Abstract
A process model for heavy oil upgrading was developed using a machine learning system based on rough sets. The model has incorporated temporal patterns for control-loop responses and key relationships between the variables at low (feedback) and high (supervisory) control levels. The model predicted reactor temperature distribution with 90 to 95 percent accuracy. Accuracy depended on the number of training cycles and on the temperature resolution used. The key advantages of using the rough sets approach were: 1) it allowed the use of qualitative and quantitative process information in the model; 2) it provided a unified description of temporal events and patterns; and 3) it permitted the use of “raw” sensor data without preprocessing.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Astron, K.J. (1986) “Auto-tuning Adaptation and Smart Control”, in Morari and McAroy (eds.) Chemical Process Control - CPC III, CACHE-Elsevier.
Birky, G.J., McAroy, T.J., and Modares, M. (1988) “An Expert System for Distillation Control Design”, Computers and Chemical Engineering, 12, 1045–63.
Buezli, C.W. Jr. (1986) “Summary of Research Activities”, AAAI Workshop on AI for Process and Industrial Monitoring and Control, AAAI-86, Philadelphia, PA.
Cheung, J.T. and Stephanopoulos, G. (1989) “Representation of Process Trends, Part I and II”, Technical Report, Laboratory of Intelligent Systems in Process Engineering, Department of Chemical Engineering, MIT.
Garrison, D.B., Pret, D.M., and Steachy, P.E. (1986) “Expert Systems in Process Control and Optimization - A Perspective”, AAAI-86 Workshop, Philadelphia, PA.
Mavrovouniotis, M. (ed.) (1989) Artificial Intelligence Applications in Process Engineering. Academic Press.
McLellan, J., J. Tscheng, and Purvis, D.H. (1986) “A Real-Time Dynamic Simulator for the CANMET Hydrocracking Process”, paper presented at 1986 Summer Computer Simulation Conference, Reno, Nevada.
Mrozek, A. (1986) “Use of Rough Sets and Decision Tables for Implementing Rule-Based Control of Industrial Processes”, Bull. Polish Acad. Sci. Tech. 34, 357.
Oyen, R.A. (1986) “Summary of Research Activities”, AAAI Workshop on AI for Process and Industrial Monitoring and Control, AAAI-86, Philadelphia, PA.
Pawlak, Z. (1985) “Decision Tables and Decision Algorithms”, Bull. Pol. Acad. Sci. (Tech. Sci.), 33, No. 9–10, 487–494.
Pawlak, Z. (1982) “Rough Sets”, International Journal of Computer and Information Sciences, 11, 341–356.
Rowan, D.A. (1989) “On-Line Expert Systems in Process Industries”, AI Expert Magazine, August.
Shum, S.K., Gandikota, M.S., Ramesh, T.S., McDowell, J.K., Myers, D.R., Whitely, J.R., and Davis, J.F. (1989) “A Knowledge-based System Framework for Diagnosis of Process Plants”, Seventh Power Plant Dynamics, Control and Testing Symposium, Knoxville, TN.
Stephanopolous, G. (ed.) (1989) CACHE Case Studies Series, Knowledge-Based Systems in Process Engineering, Austin, Texas: CACHE Corporation.
Whitely, J.R. and Davis, J.F. (1990) “Application of Neural Networks to Qualitative Interpretation of Process Sensor Data.” AICHE Spring National Meeting, Orlando.
Ziarko, W. and Katzberg, J. (1989) “Control Algorithm Acquisition” in Knowledge-Based System Diagnosis, Supervision and Control, Plenum Publishing Corp., pp. 167–178.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Szladow, A.J., Ziarko, W.P. (1992). Knowledge-Based Process Control Using Rough Sets. In: Słowiński, R. (eds) Intelligent Decision Support. Theory and Decision Library, vol 11. Springer, Dordrecht. https://doi.org/10.1007/978-94-015-7975-9_4
Download citation
DOI: https://doi.org/10.1007/978-94-015-7975-9_4
Publisher Name: Springer, Dordrecht
Print ISBN: 978-90-481-4194-4
Online ISBN: 978-94-015-7975-9
eBook Packages: Springer Book Archive