Search

In job-shop manufacturing systems, an efficient production schedule acts to reduce unnecessary costs and better manage resources. For the same purposes, modern manufacturing cells, in compliance with industry 4.0 concepts, use material handling systems in order to allow more control on the transport tasks. In this paper, a job-shop scheduling problem in vehicle based manufacturing facility that is mainly related to job assignment to resources is addressed. The considered job-shop production cell has two types of resources: processing resources that accomplish fabrication tasks for specific products, and transporting resources that assure parts’ transport to the processing area. A Variable Neighborhood Search algorithm is used to schedule product manufacturing and handling tasks in the aim to minimize the maximum completion time of a job set and an improved lower bound with new calculation method is presented. Experimental tests are conducted to evaluate the efficiency of the proposed approach.

International audience; Liquid petroleum gas (LPG) is one area where catastrophic release scenarios have occurred. For this reason, preventive, and protective barriers have to be installed in order to reduce the occurrence and the severity of these scenarios. This article addresses an analysis of deluge system barrier and proposes a making decision process to ensure a high level of reliability, availability, maintainability, and safety (RAMS) using a robust Reliability Analysis with conditional probabilities. To achieve this RAMS target, a methodology for converting fault tree analysis (FTA) in continuous time using Monte Carlo (MC) simulation to Bayesian belief network (BBN) is developed. The probabilistic importance factors (PIFs) for critical components ranking and decision making are also mapped using BBN inferences in Water Deluge Systems (WDS) with an optimization aim using redundancy or maintenance tasks. This analysis illustrates the helpfulness of mapping PIFs into BBN for making a decision in any critical technological infrastructures.

Solar energy offers a considerable potential for the energy market and it brings many challenges for the actual research. In order to meet the economic and the environmental expectation, the management of an isolated microgrid needs to be more efficient and profitable. In this paper a Multi-Agent System (MAS) is proposed in order to manage an isolated photovoltaic microgrid. The proposed approach presented in this paper improves the management of an isolated decentralized microgrid. It takes in account load voltage constraints, ensures the power demand, reduces chattering phenomenon on the storage system, and it maintains the photovoltaic panel operating in its maximum efficiency point. Finally, the proposed method is evaluated throw three scenarios, and the results are obtained by simulation using MATLAB/Simulink and JADE (Java Agent Development Environment).

International audience; This paper studies the problem of scheduling in a flexible job shop. A greedy heuristic is developed to solve precisely the sequencing (allocation) problem. The principle of this approach is to iteratively insert operations on the machines until the objective of minimizing the Cmax (makespan) is reached. The heuristic was tested on a particular Benchmark which considers the transportation times between the machines, and get inspiration from a real assembly cell: the AIP-PRIMECA cell at the University of Valenciennes, that from an OR perspective, can be viewed as Flexible Job Shop, leading to the formulation of a Flexible Job-Shop Scheduling Problem (FJSSP). The results obtained by the greedy heuristic on this benchmark are very promising.

In recent years, most companies have resorted to multi-site or supply-chain organization in order to improve their competitiveness and adapt to existing real conditions. In this article, a model for adaptive scheduling in multi-site companies is proposed. To do this, a multi-agent approach is adopted in which intelligent agents have reactive learning capabilities based on reinforcement learning. This reactive learning technique allows the agents to make accurate short-term decisions and to adapt these decisions to environmental fluctuations. The proposed model is implemented on a 3-tier architecture that ensures the security of the data exchanged between the various company sites. The proposed approach is compared to a genetic algorithm and a mixed integer linear program algorithm to prove its feasibility and especially, its reactivity. Experimentations on a real case study demonstrate the applicability and the effectiveness of the model in terms of both optimality and reactivity.

Petroleum industry production systems are highly automatized. Maintenance of such systems is vital, not only to maintain production efficiency but also to insure minimal safety levels. Maintenance task scheduling is difficult since some tasks are already identified because they must be done repeatedly, and other tasks need to be identified dynamically. In this paper, we present a multi-agent approach for the dynamic maintenance task scheduling for a petroleum industry production system. Agents simultaneously insure effective maintenance scheduling and the continuous improvement of the solution quality by means of reinforcement learning, using the SARSA algorithm. Reinforcement learning allows the agents to adapt, learning the best behaviors for their various roles without reducing the performance or reactivity. To demonstrate the innovation of our approach, we include a computer simulation of our model and the results of experimentation applying our model to an Algerian petroleum refinery.

In recent years, most companies have resorted to multi-site organization in an effort to improve their competitiveness and to adapt to current conditions. In this article, we propose a model for adaptive scheduling in multi-site companies. We adopt a multi-agent approach in which intelligent agents have reactive learning ability. This allows them to make accurate short-term decisions. Our model is implemented on a 3-tier architecture that ensures the security of the data exchanged between the various company sites. Experimentations on a real case study demonstrate the applicability and the effectiveness of our model concerning both optimality and reactivity.

International audience; In this paper we focus on the Job Shop Scheduling Problem (JSSP) using Priority Dispatching Rules. Simulation model for makespan optimization is proposed using different Dispatching Rules (DR) for each machine in the shop floor. Collected results are used for learning base construction. This database will be used to develop an inference model able to select the best DR for every new scheduling problem. This preliminary study shows advantages of using different DR and also saving progress JSSP data

The needs of flexibility, agility and adaptation capabilities for modern manufacturing systems increase constantly. In this paper, we propose an original approach combining active/intelligent product architecture with learning mechanism to assure flexibility and agility to the overall manufacturing system. Using learning approaches as Reinforcement Learning (RL) mechanism, an active product can be able to reuse learned experiences to enhance its decisional performances. A contextualization method is proposed to improve the decision making of the product for scheduling tasks. The approach is then applied to a case study using a multi-agent simulation platform.

Safety becomes a key paradigm in industrial systems because of international regulation and the cost generated by a work stoppage or to overcome disaster. The work presented in the present paper describes a distributed modelling of a safety system for technological processes, and its application to permanent magnet DC-motor. Motors are basic engines in several technological systems and especially in industry their availability and security affect the entire system. For this purpose a special attention is paid to their supervision and security. The safety model is based on agents. These agents monitor system parameters, identify risk, trigger corresponding alarms and react to protect the system. Experiments have shown that the right alarms are triggered and the system reacts in near-real time to protect the equipment.

The increasing complexity and size of electronic systems in industry, combined with growing market demand, requires industries to implement an efficient safety system to preserve equipment viability, environment protection and especially human life protection. The aim of this paper is to present a dynamic safety system based on a multi-agent paradigm using case-based reasoning to identify and react to risks. To develop the base of cases, an exhaustive risk analysis was carried out, giving rise to risk ontology and their precursors. Then, a model for identifying the similarities between precursors was developed. Case-based reasoning is very reactive, and with the presented model of similarity, the developed security system was very reactive against the risks that the system was experiencing during the experiments.

International audience; In real-world scheduling problems, several kinds of hard-to-predict risk must be considered. Scheduling under uncertainty allows these kinds of risks to be taken into account. This paper provides an overview of the state of the art in scheduling under uncertainty, including a survey on modeling techniques of uncertainty and a survey of the existing positioning typologies and contributions. A new classification scheme for the different approaches to scheduling under uncertainty is proposed and discussed. Several areas for future research are suggested.

International audience; In reactive manufacturing control, the allocation of resources for tasks is achieved in real time. When a resource becomes available it chooses one of the tasks in its queue. This choice is made according to priority rules which are designed to optimize costs, time, etc. In this paper, the aim is to exploit a Job Shop scheduling log and simulations in order to extract knowledge enabling one to create rules for the selection of priority rules. These rules are implemented in a CASI cellular automaton. Firstly, symbolic modelling of the scheduling process is exploited to generate a decision tree from the log and simulations. Secondly, decision rules are extracted to select priority rules for execution in a specific situation. Finally, the rules are integrated in CASI which implements the decisional module of agents in a distributed manufacturing control system.

This chapter’s main interest is the myopic behaviour inherent to holonic control architectures. Myopic behaviour is the lack of coherence among local decision-making and system’s global goals. So far, holonic architectures use mediator entities to overcome this issue, bringing the holonic paradigms more toward hierarchy than heterarchy. Instead, this chapter explores the recursiveness characteristic of holonic manufacturing systems (HMS) as a possible way to correct myopic behaviour, by distributing decision-making over adjunct entities. The chapter explains our approach and its agent-based implementation for solving the allocation problem in a flexible job-shop. Results from simulations are compared with a mixed-integer linear program to determine its efficiency in terms of makespan and execution time. Preliminary results encourage further research in this area.

This paper presents a model that aims at diminishing the impact of temporal myopia in Heterarchical Control Architectures (HeCA) of Flexible Manufacturing System (FMS). This model is based on a “switching architecture”, based upon the concept of intelligent reactive products. A virtual layer hosts Product Agents having the objective of preserving global performance, while a physical layer congregates physical products trying to follow the prescribed behavior, unless they sense a change of conditions. The idea is to empower autonomy while achieving an overall good global performance. For experimental purposes, this approach has been deployed at the AIP-PRIMECA center at University of Valenciennes, France and some results are presented.

Petroleum industry production systems are highly automatized. Maintenance of such systems is vital, not only to maintain production efficiency but also to insure minimal safety levels. Maintenance task scheduling is difficult since some tasks are already identified because they must be done repeatedly, and other tasks need to be identified dynamically. In this thesis, we present a multi-agent approach for the dynamic maintenance task scheduling for a petroleum industry production system. Agents simultaneously insure effective maintenance scheduling and continuous improvement of the solution quality by means of reinforcement learning, in particular the SARSA algorithm. Reinforcement learning allows the agents to adapt, learning the best behaviors for their various roles without reducing the performance or reactivity. To demonstrate our approach's contribution, an computer implementation of our model and the results of experimentation applied to the case of an Algerian petroleum refinery are presented.; Les marchés actuels sont caractérisés par une grande compétitivité. Cette compétitivité a mis les entreprises, notamment celles d'envergure internationale, dans une situation de recherche de compromis entre des objectifs et des contraintes de plus en plus forts et contradictoires. Cet environnement nous a conduit à développer un système de pilotage et de contrôle de production qui ne soit pas seulement capable de réagir efficacement mais qui soit également en évolution permanente pour améliorer ses performances et la qualité des solutions qu'il propose en terme d'ordonnancement. Ce système doit pouvoir exploiter au mieux les ressources de production. Pour ce faire, ces ressources subissent régulièrement des entretiens préventifs ou des corrections suite aux pannes, ce qui les rend indisponibles à ces moments. Les systèmes de pilotage de production doivent prendre en considération ces indisponibilités afin de mieux contrôler et commander le système de production. Par conséquent, production et maintenance doivent être gérées conjointement au sein du système de pilotage. Dans ce cadre, l'objectif de cette thèse est de proposer un système de pilotage qui soit réactif et capable d'améliorer en permanence ses performances. Dans cet objectif, un système basé sur l'approche multi-agent et l'apprentissage par renforcement multi-objectifs a été développé, ces techniques permettent au système d'être réactif et adaptatif à son environnement. Le système développé a été testé sur un cas réel qui est une unité de fabrication des huiles finies. Les expérimentations ont donné des résultats satisfaisants ouvrant la porte à de nouvelles perspectives.

Heterarchic manufacturing control system offer a significant potential in terms of capacity, adaptation, self-organisation and real time control for dynamic manufacturing system. In this paper, we present our steps to work out a manufacturing control system where the decisions taken by the system are the result of an agents group work, these agents ensure a continuous improvement of these performance, thanks to the reinforcement learning technique which was introduced to them. This technique of learning makes it possible for the agents to learn the best behaviour in their various roles (answer the requests (risks), self-organisation, plan, etc.) without attenuating the system real time quality. We also introduce a new type of agents called 'observant agent', which has the responsibility to supervise the evolution of the system's total performance. A computer implementation and experimentation of this model are provided in this paper to demonstrate the contribution of our approach.