基于KECA和FWA-SVM的间歇过程分时段故障诊断方法

Time division fault diagnosis method based on KECA and FWA-SVM for batch process

针对间歇过程的高度复杂性、强非线性、强时段性等特点,提出一种基于核熵成分分析(KECA)特征变量降维,利用烟花算法(FWA)优化支持向量机(SVM)参数的间歇过程分时段故障诊断方法。首先,通过多向核主元分析(MKPCA)进行在线故障监测,输出故障数据;其次,利用K-means分类方法将间歇过程划分为若干个子时段,对故障数据进行KECA特征变量处理,按熵值贡献率来确定选取主元的个数,深层提取特征信息;最后,在各子时段内分别构建FWA优化SVM参数故障诊断模型,将降维处理后的故障数据代入各自所属子时段FWA-SVM诊断模型内进行故障诊断。通过对青霉素仿真实验数据进行各种对比实验研究,验证了该方法的可行性与有效性。

Aiming at the high complexity, strong nonlinearity and strong time characteristics of intermittent process, this paper proposed a new method based on kernel entropy component analysis (KECA) to reduce the dimensionality of the KECA cha-racteristic variables, and used the fireworks algorithm (FWA) to optimize the support vector machine (SVM) parameters for the intermittent process of division fault diagnosis method. Firstly, it carried out multi-directional kernel principal component analysis (MKPCA) for the on-line fault monitoring and output the fault data. Second, it used K-means method to divide the batch process into several sub-periods. It used KECA to reduce characteristic variable dimensionality according to the contribution rate of entropy to determine the number of selected elements and extracted feature information in depth. Finally, it constructed FWA optimized SVM parameter fault diagnosis model in each sub-period, put the reduced dimension processed fault data into their own sub-period FWA-SVM diagnostic model for fault diagnosis. Through a variety of comparative experimental study based on penicillin simulation data, it verifies the feasibility and effectiveness of this method.