BP神经网络预测电极速度影响放电参数分析

文中结合小间隙放电的双过程模型,探讨电极移动引起放电场强和压强的变化对放电间隙内部相关因子的影响。文中同时利用BP神经网络预测分析电极移动速度对放电参数的影响。基于静电放电电极移动速度效应检测仪,不断改变电极移动速度,反复多次进行放电实验并统计试验数据。利用BP神经网络对已测实验数据进行训练、学习,从而预测不同速度与压强下对应的电流上升时间和峰值电流大小。实验结果表明,放电电流的上升时间与电极移动速度不存在相关性。根据新方法预测出的不同速度下的峰值电流和实际大小相比准确率更高。研究结果对探寻非接触式静电放电的规律和制定静电放电标准有一定的参考价值。

Analysis of Discharge Parameters Affected by BP Neural Network Predicting Electrode Velocity

The dual-process model of small gap discharge was used to investigate the influence of the change of field intensity and pressure on the internal correlation factors of the discharge gap, and the BP neural network was applied to predict and analyze the influence of the electrode moving speed on the discharge parameters. Based on the electrostatic discharge electrode moving speed effect detector, the electrode moving speed was continuously changed, and the discharge experiment had been repeated several times to obtain and statistically calculated the test data. Meanwhile, BP neural network was used to train and learn the measured experimental data, so as to predict the current rise time and peak current at different speeds and pressures. The results showed that there was no correlation between the rising time of the discharge current and the moving speed of the electrode. According to the new method, the accuracy of peak current at different speeds was higher than that of the actual size. The research results was of great reference value in exploring the law of non-contact electrostatic discharge and the formulation of electrostatic discharge standards.