松鼠搜索算法优化SVM的液体火箭动力系统故障诊断  

Fault Diagnosis of Liquid Rocket Power System Based on Optimized SVM by Squirrel Search Algorithm

作　　者：陈占国 薛薇 许亮[1] Chen Zhanguo;Xue Wei;Xu Liang(Tianjin University of Technology,School of Electrical Engineering and Automation,Tianjin Key Laboratory for Control Theory&Applications in Complicated Systems,Tianjin University of Technology,Tianjin 300384,China;China Academy of Aerospace Science and Innovation,Beijing 100083,China)

机构地区：[1]天津理工大学电气工程与自动化学院天津市复杂系统控制理论与应用重点实验室,天津300384 [2]中国航天科技创新研究院,北京100083

出　　处：《航天控制》2023年第1期82-88,共7页Aerospace Control

基　　金：国家自然科学基金(61975151,61308120)。

摘　　要：为了对液体火箭动力系统的故障进行诊断,提出了一种基于松鼠搜索算法(SSA)优化支持向量机(SVM)的故障诊断方法。将支持向量机的两个重要参数惩罚因子和核函数参数作为松鼠位置矢量,由输出的最佳参数构成SSA-SVM预测模型。实验选取某液体火箭动力系统的846组数据进行诊断。结果表明,对于168组测试样本集,诊断预测错误为4个,测试集分类错误率较低。In order to diagnose the fault of liquid rocket, a fault diagnosis method based on squirrel search algorithm(SSA) and optimized support vector machine(SVM) is proposed. Two important parameters of support vector machine and penalty factor and kernel function parameter are used as squirrel position vector. The SSA-SVM prediction model is established by the best output parameters. 846 sets of data of a liquid rocket power system are selected for diagnosis. The results show that there are 4 diagnostic prediction errors and the classification error rate of test sets is low through using 168 groups of test samples,.

关 键 词：液体火箭发动机 支持向量机 松鼠搜索算法 故障诊断 

分 类 号：V434[航空宇航科学与技术—航空宇航推进理论与工程]