A Hybrid Inductive Learning-based Scheduling Knowledge Acquisition Algorithm

It is a crucial issue that constructing a successful knowledge base to satisfy an efficient adaptive scheduling for the complex manufacturing system. Therefore, a hybrid inductive learning-based scheduling knowledge acquisition algorithm is presented in this paper. We combined genetic algorithm (GA) with simulated annealing (SA) to develop a hybrid optimization method, in which GA was introduced to present parallel search architecture and SA was introduced to increase escaping probability from local optima and ability to neighbor search. The hybrid method was utilized to resolve the optimal subset of manufacturing system attributes and determine the optimal parameters of decision tree (DT) under different scheduling objectives; DT was used to evaluate the fitness of chromosome in the method and generate the scheduling knowledge after obtaining the optimal attributes subset, optimal DT's parameters. The experimental results demonstrate that the proposed algorithm produces significant performance improvements over other machine learning-based algorithms.

[1]  Michael J. Shaw,et al.  Learning-based scheduling in a flexible manufacturing flow line , 1994 .

[2]  Michael J. Shaw,et al.  Adaptive scheduling in dynamic flexible manufacturing systems: a dynamic rule selection approach , 1997, IEEE Trans. Robotics Autom..

[3]  Ruey-Shiang Guh,et al.  The optimization of attribute selection in decision tree-based production control systems , 2006 .

[4]  Yuehwern Yih,et al.  Auto-bias selection for developing learning-based scheduling systems , 1999 .

[5]  Kevin R. Caskey.  A manufacturing problem solving environment combining evaluation, search, and generalisation methods , 2001 .

[6]  Kenneth R. Baker,et al.  Sequencing Rules and Due-Date Assignments in a Job Shop , 1984 .

[7]  Yuehwern Yih,et al.  Integration of inductive learning and neural networks for multi-objective FMS scheduling , 1998 .

[8]  K. T. Yeo,et al.  An expert neural network system for dynamic job shop scheduling , 1994 .

[9]  Michael J. Shaw,et al.  Intelligent Scheduling with Machine Learning Capabilities: The Induction of Scheduling Knowledge§ , 1992 .

[10]  Gary J. Koehler,et al.  Theory and practice of decision tree induction , 1995 .

[11]  Alberto Gómez,et al.  A review of machine learning in dynamic scheduling of flexible manufacturing systems , 2001, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[12]  Ling Wang,et al.  An effective hybrid optimization strategy for job-shop scheduling problems , 2001, Comput. Oper. Res..

[13]  L. N. Van Wassenhove,et al.  Analysis of Scheduling Rules for an FMS , 1990 .

[14]  Yohanan Arzi,et al.  Operating an FMC by a decision-tree-based adaptive production control system , 2000 .

[15]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[16]  Yuehwern Yih,et al.  A competitive neural network approach to multi-objective FMS scheduling , 1998 .