基于IGA-SVM的气动调节阀在线故障检测及诊断

On-line Fault Detection and Diagnosis for Pneumatic Control Valve Based on IGA-SV M

针对气动调节阀停机检修损失大、运行状态不易评估、故障模式复杂且故障诊断极为依赖工程经验等问题,结合残差法实现了故障的在线检测,并对传统的遗传算法进行改进,提出一种基于改进遗传算法优化的支持向量机(Improved Genetic Algorithm optimized Support vector machine,IGASVM)的故障诊断算法,作为实现气动调节阀在线故障诊断的算法基础。实验选取四类典型故障进行模拟、测试及数据分析,对阀门故障进行检测与诊断,结果表明:基于残差法的故障检测方法可以有效检测气动调节阀的故障发生,IGA-SVM算法测试诊断率达到92.67%,相较于传统方法具有提升。

With respect to the problems occurred in pneumatic control valve,such as long downtime,maintenance loss,difficult evaluation of operating state,complex failure mode,and fault diagnosis relying heavily on engineering experience,in this paper,by using residual method,online fault detection was carried out,and a new method based on Improved Genetic Algorithm optimized support vector machine(IGA-SVM)fault diagnosis algorithm for online fault diagnosis used for pneumatic control valve was proposed.In the experiment,four types of typical faults were selected for simulation,testing and data analysis,and the method presented in this paper was used to detect and diagnose valve faults.It was shown from the result that the fault detection method based on residual method can effectively detect the faults occurred in pneumatic control valves.The algorithm test diagnosis rate reaches 92.67%.Compared to traditional methods,there is apparent enhancement.