Two stage case-based reasoning application research on steel-making dynamic scheduling

Autor: Kun-Yuan Hu, Chun-Guang Chang, Bing-Lin Zheng, Ding-Wei Wang
Rok vydání: 2005
Předmět:
Zdroj: Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).
DOI: 10.1109/icmlc.2004.1382147
Popis: The purpose of this paper is to solve dynamic scheduling complex problem during steel making. To realize system stability, the 2-stage CBR (case-based reasoning) rather than conventional one-stage CBR is proposed. The framework of the 2-stage CBR is presented firstly. Then, its application to steel-making dynamic scheduling is introduced in detail such as case representation, case classifying, case retrieval, case adaptation, case evaluation, and case maintenance. Furthermore, the prototype system is developed and the running result obtains satisfactory result on system velocity, validity and stability. With the prototype system further perfected, it is put into application with benefits expected.
Databáze: OpenAIRE