An Investigation on System Anomaly Source Diagnosis Using KPCA-FPSDG

The process monitoring using kernel PCA is lack of inference and can not find the root cause of abnormal data. An abnormal root cause diagnosis method combining KPCA and FPSDG was proposed. First the FPSDG and KPCA models should be built. All the variables are monitored using KPCA, when anomaly occurs, the abnormal variable is isolated and fuzzed. Based on the states of variables, inference diagnosis on FPSDG is used to find real anomaly source. The KPCA-FPSDG has the multivariate monitoring characteristics of KPCA and fault explanation capability of SDG, and also the shortcoming of single variable statistics in discriminating node conditions and threshold values in traditional SDG avoided. This method can effectively save diagnosing time as well as raise the degree of diagnosing process automation. Case studies show that the KPCA-FPSDG method can effectively monitor the thermal system process and find the anomaly source promptly.