基于新息GM(1,1)的故障诊断预测  

Fault Diagnosis and Prediction Based on New Information GM (1,1)

作　　者：董立立[1] 黄道[1] 

机构地区：[1]华东理工大学工业自动化国家工程研究中心

出　　处：《控制工程》2006年第3期252-255,共4页Control Engineering of China

摘　　要：故障诊断预测随着设备结构的复杂性、运行环境的独特性和诱发故障的多源性而变得愈发困难,因此,利用新的科学理论对故障诊断预测方法进行了探索。基于灰理论建立的新息GM(1,1)模型能够及时更新数据,用最新数据替换老数据建立的等维新息模型,能够保证原始数据对模型的作用,使模型更能反映实际。实例计算分析表明:模型样本需求量小、计算简单,能动态地反映出系统的时变特性,有效提高预测精度。该方法应用于故障诊断预测,能够及早判明故障的发展趋势及其危害程度,避免灾难性事故发生,维护设备安全长周期运行。The fault diagnosis and prediction of equipment is getting more difficult for its complex structure, unique operating environment and multi-phcate faults. Fault diagnosis and prediction approaches are discussed by using new scientific theories in the area. New infomaation modeling GM（1 ,1）based on grey theory ensure that original data can act on the model by updating the old data. So the model will embody a much more actual situation. The calculation and analysis results show that the size of the model sample is much smaller with a simply calculation model. The time-changed character of the system can be reflected dynamically, so the forecasting precision can be improved efficiently. By using this method, the catastrophic accident can be avoided and the safety runtime is prolonged.

关 键 词：故障诊断 灰系统 新息 动态预测 

分 类 号：TH165[机械工程—机械制造及自动化]