面向系统级的装备健康状态评估与故障预测方法

Research on System Level Equipment Health Status Assessment and Fault Prediction Method

针对系统级装备健康状态评估与故障预测需求,提出面向系统级的装备健康状态评估与故障预测方法。通过构建由部组件到分系统到系统的装备健康状态评估流程和方法,建立基于健康度分析的多输出支持向量机(Support Vector Machine,SVM)故障预测模型,并提出基于蚁群算法的支持向量机模型参数优化方法,进而利用装备健康状态评估与故障预测系统进行试验验证。结果表明:提出的方法能有效完成系统级装备健康状态趋势预测,具有良好的工程应用价值。

Aiming at the requirements of system-level equipment health status assessment and fault prediction,this paper proposes a system-level equipment health status assessment and fault prediction method.Firstly,the equipment health status assessment process and method from component to subsystem to system are constructed.Then,a multi-output SVM fault prediction model based on health analysis is established,and a SVM(Support Vector Machine)model parameter optimization method based on ant colony algorithm is proposed.Finally,the experimental verification is carried out by using the equipment health status assessment and fault prediction system.The results show that the proposed method can effectively complete the systemlevel equipment health status trend prediction,and has good engineering application value.