摘要
提出了一种基于粗糙集理论和支持向量机算法的推土机发动机故障诊断方法。首先利用粗糙集理论对故障诊断决策系统进行约简,消除样本噪声和冗余,然后在此基础上设计支持向量机多分类器,进行故障检测分类。这样,可以有效减小SVM训练的数据,加快多分类器的处理速度。实验结果显示它能提高故障诊断的准确性和效率。
A bulldozer engine fault diagnosis method based on rough set and support vector machine is proposed. Firstly, diagnostic decision-making is reduced based on rough sets theory, the noise and redundancy in the sample are removed. According to the chosen reduction a support vector machine multi-classifier is designed for fault diagnosis. Therefore, the multi-classifier training data can be reduced and running speed can quicken. Test shows its accuracy and efficiency of fault diagnosis.
出处
《筑路机械与施工机械化》
北大核心
2007年第1期56-59,共4页
Road Machinery & Construction Mechanization
关键词
粗糙集
支持向量机
推土机
发动机
故障诊断
rough sets
support vector machine
bulldozer
diagnosis. engine
fault diagnosis
