Artificial intelligence for monitoring and supervisory control of process systems

https://doi.org/10.1016/j.engappai.2006.07.002Get rights and content

Abstract

Complex processes involve many process variables, and operators faced with the tasks of monitoring, control, and diagnosis of these processes often find it difficult to effectively monitor the process data, analyse current states, detect and diagnose process anomalies, or take appropriate actions to control the processes. The complexity can be rendered more manageable provided important underlying trends or events can be identified based on the operational data (Rengaswamy and Venkatasubramanian, 1992. An Integrated Framework for Process Monitoring, Diagnosis, and Control Using Knowledge-based Systems and Neural Networks. IFAC, Delaware, USA, pp. 49–54.). To assist plant operators, decision support systems that incorporate artificial intelligence (AI) and non-AI technologies have been adopted for the tasks of monitoring, control, and diagnosis. The support systems can be implemented based on the data-driven, analytical, and knowledge-based approach (Chiang et al., 2001. Fault Detection and Diagnosis in Industrial Systems. Springer, London, Great Britain). This paper presents a literature survey on intelligent systems for monitoring, control, and diagnosis of process systems. The main objectives of the survey are first, to introduce the data-driven, analytical, and knowledge-based approaches for developing solutions in intelligent support systems, and secondly, to present research efforts of four research groups that have done extensive work in integrating the three solutions approaches in building intelligent systems for monitoring, control and diagnosis. The four main research groups include the Laboratory of Intelligent Systems in Process Engineering (LISPE) at Massachusetts Institute of Technology, the Laboratory for Intelligent Process Systems (LIPS) at Purdue University, the Intelligent Engineering Laboratory (IEL) at the University of Alberta, and the Department of Chemical Engineering at University of Leeds. The paper also gives some comparison of the integrated approaches, and suggests their strengths and weaknesses.

Introduction

Computerized control systems that monitor, control, and diagnose process variables such as pressure, flow, and temperature have been implemented for various processes. When these systems are for large-scale processes, they generate many process variable values, and operators often find it difficult to effectively monitor the process data, analyze current states, detect and diagnose process anomalies, and/or take appropriate actions to control the processes. To assist plant operators, process operational information must be analysed and presented in a manner that reflects the important underlying trends or events in the process (Rengaswamy and Venkatasubramanian, 1992). Intelligent decision support systems that incorporate a variety of AI and non-AI techniques can support this task. Our survey of some relevant literature reveals three general solution approaches for supporting the tasks of monitoring, control, and diagnosis can be identified. They include the data-driven, analytical, and knowledge based approaches (Chiang et al., 2001). Our review of the relevant literature also reveals extensive research effort has been devoted to enhancing robustness of the approaches by combining them so as to minimize their weaknesses and maximize their strengths. However, successful integration of the three approaches has not been realized. The task of integrating the solution approaches is rendered more complex due to the proliferation of software and databases, which makes it impossible to combine these approaches using the rigid structure of conventional integration methods. The objective of this paper is to explain characteristics of the three solution approaches and present efforts at integration conducted at some major research centers in both North America and Europe. The discussion also presents a summary of approaches from each of the four research groups as well as their advantages and disadvantages.

Section snippets

Solution approaches for developing intelligent support systems in process control engineering

For developing decision support systems in process control engineering, the three solution approaches of data driven, analytical, and knowledge-based have been identified; each approach will be discussed in detail as follows.

A survey of four integrated approaches for monitoring, diagnosis and control of industrial processes

Our survey on literature about development of intelligent systems for monitoring, diagnosis and control in process industries reveals that the three solution approaches described in Section 2 are often combined in system construction. Due to growing complexity of current systems, the integration of the three solution approaches into an intelligent system requires a framework which coordinates communication among the different solution modules. Tzafestas and Verbruggen (1995) stated that an

Discussion

On comparing the four integrated frameworks of IRTW, INTEMOR, OOSE, and DKIT in terms of their approaches and tasks addressed, a number of similarities and differences can be observed. The four integrated frameworks for development of intelligent systems for process systems combine the three solution approaches, but the priority they assign to the approaches are different. INTEMOR, DKIT and IRTW give the highest priority to the knowledge-based system (KBS) solution approach whereas OOSS assign

Conclusion

This paper has presented an overview of research work on development of intelligent systems for monitoring, supervisory control, and diagnosis of operations in process systems engineering. We have discussed the three solution approaches often adopted for building automated systems in process control engineering, namely the data-driven, analytical and knowledge-based approaches. Some popular algorithms and applications of each approach have also been discussed. We have also presented what we

Acknowledgement

We would like to acknowledge the generous financial support of a Strategic Grant from Natural Sciences and Engineering Research Council (NSERC) of Canada.

References (117)

  • W. Lin et al.

    Nonlinear dynamic principal component analysis for on-line process monitoring and diagnosis

    Computers & Chemical Engineering

    (2000)
  • I. Miletic et al.

    An industrial perspective on implementing on-line applications of multivariate statistics

    Journal of Process Control

    (2004)
  • D. Mylaraswamy et al.

    A hybrid framework for large-scale process fault diagnosis

    Computers & Chemical Engineering

    (1997)
  • A. Norvilas et al.

    Intelligent process monitoring by interfacing knowledge-based system and multivariate statistical monitoring

    Journal of Process Control

    (2000)
  • Y. Power et al.

    A two-step supervisory fault diagnosis framework

    Computers & Chemical Engineering

    (2004)
  • Y. Power et al.

    Integration techniques in intelligent operational management: a review

    Knowledge-Based Systems

    (2005)
  • M. Rao et al.

    Intelligent system architecture for process operation support

    Expert Systems with Applications

    (2000)
  • D. Ruiz et al.

    On-line fault diagnosis system support for reactive scheduling in multipurpose batch chemical plants

    Computers & Chemical Engineering

    (2001)
  • G. Stephanopoulos

    Artificial intelligence in process engineering—current state and future trends

    Computers & Chemical Engineering

    (1990)
  • G. Stephanopoulos et al.

    Intelligent systems in process engineering: a review

    Computers & Chemical Engineering

    (1996)
  • G. Stephanopoulos et al.

    MODEL.LA. a modeling language for process engineering—I. the formal framework

    Computers & Chemical Engineering

    (1990)
  • G. Stephanopoulos et al.

    MODEL.LA. a modeling language for process engineering—II. multifaceted modeling of processing systems

    Computers & Chemical Engineering

    (1990)
  • C.L. Sun et al.

    An integrated expert system/operation research approach for automation of natural gas pipeline operations

    Engineering Applications Artificial Intelligence

    (2000)
  • C. Ündey et al.

    Real-time batch process supervision by integrated knowledge-based systems and multivariate statistical methods

    Engineering Applications Artificial Intelligence

    (2003)
  • C. Ündey et al.

    Intelligent real-time performance monitoring and quality prediction for batch/fed-batch cultivations

    Journal of Biotechnology

    (2004)
  • V. Uraikul et al.

    Development of an expert system for optimizing natural gas pipeline operations

    Expert System with Applications

    (2000)
  • H. Vedam et al.

    An intelligent operator decision support system for abnormal situation management

    Computational Chemical Engineering

    (1999)
  • V. Venkatasubramanian et al.

    A review of process fault detection and diagnosis part II: qualitative models and search strategies

    Computers & Chemical Engineering

    (2003)
  • V. Venkatasubramanian et al.

    A review of process fault detection and diagnosis part III: process history based methods

    Computers & Chemical Engineering

    (2003)
  • V. Venkatasubramanian et al.

    A review of process fault detection and diagnosis part I: quantitative model-based methods

    Computers & Chemical Engineering

    (2003)
  • A.O. Adebiyi et al.

    Dynamic neural networks partial least squares (DNNPLS) identification of multivariable processes

    Computers & Chemical Engineering

    (2003)
  • K.R. Aggarwal et al.

    Novel approach to fault diagnosis in multicircuit transmission lines using fuzzy ARTmap neural network

    IEEE Transactions on Neural Networks

    (1999)
  • S. Albayrak et al.

    Distributed artificial intelligence in manufacturing control

  • H. Al-Bazzaz et al.

    Statistical process control charts for batch operations based on independent component analysis

    Industrial Engineering and Chemistry Research

    (2004)
  • P.A. Alexandridis et al.

    Modelling of Nonlinear Process dynamics using kohonen's neural networks, fuzzy systems and chebyshev series

    Computers & Chemical Engineering

    (2002)
  • R.B. Bakshi et al.

    Representation of process trends—III multiscale extraction of trends from process data

    Computers & Chemical Engineering

    (1994)
  • R.B. Bakshi et al.

    Representation of process trends—IV induction of real-time patterns from operating data for diagnosis and supervisory control

    Computers & Chemical Engineering

    (1994)
  • V.J. Beck et al.

    Parameter Estimation in Engineering and Science

    (1977)
  • J.G. Chen et al.

    Robust PCA and normal region in multivariate statistical process monitoring

    AIChE Journal

    (1996)
  • T.C. Chen et al.

    Intelligent process control using neural fuzzy techniques

    Journal of Process Control

    (1999)
  • Z.F. Chen et al.

    An integrated data mining system and its application to process operational data analysis

    Computers & Chemical Engineering

    (1999)
  • Z.F. Chen et al.

    Discovery of operational spaces from process data for production of multiple grades of products

    Industrial Engineering and Chemistry Research

    (2000)
  • H.B. Chen et al.

    On-line operational support system for faults diagnosis in process plants

    Computers & Chemical Engineering

    (1998)
  • Y.J.T. Cheung et al.

    Representation of process trends—Part I. A formal representation framework

    Computers & Chemical Engineering

    (1990)
  • Y.J.T. Cheung et al.

    Representation of process trends—Part II. The problem of scale and qualitative scaling

    Computers & Chemical Engineering

    (1990)
  • H.L. Chiang et al.

    Fault Detection and Diagnosis in Industrial Systems

    (2001)
  • A.F. Cubillos et al.

    Adaptive hybrid neural models for process control

    Computers & Chemical Engineering

    (1998)
  • X. Ding et al.

    Observer-based fault detection optimized in the frequency domain

  • S.R. Engelmore et al.

    Introduction (chapter 1)

  • Cited by (186)

    View all citing articles on Scopus
    View full text