基于MIV和BRBP神经网络的电路板红外诊断方法

针对BP神经网络对于海量数据训练及多维数据训练收敛困难的问题,在使用增加动力项、自适应学习速率等方法的基础上,引入均值影响度算法(MIV)构造了贝叶斯正则化反向传播(BRBP)神经网络,以此提高电子线路板红外故障诊断算法的效率。利用红外测温方式,获取了不同室温及运行状态下电路板中21个元器件温度数据。将此21个参数作为故障诊断模型的初始输入变量,经过MIV算法简约为12个参数输入至BRBP神经网络,进行故障评估和诊断。结果表明:相对于传统的BRBP神经网络,本文设计的基于MIV和BRBP神经网络模型诊断方法极大简化了数据训练的数据量并解决了数据收敛的困难,因此效率更高,用时更省。

Infrared diagnosis of circuit board fault based on MIV and BRBP neural networks

The training algorithm for BP network is hard to converge when the input data is large and has high dimension. Aiming at this problem,a novel fault diagnosis method based on MIV and BRBP neural networks by infrared temperature measuring is put forward. Sample data about 21 variables of circuit board under different room temperature and operating conditions are measured,and these 21 parameters are used as the initial input variables of fault diagnosis model. After MIV optimization,the reduced 12 variables will be input into BRBP neural networks to predict faults and classify the circuit board running conditions. Experiments show that the proposed neural networks model is more efficiently and more rapidly compared with the traditional BRBP neural network. The neural network model presented in the paper can effectively diagnose the circuit board faults.