Intelligent and collaborative Multi-Agent System to generate and schedule production orders (original) (raw)
Related papers
The authors describe the implementation of a multi-agent system, whose goal is to enhance production planning i.e. to improve the construction of production orders. This task has been carried out traditionally by the module known as production activity control (PAC). However, classic PAC systems lack adaptive techniques and intelligent behaviour. As a result they are mostly unfit to handle the NP Hard combinatorial problem underlying the construction of right production orders. To overcome this situation, we illustrate how an intelligent and collaborative multi-agent system (MAS) obtains a correct production order by coordinating two different techniques to emulate intelligence. One technique is performed by a feed-forward neural network (FANN), which is embedded in a machine agent, the objective being to determine the appropriate machine in order to fulfil clients’ requirements. Also, an expert system is provided to a tool agent, which in turn is in charge of inferring the right tooling. The entire MAS consists of a coordinator, a spy, and a scheduler. The coordinator agent has the responsibility to control the flow of messages among the agents, whereas the spy agent is constantly reading the Enterprise Information System. The scheduler agent programs the production orders. We achieve a realistic MAS that fully automates the construction and dispatch of valid production orders in a factory dedicated to produce labels.
International Journal of Advanced Manufacturing Technology, 2009
The authors describe the implementation of a supervised learning algorithm within a multi-agent system, whose general objective is to build production orders. Although this task has been carried out traditionally by the production management system, the classic approach lacks adaptive techniques and intelligent behavior. It is acknowledged that the combinatorial problem underlying the construction of production orders belongs to the NP hard complexity class. Therefore, flexible computational solutions are needed. We claim that by using intelligence and collaboration in a multi-agent system (MAS), a correct solution is reached more efficiently. Intelligence is emulated by both learning and decision-making, achieved through a feed-forward artificial neural network (FANN). The FANN is embedded in a machine agent, which determines the appropriate machine to manufacture the product. Collaboration is obtained by employing a sound protocol based on FIPA-ACL messages. We illustrate the approach by designing and implementing a MAS, which is already in use in a company that produces labels.
And Schedule Production Orders
2015
constructing and releasing production orders. In a manufac-turing enterprise, the generation of production orders con-sists in a set of coordinated tasks among departments. This has been achieved traditionally as a module of the Production Activity Control (PAC) system. However, classic PAC mod-ules lack collaborative techniques and intelligent behaviour. Moreover, in real-life situations experienced planners take over traditional PAC systems, since the range of possibilities to actually build production orders increases exponentially. To contribute to production planning, we present an intelli-gent and collaborative Multi-Agent System (MAS), having coordinated two forms to emulate intelligence. The learn-ing capability is achieved by means of a Feed-forward Arti-ficial Neural Network (FANN) with the back-propagation algorithm. The FANN is embedded within a machine agent whose objective is to obtain the appropriate machine in order to comply with requirements coming from the sales d...
Distributed production planning and control agent-based system
International Journal of Production Research, 2006
A model of an Agent based Production Planning and Control (PPC) system able to be dynamically adaptable to local and distributed utilization of production resources and materials is presented. The PPC system is based on the selection of resources to deal with one order of different quantities of one product each time. In this way it is build one scheduling solution for that particular order. The production resources are selected and scheduled using a multiagent system supported by an implementation of the Smith Contract Net, using Java Spaces technology. The multiagent system is based on three main agents: Client, Resource and Manager. These agents negotiate the final product, and the correspondent components, requested by the client. An order for each product (component) triggers a process of dynamic design of a production system to fulfill that particular order. This system exists till the end of the order.
Multiagent Systems for Production Planning in Automation
Lecture Notes in Computer Science, 2011
The production planning represents a key activity in the performance of the industry, reason why the necessity of applications that offer support to this activity, that allow to reach the goals of production with the maximum benefit. The proposal of this work is to develop a Multiagent Systems (MAS) for the Production Planning in Industrial Automation (specifically, in continuous processes). In addition, we present an application of our proposal in a process of petroleum production based on the Artificial Gas Lift Method.
A general agent-based architecture for production planning i electronic commerce scenarios
2000
The creation of a general architecture for the use of agents in production planning is addressed. The modularity and flexibility provided by an agent-oriented system proves itself useful in dynamic scenarios. The anthropomorphic features of the agents make them suitable for Electronic Commerce systems. Agents enable the interconnection of already existent web-based systems with the production lines of a company, potentiating higher degrees of client satisfaction.
Intelligent Agents for Production Systems, In Intelligent Agent-based Operations Management
The paper focuses on development of new approaches based on interactions between intelligent agents, operating at product and process level in production system. These agents are able to define the right coupling, to evaluate task assignments and to adjust product and process parameters, thus to perform automatic reconfiguration of the system. They integrate quantitative and cognitive data processing, associated with learning capabilities. Improvement works are still in progress to integrate such upgrades and enhancements in the next generation of production systems. Different schemes of implementation are proposed: VFDCS simulator within the PABADIS EC-funded Project. RÉSUMÉ. Le papier se concentre sur le développement de nouvelles approches basées sur les interactions entre des agents intelligents au niveau du produit et du processus dans un système de production. Ces agents peuvent définir le bon couplage entre eux en évaluant de tâches et en ajustant les paramètres, dans le but d'avoir une reconfiguration automatique du système. Ils intègrent et traitent des informations quantitative et cognitive, avec des capacités d'apprentissage. Des travaux en cours visent à intégrer de telles approches et perfectionnements dans des systèmes de production. On propose différentes structures de mise en place : le simulateur VFDCS et le projet européen PABADIS IST-60016.
A General Agent-Based Architecture for Production Planning in Electronic Commerce Scenarios
ESM2000-European Simulation …, 2000
The creation of a general architecture for the use of agents in production planning is addressed. The modularity and flexibility provided by an agent-oriented system proves itself useful in dynamic scenarios. The anthropomorphic features of the agents make them suitable for Electronic Commerce systems. Agents enable the interconnection of already existent web-based systems with the production lines of a company, potentiating higher degrees of client satisfaction.
Developing intelligent manufacturing systems using collaborative agents
1999
Agent technology has been considered as an important approach for developing distributed intelligent manufacturing systems. This paper presents some preliminary results of our two ongoing research projects related to the development of a new collaborative agent system architecture for intelligent manufacturing systems. The main features of the proposed architecture are described; some domain independent mechanisms and components are briefly introduced; and a case study is presented.
Production planning systems with AI philosophy
Expert Systems with Applications, 1995
In this article we present our experience with the development of several systems for computer-aided production planning. The real life production planning tasks can be decomposed into two steps. The latter is the scheduling task, including resource allocation, which must conform to rules, created in the former step. They describe technological conditions that are specific for the manufacturing domain and the factory organization. Thus, the production plan may be viewed as a set of rules that may be considered as constraints for the scheduling task. We focus our analysis on the problem of how to specify these rules. We also show how these plans as manufacturing instruction sequences are structured for diverse production goals. A brief survey of the systems the authors have developed is given as well.