远程协同诊断的现场信息预处理研究  

On Local Information Preprocessing for Remote Collaborative Diagnosis

作　　者：刘建辉 秦现生[1] 

机构地区：[1]西北工业大学机电学院,西安710072

出　　处：《机械科学与技术》2008年第3期338-342,共5页Mechanical Science and Technology for Aerospace Engineering

摘　　要：面对远程协同诊断存在的信息传输延迟、网络阻塞等问题,提出了现场诊断信息预处理概念。在其框架介绍基础上,重点研究了现场信息预处理策略控制和深层信息预处理;运用统计分析和SVM回归预测的集成工况预测方法作为预处理策略控制的依据,而基于粗集的时序诊断信息提取方法则是深层信息预处理的核心。最后给出了现场信息预处理在工程装备上的应用示例。In order to solve the bottleneck problems in remote collaborative diagnosis, such as information transmission barrage and net delay, an iD-LIP （intelligent Diagnosis-Local Information Preprocessing）was proposed. We first presented an iD-LIP function framework. Then we studied the managing strategy of preprocessing and deep in- formation preprocessing. The managing strategy of preprocessing was realized by an integrated equipment performance prediction method which composed of statistics analysis and SVM （ support vector machine） regression prediction. An information reduction method based on rough set theory was adopted in deep information preprocessing. As an example, an application of iD-LIP to engineering equipments was given. Results show that the iD-LIP strategy is feasible and efficient.

关 键 词：预处理策略控制 SVM回归预测 深层信息预处理 粗集论 

分 类 号：TH17[机械工程—机械制造及自动化] TP277[自动化与计算机技术—检测技术与自动化装置]