Abstract
Application of artificial intelligence techniques to planning and scheduling problems are briefly reviewed, issues involved in knowledge acquisition are discussed, and methods for machine learning are introduced.
More in depth treatise of selected approaches, with processing systems engineering examples, are used to illustrate some of the issues involved. The examples utilize genetic programming for batch scheduling and design problems, and a hybrid of symbolic and connectionist approaches to automated knowledge acquisition (machine learning).
Concepts and issues involved in Genetic Programming are discussed within the context of batch processing systems examples. A scheduling example is used to illustrate discrete variable based decision models and associated terminology while a design problem with continuous decision variables and constraints is also optimized. Possibility of using genetic programming as an integrating tool for computer integrated manufacturing is also discussed.
A novel instance based learning algorithm that allows symbolic information to be encoded into a connectionist representation is introduced. Selection of complex distillation column sequencing designs is used as the example. However, the approach is ideally suited for fault diagnosis and structured selection problems. The knowledge/rules extracted from the learning algorithm are very similar to the design heuristics proposed in literature. The performance of the Symbolic Connectionist network (SC-net) is studied based on its knowledge extraction capabilities and the classification accuracy in the test case.
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
Biegler,L.T., I.E. Grossmann and G.V. Reklaitis: Application of Operations Research Techniques in Chemical Engineering. In: Engineering Design, Better Results through Operations Research Methods (R.Levary, ed.), Elsevier Science Publishing Co., Inc. 1988
Booker, L.: Improving Search in Genetic Algorithms. In: Genetic Algorithms and Simulated Annealing (L. Davis, ed.) Morgan Kaufman Publishers, Inc., Los Altos, CA, 1987
Brooks, R.A.: A Robust Layered Control System for a Mobile Robot. IEEE Journal of Robotics and Automation RA-2 1 (1986)
Cukierman, D., R. Owans, and S. Sloseris: Interactivity Activity Scheduling with Object Oriented Constraint Logic Programming. In: Application of Artificial Intelligence in Engineering VIII. Vol:II Computational Mechanics Publications/Elsevier Applied Science. (G. Rzevski et al. ed.), 1993
Das, H., P.T. Cummings, and M.D. LeVan: Scheduling of Serial Multiproduct Batch Processes via Simulated Annealing, Computers in Chemical Engineering, 14 (12), 1351–1362, (1990)
Davis, L: Handbook of Genetic Algorithms. NY: Van Nostrand Reinhold, 1991
DeJong,K.A.: An Analysis of the Behavior of a Class of Genetic Adaptive Systems. Doctoral dissertation, University of Michigan, 1975
Famili, A., D. Nau, and S. Kim: Artificial Intelligence Applications in Manufacturing, AAAI Press/MIT Press, 1992
Fuernsinn, M., and G. Meyer: The Configuration of Automobile Manufacturing Plants Using FAKIR. In: Application of Artificial Intelligence in Engineering VIII. Vol:1 Computational Mechanics Publications/Elsevier Applied Science. (G. Rzevski et al. ed.), 1993
Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Reading, MA: Addison-Wesley 1989
Grefenstette, J.J., L.Davis, and D. Cerys: GENESIS & OOGA - Two Genetic Algorithm Systems, Melrose MA: TSP 1991
Hammond, K., Chef: A Model of Case-Based Planning. In: Proceedings of AAAI-86 (1986)
Hillard, M.R., G.E. Liepens, M. Palmer, M. Morrow, and J. Richardson: A Classifier Based System for Discovering Scheduling Heuristics In: Genetic Algorithms and Their Applications. Proceedings of the Second International Conference on Gnetic Algorithms, 231–235 (1987)
Holland,J.H., Adaptation in Natural and Artificial Systems, The University of Michigan: Ann Arbor 1975
Kapanoglu, M., Genetic Intelligence in Scheduling of Modular Manufacturing Systems, PhD dissertation (in preparation), U.of South Florida, 1995
Kempf, K. C. LePape, S. Smith, and B. Fox: Issues in The Design of AI-Based Schedulers: A Workshop Report. AI Magazine 11 (5) (1991)
Lambrou, S.K., and A.J. Dentsoras: A Machine Based System for Valuation and Consultation on Machine Assemblies during Design for Configuration. In: Application of Artificial Intelligence in Engineering VIII. Vol:1 Computational Mechanics Publications/Elsevier Applied Science. (G. Rzevski et al. ed.) 1993
Laszlo, H, M, Hoffineister, D.W.T. Rippin: Gantt: an Interactive tool, This volume, p. 706
Liepins, G.E., M.R. Hilliard, J. Richardson, and M.Palmer: Genetic Algorithms Applications to Set Covering and Traveling Salesman Problems. In: Operations Research and Artificial Intelligence: The Integration of Problem Solving Strategies (1990)
Mah,R.S.: Chemical Process Structures and Information Flows, Boston: Butterworths 1990
Michalski, J., G. Carbonell, and T.M. Mitchell.: Machine Learning, Volumes I and II, Los Altos: Morgan Kaufman 1986
Minton, S. Machine Learning Methods for Planning, Morgan Kaufmann, 1993
Mitchell, T.M.: Becoming Increasingly Reactive. In: Proceedings AAAI-90
Nilsson, N.J.: Principles of Artificial Intelligence Palo Alto: Morgan Kaufmann 1980
Noronha, S.J., and V.V.S. Sarnia: Knowledge Based Approaches for Scheduling Problems: A Survey, IEEE Transactions on Knowledge and Data Engineering, 3, 160–171 (1991)
Patel, A.N., R.S.H. Mah, and I.A. Karimi. Preliminary Design of Multi-product Noncontinuous Plants Using Simulated Annealing, Computers and Chemical Engineering, 15, 451–469 (1991)
Pearl, Judea: Heuristics. Addison-Wesley, 1985
Raich, A., X. Wu, and A. Cinar: Comparison of Neural Networks and Nonlinear Time Series Techniques for Dynamic Modeling of Chemical Processes. This volume, p. 309
Realff, M,: Learning Localized Heuristics in Batch Scheduling. Internal report LISPE 88–053, MIT, 1989
Realff, M,: An Analysis of the Chemical Batch Production Problem and a Detailed Methodology for Scheduling. Internal report LISPE 88–054, MIT, 1989
Rich, E and K. Knight: Artificial Intelligence, McGraw-Hill, 1991
Romaniuk, S.G. Extracting Knowledge from a hybrid Symbolic, Connectionist network. Ph.D thesis, Univ. of South Florida 1991
Smith, P., E. Fletcher, F. Gronskov, L. Malmgren-Hansen, K.Ho, B. Gaze: CIM.REFLEX- Using Expert System Technology to Achieve Real Time Shop Floor Scheduling. In: Application of Artificial Intelligence in Engineering VIII. Vol:II Computational Mechanics Publications/Elsevier Applied Science. (G. Rzevski et al. ed.) 1993
Tedder, D.W., Rudd, D.F.: Parametric Studies in Industrial Distillation. AICHE J. 24, No. 2, (1978)
Tsukiyama, M., K. Mori, and T. Fukuda: Strategic Level Interactive Scheduling and Operational Level Real-Time Scheduling for Flexible Manufacturing Systems. In: Application of Artificial Intelligence in Engineering VIII. Vol:II Computational Mechanics Publications/Elsevier Applied Science. (G. Rzevski et al. ed.) 1993
Venkatasubramanian, V.: Fault Diagnosis Through Neural Networks. This volume, p. 631
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sunol, A.K., Kapanoglu, M., Mogili, P.K. (1996). Selected Topics in Artificial Intelligence for Planning and Scheduling Problems, Knowledge Acquisition, and Machine Learning. In: Reklaitis, G.V., Sunol, A.K., Rippin, D.W.T., Hortaçsu, Ö. (eds) Batch Processing Systems Engineering. NATO ASI Series, vol 143. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-60972-5_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-60972-5_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-64635-5
Online ISBN: 978-3-642-60972-5
eBook Packages: Springer Book Archive