An improved probabilistic principal component analysis approach for process monitoring and fault diagnosis

Recently probabilistic principal component analysis (PPCA) has been used for process monitoring and fault diagnosis, which can model the process noise and can handle the problem of missing data in the probabilistic framework. Nevertheless, the missing data samples are treated as principal components in conventional PPCA method, which causes the estimation accuracy is largely influenced by data missing rate. In this paper, a fault detection and identification method based on improved PPCA is proposed for industry process whose variables are missing with a large rate. First, for decreasing the estimation errors of the missing data, an improved estimation method for model parameters of PPCA and missing data is studied. By optimizing the low bound of a log-likelihood function, the missing data are imputed after the value of low bound is converged. Then, a Bayesian inference probability index is constructed to identify the major faulty variables. At last, a new fault diagnosis method is proposed for improving the accuracy of diagnosis with data missing and unknown noise. Using Tennessee Eastman Process as a case study, the simulation results show that the proposed method is more accuracy, efficient and robust, under the condition of large missing data rate in the procedure of fault detection and diagnosis, than convention al PPCA method.