为了提高矿井通风机机械故障诊断的准确性,提出了一种基于遗传神经网络的矿井通风机故障诊断模型。利用BP神经网络的自学习、自适应、强容错性,并通过遗传算法优化BP神经网络的连接权重和阈值。弱化了故障诊断中的人为因素,提高了评价结果的准确性和权威性。仿真结果表明,该诊断方法具有准确度高、诊断速度快等优点,是一种实用的故障诊断方法。

In order to improve the accuracy of the fault diagnosis on mine ventilator,an fault detection of mine ventilator based on neural network whose thresholds and connection weights are optimized by genetic algorithm（GA-NN） is proposed in this paper.Using the characteristic of self-learning,self-adaptive and efficient fault tolerant of BP neural networks,the model weaken the human factors to improve the accuracy of the results of the assessment and authority.Simulation results show that the diagnosis method,a higher accuracy and quicker diagnosis,is a more practical fault diagnosis method.