Nonlinear Process Monitoring and Fault Diagnosis Based on KPCA and MKL-SVM

A new method for nonlinear process monitoring and fault diagnosis based on kernel principal analysis and multiple kernel learning support vector machines is proposed. The data is analyzed using KPCA. T2 and SPE are constructed in the future space. If the T2 and SPE exceed the predefined control limit, a fault may have occurred. Then the nonlinear score vectors are calculated and fed into the MKL-SVM to identify the faults. The results of the monitoring application to the Tennessee Eastman (TE) chemical process demonstrate the effectiveness of the proposed method.