自确认气动执行器的故障诊断算法研究  

Research on Fault Diagnosis Algorithm of Self-validating Pneumatic Actuator

作　　者：冯志刚 杨佳琪 FENG Zhigang;YANG Jiaqi(Department of Automation,Shenyang Aerospace University,Shenyang Liaoning 110136,China)

机构地区：[1]沈阳航空航天大学自动化学院,辽宁沈阳110136

出　　处：《传感技术学报》2022年第6期785-791,共7页Chinese Journal of Sensors and Actuators

基　　金：国家自然科学基金青年基金项目(61104023)。

摘　　要：为解决自确认气动执行器的故障诊断问题,本文提出一种基于自适应多核多分类关联向量机的气动执行器故障诊断方法。基于DAMADICS平台建立气动阀门仿真模型,利用DABLib模块生成故障数据,采用关联向量机回归原理,根据正常样本序列,构建数据恢复模型,与实际执行器的输出值相比较,得到残差,完成特征提取。以残差作为输入,选用高斯核函数和多项式核函数的组合,建立多核多分类关联向量机,利用自适应粒子群遗传融合算法实现多目标核参数的优化,判断气动执行器的故障类型。实验结果表明,该方法有更高的建模精度和更好的实用性,实现了自确认气动执行器多故障诊断和分类。In order to solve the fault diagnosis problem of self-validating pneumatic actuators,a pneumatic actuator fault diagnosis method based on adaptive multi-kernel multi-class relevance vector machine is proposed.The simulation model of pneumatic valve was established based on DAMADICS platform and fault data were generated by using the DABLib module.Relevance vector machine regression was used to establish the recovery model according to normal sample sequence.The residuals were generated by comparing the output of the model and that of the actual actuator,and the feature extraction was achieved.A multi-kernel multi-class relevance vector machine was established by using the combination of gaussian kernel function and polynomial kernel function,and trained by the residuals.A hybrid algorithm of adaptive particle swarm optimization algorithm and genetic algorithm was used to achieve optimization of multi-objective kernel parameters.The experimental results show that the method has higher modeling accuracy and better practicability,and realizes multi-fault diagnosis and classification of self-validating pneumatic actuators.

关 键 词：自确认气动执行器 故障诊断 关联向量机回归 多核多分类关联向量机 粒子群算法 遗传算法 

分 类 号：TP214[自动化与计算机技术—检测技术与自动化装置] TP18[自动化与计算机技术—控制科学与工程]