Iori Hashimoto

Comparison of Multivariate Statistical Process Monitoring Methods with Applications to the Eastman Challenge Problem

Abstract To improve the performance of multivariate statistical process control (MSPC), two advanced methods, moving principal component analysis (MPCA) and DISSIM, have been proposed. In MPCA and DISSIM, an abnormal operation can be detected by monitoring the directions of principal components and the dissimilarity index, respectively. Another important extension of MSPC was made with Multiscale PCA (MS-PCA). The present work investigates the characteristics of several statistical monitoring methods. The monitoring performance is compared with applications to simulated data obtained from a 2×2 process and the Tennessee Eastman process. The superiority of MPCA and DISSIM over the conventional methods comes from the fact that those methods focus on changes in the distribution of process data. Furthermore, the advantages of MPCA or DISSIM over the conventional MSPC and that of MS-PCA are combined, and new methods, termed MS-MPCA and MS-DISSIM, are proposed.

A new multivariate statistical process monitoring method using principal component analysis

Abstract Principal component analysis (PCA) has been used successfully as a multivariate statistical process control (MSPC) tool for detecting faults in processes with highly correlated variables. In the present work, a novel statistical process monitoring method is proposed for further improvement of monitoring performance. It is termed ‘moving principal component analysis’ (MPCA) because PCA is applied on-line by moving the time-window. In MPCA, changes in the direction of each principal component or changes in the subspace spanned by several principal components are monitored. In other words, changes in the correlation structure of process variables, instead of changes in the scores of predefined principal components, are monitored by using MPCA. The monitoring performance of the proposed method and that of the conventional MSPC method are compared with application to simulated data obtained from a simple 2×2 process and the Tennessee Eastman process. The results clearly show that the monitoring performance of MPCA is considerably better than that of the conventional MSPC method and that dynamic monitoring is superior to static monitoring.

Inferential control system of distillation compositions using dynamic partial least squares regression

In order to control product compositions in a multicomponent distillation column, the distillate and bottom compositions are estimated from on-line measured process variables. In this paper, inferential models for estimating product compositions are constructed using dynamic Partial Least Squares (PLS) regression, on the basis of simulated time series data. It is found that the use of past measurements is eAective for improving the accuracy of the estimation. The influence of selection of measurements and sampling intervals on the performance is also investigated. From the detailed dynamic simulation results, it is found that the cascade control system based on the proposed dynamic PLS model works much better than the usual tray temperature control system. # 2000 IFAC. Published by Elsevier Science Ltd. All rights reserved.

Comparison of statistical process monitoring methods: application to the Eastman challenge problem

Abstract Multivariate statistical process control (MSPC) has been successfully applied to chemical procesess. In order to improve the performance of fault detection, two kinds of advanced methods, known as moving principal component analysis (MPCA) and DISSIM, have been proposed. In MPCA and DISSIM, an abnormal operation can be detected by monitoring the directions of principal components (PCs) and the degree of dissimilarity between data sets, respectively. Another important extension of MSPC was made by using multiscale PCA (MS-PCA). In the present work, the characteristics of several monitoring methods are investigated. The monitoring performances are compared with using simulated data obtained from the Tennessee Eastman process. The results show that the advanced methods can outperform the conventional method. Furthermore, the advantage of MPCA and DISSIM over conventional MSPC (cMSPC) and that of the multiscale method are combined, and the new methods known as MS-MPCA and MS-DISSIM are proposed.

Inferential control of distillation compositions: selection of model and control configuration

Abstract This article is concerned with a classical problem of how to design an inferential control system for enhancing the performance of distillation composition control. In this article, a new inferential control, termed “predictive inferential control,” is proposed. In the predictive inferential control system, future compositions predicted from on-line measured process variables are controlled instead of the estimates of current compositions. The key concept of the predictive inferential control is to realize feedback control with a feedforward effect by the use of the inherent nature of a distillation column. The detailed dynamic simulation results show that the proposed predictive inferential control scheme integrated with cascade control works considerably better than other control schemes. Furthermore, the improvement of the control performance through iterative modeling or control-relevant identification is also demonstrated.

Theory and practice of optimal control in continuous fermentation process

In this paper a mathematical model of aminoacid fermentation using bacteria is built based on the kinetic study of experimental data of the pilot plant. This model makes it possible to formulate mathematically two optimal control problems in the actual process: (1) the problem of optimal start-up to a desired steady state, involving the optimization of the steady state, and (2) the problem of dynamical operation aiming at the maximum production of the amino-acid within a specified operation period. Both problems are solved by the maximum principle and Greens theorem. The numerical results suggest one of the most practical patterns of operation.

Dynamic interaction and multiloop control system design

Abstract Existing interaction measures cannot consistently provide accurate results for variable pairing in the design of multiloop control systems. Each defined measure, including the RGA and DNA, has its own limitations. In this paper, a generalized dynamic relative gain (GDRG) is used to analyse the loop interactions of a multiloop control system. In doing so, an interaction potential is introduced as a basic part of a proposed approach for selecting pairings of input/output variables. This approach consists of two steps. The first is to eliminate some infeasible pairings by using the static RGA. The second is to determine preferred input/output pairings by using the proposed interaction potential. By comparing the interaction measures for variable pairing that incorporate the interaction potential with those that utilize other established methods, it is shown that the former renders better results.

Optimal Design and Operation of Complex Batch Distillation Column

Abstract A new type of batch distillation column called a “complex batch distillation column” is proposed, and the characteristics of this column are studied. In the complex “batch distillation column, the feed is supplied to the middle of the column, and the liquid on the feed tray is recycled to the feed tank. The complex column is convenient for removing light and heavy impurities from the raw materials since the impurities could be withdrawn simultaneously from the top and the bottom. In this research, the complex column is regarded as a combined system of ordinary and stripping batch distillation columns where the condenser of the stripping column is heat-integrated with the reboilerof the ordinary column. First, the differences between the ordinary and stripping columns are clarified analytically. By using this result, the conditions at which the complex column works effectively compared with the ordinary batch distillation column are clarified.

Systematic structure generation for reactive distillation processes

Abstract This paper proposes a systematic structure generation method for reactive distillation processes. When a feed composition to the process is given, the maximum degree of conversion and product compositions of the reactive distillation column are calculated by using the method called Static Analysis (SA). In order to derive the results, the SA uses only the information about the physicochemical properties of the reaction mixture and a selected feed composition. From the results obtained by the SA, the entire feed composition region is classified into several subregions, each of which has different product configurations. Then, a specific process structure consisting of two or three columns is generated for each of the feed subregions. Finally, the design parameters of the columns and the operating conditions are determined by a process simulator. The proposed method is applied to three example problems: the production of MTBE, the esterification of methanol and acetic acid, and the hydrolysis of methyl acetate. The results show that many different feasible structures are enumerated systematically, and that most of the infeasible structures can be eliminated before precise simulations are executed. In the SA, unrealistic assumptions such as infinite flow rate in the column are introduced to simplify the analysis. However, for the above-mentioned examples a good agreement between the results of the SA and those obtained by precise simulations is achieved. Thus, it can be concluded that the results obtained by using the SA are reliable and can be widely used to generate feasible structures of RD processes.

Optimal operation policy for total reflux and multi-effect batch distillation systems

Abstract The optimal operation policy which minimizes energy consumption is derived for a total-reflux-type batch distillation system and for a new type of separation system called ‘multi-effect batch distillation system (MEBAD)’. The results of optimizations for the binary system show that the separation performance of the total reflux column is increased remarkably by optimizing the reboiler hold-up as a function of time, and that the performance is the same or even better than that of the rectifying column if the hold-up is optimized. The MEBAD can be regarded as a heat-integrated batch distillation system. Thus, for ternary systems the separation performance of the MEBAD is better than the conventional batch distillation column even if the hold-up of each vessel is kept constant during the entire operation period. Furthermore, the simulation results indicate that by optimizing the hold-up of each vessel as a function of time the separation performance of the MEBAD can be improved to the level of a continuous distillation system.