Hybrid intelligent control strategy. Supervising a DCS-controlled batch process

In industrial control, it frequently happens that, while the low-level controller performs very well, high-level supervision is required to maintain good overall performance that is usually beyond the capability of direct machine control. A hybrid control methodology combining conventional and intelligent techniques has been introduced to replace human supervision for a DCS-controlled laminar cooling process. The industrial experiments show the improved performance of the proposed hybrid control model and confirm its validity in a real manufacturing environment. The results can be extended to a wide range of processes with similar features. The methodology is superior in terms of high performance, reliability, simplicity and ease of construction.

[1]  Michel Dussud,et al.  Application of fuzzy logic control for continuous casting mold level control , 1998, IEEE Trans. Control. Syst. Technol..

[2]  Bjarne A. Foss,et al.  A field study of the industrial modeling process , 1998 .

[3]  Toshiaki Itoh,et al.  Future needs for control theory in industry-report of the control technology survey in Japanese industry , 1999, IEEE Trans. Control. Syst. Technol..

[4]  R. Braatz,et al.  Globally optimal robust process control , 1999 .

[5]  R. Pearson.  Nonlinear Input/Output Modeling , 1994 .

[6]  Stephen A. Billings,et al.  Non-linear system identification using neural networks , 1990 .

[7]  Frank L. Lewis,et al.  A framework for hybrid control design , 1997, IEEE Trans. Syst. Man Cybern. Part A.

[8]  G. van Ditzhuijzen,et al.  The controlled cooling of hot rolled strip: a combination of physical modeling, control problems and practical adaption , 1993, IEEE Trans. Autom. Control..

[9]  Feng Gao,et al.  Process control: Art or practice , 1995 .

[10]  Peter J. Fleming,et al.  Development framework approach to heterogeneous system design for control systems , 1996 .

[11]  Graham M. Geary,et al.  The control of input-constrained nonlinear processes using numerical generalized predictive control methods , 1998, IEEE Trans. Ind. Electron..

[12]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.

[13]  R. Perne,et al.  Design and control of batch reactors , 1995 .

[14]  Mituhiko Araki,et al.  Future needs for the control theory in industries—report and topics of the control technology survey in Japanese industry , 1998 .

[15]  Michael J. Piovoso,et al.  A multivariate statistical controller for on-line quality improvement , 1998 .

[16]  Karl Johan Åström,et al.  Process control--Past, present and future , 1985 .

[17]  Karl Johan Åström,et al.  Adaptive Control , 1989, Embedded Digital Control with Microcontrollers.

[18]  Han-Xiong Li,et al.  Conventional fuzzy control and its enhancement , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[19]  George Krauss,et al.  Principles of Heat Treatment of Steel , 1980 .

[20]  Jordan M. Berg,et al.  Neural-network feedback control of an extrusion , 1998, IEEE Trans. Control. Syst. Technol..

[21]  Sunwon Park,et al.  PID controller tuning to obtain desired closed loop responses for cascade control systems , 1998 .

[22]  M. Friedrich,et al.  Design and control of batch reactors: -An industrial viewpoint- , 1995 .

[23]  Wang Jin,et al.  A knowledge-based controller with fuzzy reasoning used in process control , 1997 .

[24]  Shaocheng Tong,et al.  Fuzzy adaptive control for a class of nonlinear systems , 1999, Fuzzy Sets Syst..

[25]  Katalin M. Hangos,et al.  Grey box modelling for control : qualitative models as a unifying framework , 1995 .

[26]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..

[27]  Natsuo Hatta,et al.  Numerical Modeling for Cooling Process of a Moving Hot Plate by a Laminar Water Curtain , 1989 .