摘要
设计液压缸泄漏的模拟实验,分别提取压力、位移信号的时域频域组合特征,利用概率神经网络作为故障分类器,对"无泄漏"、"轻微泄漏"、"严重泄漏"三种故障状态进行识别与分类。采用Matlab仿真的方法测试了径向基传播率和训练样本变化时模型的训练效果。
Simulation experiment for hydraulic cylinder leakage was design.Cylinder pressure and displacement signals were detected,and the combination of time domain and frequency domain features were extracted respectively.Three kinds of fault condition ＂leak＂,＂minor leaks＂,＂serious leak＂ were identified and classified by probabilistic neural network classifier.To test the training effect of the model in different radial basis transmission rate and changing the training sample size by matlab simulation.
出处
《机电产品开发与创新》
2014年第6期102-104,共3页
Development & Innovation of Machinery & Electrical Products
基金
2013年度广东省高职教育机电类专业教育教学改革项目(jd201303)
关键词
概率神经网络
液压缸
故障状态识别
probabilistic neural network
hydraulic cylinder
fault state recognition
