The Use of Expert Systems Associated to Agents for Routing Suggestions for Service Orders

被引:0
作者
Zattar, Izabel C. [1 ]
Ferreira, Joao Carlos E. [2 ]
机构
[1] Univ Fed Parana, Curitiba, PR, Brazil
[2] Univ Fed Santa Catarina, Florianopolis, SC, Brazil
来源
NEW WORLD SITUATION: NEW DIRECTIONS IN CONCURRENT ENGINEERING | 2010年
关键词
Multiagent systems; Expert systems; Routing;
D O I
10.1007/978-0-85729-024-3_9
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
In dynamic environments, a great obstacle for the integration between process planning and production scheduling is the lack of flexibility for the analysis of alternative resources during the allocation of the jobs on the shop floor. In this phase the process plan is treated as fixed, that is, scheduling does not consider all the possible manufacturing combinations. In order to solve this problem, it was proposed and developed a multiagent system that enables the use of process plans with on-line alternatives. After implementing the system, a large number of tests were carried out, resulting in a database with more than twelve thousand simulations. By analyzing the results, it was observed that despite shorter makespan and flow times were attained, the standard deviation was high when comparing with other approaches found in the literature. As the problem is significantly complex, involving many parts, resources and alternative plans, an Expert Agent based on the JESS language (Java Expert System Shell) was implemented which, through the application of rules, filters the information in the database of simulations and provides the system with an adequate suggestion of the route to be executed.
引用
收藏
页码:71 / 78
页数:8
相关论文
共 11 条
[1]   The scope of application of multi-agent systems in the process industry:: three case studies [J].
Aldea, A ;
Bañares-Alcántara, R ;
Jiménez, L ;
Moreno, A ;
Martínez, J ;
Riaño, D .
EXPERT SYSTEMS WITH APPLICATIONS, 2004, 26 (01) :39-47
[2]   A REVIEW OF MACHINE LEARNING IN SCHEDULING [J].
AYTUG, H ;
BHATTACHARYYA, S ;
KOEHLER, GJ ;
SNOWDON, JL .
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT, 1994, 41 (02) :165-171
[3]  
Cardoso H.Lopes., Integrating JADE and Jess
[4]   Reactive agent design for intelligent tutoring systems [J].
Cruces, ALL ;
De Arriaga, F .
CYBERNETICS AND SYSTEMS, 2000, 31 (01) :1-47
[5]  
Friedman-Hill E., 2003, Jess in action: Rule-based systems in Java
[6]   A combined optimization and agent-based approach to supply chain modelling and performance assessment [J].
Gjerdrum, J ;
Shah, N ;
Papageorgiou, LG .
PRODUCTION PLANNING & CONTROL, 2001, 12 (01) :81-88
[7]   A symbiotic evolutionary algorithm for the integration of process planning and job shop scheduling [J].
Kim, YK ;
Park, K ;
Ko, J .
COMPUTERS & OPERATIONS RESEARCH, 2003, 30 (08) :1151-1171
[8]  
Rezende Solange Oliveira, 2005, Sistemas inteligentes: fundamentos e aplicacoes, V1
[9]   Agent-based distributed manufacturing process planning and scheduling: A state-of-the-art survey [J].
Shen, Weiming ;
Wang, Lihui ;
Hao, Qi .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2006, 36 (04) :563-577
[10]  
Zattar IC, 2010, THESIS