基于遗传算法优化神经网络的齿轮故障诊断  

Gear Fault Diagnosis Based on GA-Elman Neural Network Model

作　　者：乔晶晶[1] 潘宏侠[1] 

机构地区：[1]中北大学机械工程与自动化学院,山西太原030051

出　　处：《水电能源科学》2010年第6期106-108,共3页Water Resources and Power

摘　　要：针对齿轮故障诊断的重要性和复杂性,基于神经网络固有的局部极小值及遗传算法良好的全局收敛能力和搜索性,在遗传算法优化初始权值和阈值的基础上构建了GA-Elman神经网络的故障诊断系统。仿真结果表明,该方法用于齿轮常见故障诊断和预测有效、可行。Aiming at the importance and complexity of gear fault diagnosis,genetic algorithm(GA) is used to optimize the initial weights and threshold value of the neural networks(NN) based on the inherent local minimum problem of NN and the good global convergence and global search ability of GA.The fault diagnosis system with GA-Elman neural network is established for gear vibration signal.The simulation results demonstrate that it is an effective method to diagnose and predict the common fault of gear.

关 键 词：GA-Elman神经网络 齿轮 故障诊断 模式识别 

分 类 号：TH165.3[机械工程—机械制造及自动化]