Fault detection of a non-linear continuous stirred tank heater based on SVM

Abstract

Industrial big data has created a challenge for data measurement, detection, and processing. This paper shows that support vector machine (SVM) is extremely useful in detecting fault information in modern complex industrial processes. With a pilot plant of Continuous Stirred Tank Heater (CSTH) process, the SVM method with radial basis function (RBF) kernels is tested on the CSTH database and compared with an improved Partial Least Squares (IPLS) and Principal Component Analysis (PCA). The performance of SVM is validated using k-fold cross-validation where the classifier based on SVM outperforms those based on PCA and IPLS. These comparisons show that SVM has remarkable detection performance and satisfying elapsed time. From an industrial point of view, the vitality of SVM algorithm in actual industrial process is discussed.