Junghui Chen

On-line Batch Process Monitoring Using Dynamic PCA and Dynamic PLS Models

Abstract Producing value-added products of high-quality is the common objective in industries. This objective is more difficult to achieve in batch processes whose key quality measurements are not available on-line. In order to reduce the variations of the product quality, an on-line batch monitoring scheme is developed based on the multivariate statistical process control. It suggests using the past measured process variables without real-time quality measurement at the end of the batch run. The method, referred to as BDPCA and BDPLS, integrates the time-lagged windows of process dynamic behavior with the principal component analysis and partial least square respectively for on-line batch monitoring. Like traditional MPCA and MPLS approaches, the only information needed to set up the control chart is the historical data collected from the past successful batches. This leads to simple monitoring charts, easy tracking of the progress in each batch run and monitoring the occurrence of the observable upsets. BDPCA and BDPLS models only collect the previous data during the batch run without expensive computations to anticipate the future measurements. Three examples are used to investigate the potential application of the proposed method and make a comparison with some traditional on-line MPCA and MPLS algorithms.

Applying neural networks to on-line updated PID controllers for nonlinear process control

Abstract The inherent time-varying nonlinearity and complexity usually exist in chemical processes. The design of control structure should be properly adjusted based on the current state. In this paper, an improved conventional PID control scheme using linearization through a specified neural network is developed to control nonlinear processes. The linearization of the neural network model is used to extract the linear model for updating the controller parameters. In the scheme of the optimal tuning PID controller, the concept of general minimum variance and constrained criterias are also considered. In order to meet most of the practical application problems, several variations of the proposed method, including the momentum filter, the updating criterion and the adjustment of the step size of the control action, are presented to make the proposed algorithm more practical. To demonstrate the potential applications of the proposed strategies, two simulation problems, including a pH neutralization and a batch reactor, are applied.

Study on membrane reactors for biodiesel production by phase behaviors of canola oil methanolysis in batch reactors

In comparison with the general stirring batch reactor, the membrane reactor has been reported to have higher molar ratios of methanol to oil but ultralow catalyst concentration in the biodiesel production. In this research, the methanolysis of canola oil is conducted in a stirring batch reactor in the presence of NaOH as a catalyst. Based on the investigation of the effects of operating conditions, including methanol to oil molar ration, catalyst concentrations and temperatures, the time course of the reaction path for the reactant composition in the ternary phase diagram of oil-FAME-MeOH offers an effective way to understand the operation of membrane reactors in the biodiesel production. The results show that increasing the residence time of the whole reactant system within the two-phase zone is good for the separation operation through the membranes.

Derivation of function space analysis based PCA control charts for batch process monitoring

A technique of the multivariate statistical process control for the analysis and monitoring of batch processes is developed. This technique, called FSPCA, combines the function space analysis and the principal component analysis method (PCA). The function space analysis is based on the concept of the orthonormal function approximation. The trajectories of process measurements in the batches are mapped onto the new feature parameters in the function space. Then the concept of the multivariate statistical process control can be applied for this type of new parameters to extract the correlated features. Like the philosophy of statistical process control in the traditional PCA, FSPCA can generate simple monitoring charts, easy tracking of the progress in each batch run and monitoring the occurrence of observable upsets. The proposed technique are that not only the process variables are significantly reduced but also the problem of the varying time in the batch runs is eliminated. Furthermore, the proposed technique can extract the nonlinear feature without heavy computation load. Two major contributions of this paper are made. First, FSPCA is systematically derived. It is proved that the statistic properties of coefficient matrix derived from the orthogonal function follow Gaussian distribution. PCA, thus, can be properly applied. Second, FSPCA is a methodology of general purposes since both fixed operating time and varying operating time are considered. The control charts performance, design and usage are also included. By making comparison with the other methods, the effectiveness of the proposed method is shown through two detailed simulation studies to demonstrate the potential applications of FSPCA.

Correntropy Based Data Reconciliation and Gross Error Detection and Identification for Nonlinear Dynamic Processes

Abstract Measurement information in dynamic chemical processes is subject to corruption. Although nonlinear dynamic data reconciliation (NDDR) utilizes enhanced simultaneous optimization and solution techniques associated with a finite calculation horizon, it is still affected by different types of gross errors. In this paper, two algorithms of data processing, including correntropy based NDDR (CNDDR) as well as gross error detection and identification (GEDI), are developed to improve the quality of the data measurements. CNDDRs reconciliation and estimation are accurate in spite of the presence of gross errors. In addition to CNDDR, GEDI with a hypothesis testing and a distance–time step criterion identifies types of gross errors in dynamic systems. Through a case study of the free radical polymerization of styrene in a complex nonlinear dynamic chemical process, CNDDR greatly decreases the influence of the gross errors on the reconciled results and GEDI successfully classifies the types of gross errors of the measured data.

Plant-Wide Industrial Process Monitoring: A Distributed Modeling Framework

With the growing complexity of the modern industrial process, monitoring large-scale plant-wide processes has become quite popular. Unlike traditional processes, the measured data in the plant-wide process pose great challenges to information capture, data management, and storage. More importantly, it is difficult to efficiently interpret the information hidden within those data. In this paper, the road map of a distributed modeling framework for plant-wide process monitoring is introduced. Based on this framework, the whole plant-wide process is decomposed into different blocks, and statistical data models are constructed in those blocks. For online monitoring, the results obtained from different blocks are integrated through the decision fusion algorithm. A detailed case study is carried out for performance evaluation of the plant-wide monitoring method. Research challenges and perspectives are discussed and highlighted for future work.

Multiloop PID Controller Design using Partial Least Squares Decoupling Structure

The goal of this paper is to identify and control multi-input multi-output (MIMO) processes by means of the dynamic partial least squares (PLS) model, which consists of a memoryless PLS model connected in series with linear dynamic models. Unlike the traditional decoupling MIMO process, the dynamic PLS model can decompose the MIMO process into a multiloop control system in a reduced subspace. Without the decoupler design, the optimal tuning multiloop PID controller based on the concept of general minimum variance and the constrained criteria can be directly and separately applied to each control loop under the proposed PLS modeling structure. Several potential applications using this technique are demonstrated.

Simultaneous data reconciliation and gross error detection for dynamic systems using particle filter and measurement test

Abstract Good dynamic model estimation plays an important role for both feedforward and feedback control, fault detection, and system optimization. Attempts to successfully implement model estimators are often hindered by severe process nonlinearities, complicated state constraints, systematic modeling errors, unmeasurable perturbations, and irregular measurements with possibly abnormal behaviors. Thus, simultaneous data reconciliation and gross error detection (DRGED) for dynamic systems are fundamental and important. In this research, a novel particle filter (PF) algorithm based on the measurement test (MT) is used to solve the dynamic DRGED problem, called PFMT-DRGED. This strategy can effectively solve the DRGED problem through measurements that contain gross errors in the nonlinear dynamic process systems. The performance of PFMT-DRGED is demonstrated through the results of two statistical performance indices in a classical nonlinear dynamic system. The effectiveness of the proposed PFMT-DRGED applied to a nonlinear dynamic system and a large scale polymerization process is illustrated.

Systematic derivations of model predictive control based on artificial neural network

This article presents systematic derivations of setting up a nonlinear model predictive control based on the artifical neural network. Unlike most research in the past, the control law is mathematically developed in detail so that the performance of the ANN-based controller can be improved. In this paper, a three-layer feedforward neural network with hyperbolic tangent functions in the hidden layer and with a linear function in the output layer is used. The two-stage scheme including pseudo Gauss-Newton and least squares is proposed for training ANN. This training method is better than the traditional algorithm in terms of training speed. The Levenberg-Marquardt approximation is also utilized for the minimum of the predictive control criterion. Two typical chemical processes are simulated and the ANN model predictive control applications can reach fairly good results.

Three-way data analysis with time lagged window for on-line batch process monitoring

In this paper, on-line batch process monitoring is developed on the basis of the three-way data structure and the time-lagged window of process dynamic behavior. Two methods, DPARAFAC (dynamic parallel factor analysis) and DTri-PLS (dynamic trilinear partial least squares), are used here depending on the process variables only or on the process variables and quality indices, respectively. Although multivariate analysis using such PARAFAC (parallel factor analysis) and Tri-PLS (trilinear partial least squares) models has been reported elsewhere, they are not suited for practicing on-line batch monitoring owing to the constraints of their data structures. A simple modification of the data structure provides a framework wherein the moving window based model can be incorporated in the existing three-way data structure to enhance the detectability of the on-line batch monitoring. By a sequence of time window of each batch, the proposed methodology is geared toward giving meaningful results that can be easily connected to the current measurements without the extra computation for the estimation of unmeasured process variables. The proposed method is supported by using two sets of benchmark fault detection problems. Comparisons with the existing two-way and three-way multiway statistical process control methods are also included.