基于概率神经网络的电子油门踏板故障诊断

来源期刊:中南大学学报(自然科学版)2019年第6期

论文作者:赵晓欢 蒋玉秀 邓元望

文章页码:1370 - 1378

关键词:电子油门踏板;概率神经网络;故障模型;故障诊断

Key words:electronic accelerator pedal; probabilistic neural network(PNN); fault model; fault diagnosis

摘    要:针对电子油门踏板的工作状况,基于概率神经网络原理,建立故障诊断模型。根据实际采集的试验数据,通过电子油门踏板故障分类器设计并定义6种故障判断模式,测试4组不同故障顺序的试验样本。在MATLAB中检查定义变量对应的维度后,开展故障诊断,得出正确的诊断结果。研究结果表明:概率神经网络故障模型可以省时、高效地预测故障类型,且测试试验数据显示顺序结构诊断用时最少。

Abstract: According to working conditions of electronic accelerator pedal, a fault diagnosis model was established based on the principle of probabilistic neural network(PNN). According to the collected actual data, 6 fault judgment modes were designed and defined through electronic accelerator pedal fault classifier. 4 groups of test samples with different fault sequences were tested. After checking the dimensions of the variables defined in MATLAB, the fault diagnosis was carried out, and the corresponding diagnosis results were obtained. The results show that PNN diagnosis model can effectively predict different types of faults. The test data shows that the sequential structure diagnosis takes the least time.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号