摘要
针对齿轮箱的故障模式和特征量之间复杂的非线性关系,采用SOM-BP复合神经网络,引用齿轮箱常见的故障及其相关参数作为训练样本建立诊断模型。在Matlab环境下,通过仿真试验并与BP网络进行比较,验证了此复合神经网络用于齿轮箱故障诊断的正确性和精确性,具有一定的工程应用价值。
Due to the complex nonlinear relation between breakdown mode and characteristic parameters of gear-boxes,the SOM-BP composite neural network is used,and the diagnosis mode is established with the common breakdown condition and the related parameters of the gear boxes used as the training sample.Under the Matlab environment,through the simulation test and comparison with BP network,correctness and accuracy of the composite neural network for gear box failure diagnosis are verified.
出处
《噪声与振动控制》
CSCD
北大核心
2010年第5期165-168,共4页
Noise and Vibration Control
基金
国家自然科学基金资助(50875247)
关键词
振动与波
复合神经网络
故障诊断
仿真测试
vibration and wave
composite neural network
fault diagnosis
simulation and test
