Analysis Model of Drilling Tool Failure Based on PSO-SVM and Its Application
Computational and Information Sciences（2012）
摘要
Accurate drilling tool failure diagnosis is an important issue. This paper proposes a new forecasting method, using the support vector machine (SVM) to forecast drilling tool failure. First, select several major factors that affecting drilling tool failure as input features of SVM, then SVM's nuclear parameters are optimized with particle swarm optimization (PSO) in order to enhance its accuracy. This method takes full advantages of special advantages of SVM in treating small sample classification study problems, and the overall parallel search of PSO. Compared with actual engineering results, it is proved to have high performance and accuracy, which provides a new method to forecast drilling tool failure.
更多查看译文
关键词
high performance,pso parallel search,particle swarm optimization (pso),svm nuclear parameters,analysis model,pso-svm,important issue,major factor,pattern classification,particle swarm optimisation,drilling tool failure,drilling machines,full advantage,actual engineering result,failure analysis,fault diagnosis,support vector machine,new forecasting method,forecasting method,accurate drilling tool failure,support vector machine (svm),drilling took failure,drilling tool failure diagnosis,mechanical engineering computing,drilling tool failure analysis model,support vector machines,classification study problems,new method,input feature,particle swarm optimization,optimization,mathematical model
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要