基于SVM的飞机引气系统故障检测方法研究

Fault Detection Method of Aircraft Bleed Air System Based on SVM

基于飞机的历史QAR(Quick Access Recorder,快速存取记录器)数据构建数据集,对数据集进行参数选择、数据预处理、数据集划分等操作,目的是提高模型的运行效率和准确度;使用改进粒子群算法对SVM(Support Vector Machines,支持向量机)的分类参数进行优化,使模型的分类效果达到最优;为了验证模型的故障检测效果,将收集到的某航空公司A320系列飞机的引气系统QAR数据进行预处理并导入模型故障检测,最终将检测结果进行验证。结果表明,使用改进粒子群算法优化的SVM对飞机引气系统进行故障检测,可以提高故障检测的准确率,提前发现潜在的故障,减少故障发生的可能性。

Based on the historical QAR(Quick Access Recorder)data set of aircraft,the operation of parameter selection,data preprocessing and data set division are carried out to improve the operation efficiency and accuracy of the model.In order to get optimal classification effect of the model,the improved particle swarm optimization algorithm was used to optimize the classification parameters of SVM(Support Vector Machines).In order to verify the fault detection effect of the model,the QAR data of the air bleed system of an airline A320 series aircraft were preprocessed and imported into the model fault detection,and finally the detection results were verified.The results show that the SVM optimized by the improved particle swarm optimization algorithm can improve the accuracy of fault detection,detect potential faults in advance and reduce the possibility of faults.