A probabilistic principal component analysis-based approach in process monitoring and fault diagnosis with application in wastewater treatment plant

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.

Given their potentially enormous risk, process monitoring and fault diagnosis for chemical plants have recently been the focus of many studies. Based on hazard and operability (HAZOP) analysis, kernel principal component analysis (KPCA), wavelet neural network (WNN), and fault tree analysis (FTA), a hybrid process monitoring and fault diagnosis approach is proposed in this study. HAZOP analysis helps identify the fault modes and determine process variables monitored. The KPCA model is then constructed to reduce monitoring variable dimensionality. Meanwhile, the fault features of the monitoring variables are extracted, so then process monitoring can be performed with the squared prediction error (SPE) statistics of KPCA. Then, multiple WNN models are designed through the use of low-dimensional sample data preprocessed by KPCA as the training and test samples to detect the fault mode online. Finally, FTA approach is introduced to further locate the fault root causes of the fault mode. The proposed approach is applied to process monitoring and fault diagnosis in a depropanizer unit. Case study results indicate that this approach can be applicable to process monitoring and diagnosis in large-scale chemical plants. Accordingly, the approach can serve as an early and reliable basis for technicians’ and operators’ safety management decision-making.

In this paper, a novel nonlinear process monitoring and fault detection method based on kernel ICA is proposed. The Kernel ICA method is a two-phase algorithm, KPCA first spheres data and makes the data structure become as linearly separable as possible using an implicit nonlinear mapping determined by kernel. Then ICA seeks the projection directions in the KPCA whitened space, making the distribution of the projected data as non-gaussian as possible. The application to the FCCU simulated process indicates that the proposed process monitoring method based on Kernel ICA can effectively capture the nonlinear relationship in process variables. Its performance significantly outperforms monitoring method based on ICA or KPCA.

Nonlinear biological batch process monitoring and fault identification based on kernel fisher discriminant analysis

Study on modifications of PLS approach for process monitoring

Probabilistic latent variable models (PLVMs), such as probabilistic principal component analysis (PPCA), are widely employed in process monitoring and fault detection of industrial processes. This article proposes a novel deep PPCA (DePPCA) model, which has the advantages of both probabilistic modeling and deep learning. The construction of DePPCA includes a greedy layer-wise pretraining phase and a unified end-to-end fine-tuning phase. The former establishes a hierarchical deep structure based on cascading multiple layers of the PPCA module to extract high-level features. The latter builds an end-to-end connection between the raw inputs and the final outputs to further improve the representation of the model to high-level features. After constructing the model structure of DePPCA, we first present the detailed training processes of the pretraining and fine-tuning stages, then clarify the theoretical merits of the proposed model from the perspective of variational inference. For process monitoring purposes, we develop two statistics based on the established DePPCA. The monitoring performance of these two statistics can remain superior even if the features extracted by DePPCA are significantly compressed to univariate. This makes the feature extraction process and online monitoring procedure of DePPCA quite fast. In other words, the proposed DePPCA can achieve accurate and efficient process monitoring by only extracting one feature for each sample. Finally, the effectiveness of DePPCA is evaluated on the Tennessee Eastman (TE) process and the multiphase flow (MPF) facility.

A syntactic pattern-recognition approach for process monitoring and fault diagnosis

There exists nonlinear information and strong correlation among variables in modern industrial processes. As a typical linear process monitoring method, probabilistic principal component analysis (PPCA) cannot capture the nonlinear information among process data. To cope with this problem and improve real time performance, a new just-in-time-learning based PPCA (JITL–PPCA) method is proposed in this paper. In JITL–PPCA, an online local model structure is first designed for extracting nonlinear features, by incorporating an improved JITL approach and least squares support vector regression (LSSVR) model. Then, the remaining linear residuals are input into the PPCA scheme for final process monitoring and fault detection. A simulated numerical case and a real industrial process case are used to evaluate the performance and effectiveness of the proposed method. The monitoring results show the effectiveness of the proposed JITL–PPCA method.

In order to monitor nonlinear production process effectively, multivariate statistical process control based on kernel principal component analysis is applied to process monitoring and diagnosis. Squared prediction error (SPE) statistic of the kernel principal component analysis (KPCA) model is used for process monitoring, and the fault causes of the production process could be tracked by the methods of data reconstruction and the optimal neighbor selection strategy. Simulation data and Tennessee Eastman process data are used for model validation, as a result the proposed method has better performance on abnormality detecting, compared with multivariate statistical process control based on linear principal component analysis. What is more, the causes of the faults are tracked effectively, thus the production process can be adjusted to prevent substandard products.

Probabilistic models, which can model the process noise and can handle the problem of missing data in the probabilistic framework, recently have been got much attention in process monitoring and fa...

The aim of this paper is to propose a novel real‐time process monitoring and fault diagnosis method based on the principal component analysis (PCA) and kernel Fisher discriminant analysis (KFDA). There is a need to develop this method in order to overcome the inherent limitations of the current kernel FDA method. The idea of the method is to initially reduce dimensionality using PCA and then to map the score data in the reduced original space to the high‐dimensional feature space via a nonlinear kernel function. Following this, the optimal Fisher feature vector and discriminant vector are extracted to perform process monitoring. If faults occur, the method uses the degree of similarity between the optimal discriminant vector presented and the optimal discriminant vector of the faults in the historical dataset to perform a diagnosis. The proposed method can effectively capture nonlinear relationships in process variables. In comparison with kernel FDA, the PCA plus kernel FDA method is more efficient and has a more rapid response when used to undertake online monitoring and fault diagnosis. In this study, the method is evaluated by applying it to the fluid catalytic cracking unit (FCCU) process. As a consequence, its effectiveness is demonstrated.

Probabilistic contribution analysis for statistical process monitoring: A missing variable approach

A Systematic Approach to Dynamic Monitoring of Industrial Processes Based on Second-Order Slow Feature Analysis

In this paper, decision theory is introduced to key performance indicator (KPI) related process monitoring and fault diagnosis (PM-FD) field in order to settle the difficulties of making the most rational decision among several candidates. Considering that there are several evaluation criteria for PM-FD approaches, this paper provides some methods to help decision makers to find the most effective PM-FD approach among lots of alternatives when a few criteria are taken into consideration. Also, these methods are applied in the simulation study, including a numerical example and Tennessee Eastman process (TEP) benchmark.

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.