An improved adaptive neural network for job-shop scheduling

Date

2005

Advisors

Journal Title

Journal ISSN

ISSN

DOI

Volume Title

Publisher

IEEE Press

Type

Conference

Peer reviewed

Yes

Abstract

Job-shop scheduling is one of the most difficult production scheduling problems in industry. This paper presents an improved adaptive neural network together with heuristic methods for job-shop scheduling problems. The neural network is based on constraints satisfaction of job-shop scheduling and can adapt its structure and neuron connections during the solving. Several heuristics are also proposed to be combined with the neural network to guarantee its convergence, accelerate its solving process, and improve the quality of solutions. Experimental study shows that the proposed hybrid approach outperforms two classical heuristic algorithms regarding the quality of solutions.

Description

Keywords

Adaptive neural network, Job-shop scheduling, Constraint satisfaction, Heuristics

Citation

Yang, S. (2005) An improved adaptive neural network for job-shop scheduling. Proceedings of the 2005 IEEE International Conference on Systems, Man and Cybernatics, 2, pp. 1200-1205

Rights

Research Institute

Institute of Artificial Intelligence (IAI)