Xavier Desforges

Multi-agent framework based on smart sensors/actuators for machine tools control and monitoring

Abstract Throughout the history, the evolutions of the requirements for manufacturing equipments have depended on the changes in the customers’ demands. Among the present trends in the requirements for new manufacturing equipments, there are more flexible and more reactive machines. In order to satisfy those requirements, this paper proposes a control and monitoring framework for machine tools based on smart sensor, on smart actuator and on agent concepts. The proposed control and monitoring framework achieves machine monitoring, process monitoring and adapting functions that are not usually provided by machine tool control systems. The proposed control and monitoring framework has been evaluated by the means of a simulated operative part of a machine tool. The communication between the agents is achieved thanks to an Ethernet network and CORBA protocol. The experiments (with and without cooperation between agents for accommodating) give encouraging results for implementing the proposed control framework to operational machines. Also, the cooperation between the agents of control and monitoring framework contributes to the improvement of reactivity by adapting cutting parameters to the machine and process states and to increase productivity.

Distributed machining control and monitoring using smart sensors/actuators

The study of smart sensors and actuators led, during the past few years, to the development of facilities which improve traditional sensors and actuators in a necessary way to automate production systems. In another context, many studies have been carried out aimed at defining a decisional structure for production activity control and the increasing need of reactivity leads to the autonomization of decisional levels close to the operational system. We study in this paper the natural convergence between these two approaches and we propose an integration architecture, dealing with machine tool and machining control, that enables the exploitation of distributed smart sensors and actuators in the decisional system.

A Neural Network for Parameter Estimation of a DC Motor for Feed-Drives

The monitoring of machine-tools implicated in the metal cutting process is the subject of increasing developments because of demands on control, reliability, availability of machine-tools and on the work-piece quality. The use of computers contributes to a better machine and process monitoring by enabling the implementation of complex algorithms for control, monitoring,...

Service-Oriented Computing for intelligent train maintenance

ABSTRACT The purpose of this work is to apply the servicization of enterprise information systems in maintenance, particularly in the management of the maintenance process of the component parts of trains. Service Oriented Architecture (SOA) is an architectural approach that permits servicization since it provides a flexible set of design principles used during the modeling practices (abstraction and realization). With a view to supporting the model-driven engineering of software systems, Mode Driven Architecture (MDA) is a design approach delivering a set of guidelines for the configuring of specifications in systems development. Therefore, the combination of these two approaches can be fruitful to address the challenging issues the enterprise information system is facing today. Our study is based on a methodological approach using the MDA models for the automatic generation of web service. The case study concerns a Railways Maintenance Workshop (RMW) at Sidi Bel Abbes (Algeria). Finally, the information system for the management of maintenance of the component parts of passengers and baggage railcars, using the generated solution, is realized and deployed. This software helps to have better management of the RMW by the effective planning of interventions, improve performance by increasing reliability, traceability, and availability of the equipment (parts).

Distributed embedded health assessment of networked instruments

Abstract This article presents an applicative architecture based on a solving method for embedded technical health assessment of complex systems. This architecture is defined in order to provide services enabling the evaluation of the health status of complex systems. Diagnostic and prognostic services provide information to the maintenance decision support system that leads to reduce the periods of unavailability and determine if future missions of complex systems can be carried out. The architecture presented in this paper implements distributed diagnostic and prognostic functions using multi-***agent techniques. An example shows the effectiveness of the applicative architecture.

EXPERIENCE FEEDBACK, FROM CASES TO KNOWLEDGE

Abstract “Capitalizing on” and “making uses” of all crucial information, referred as knowledge, is nowadays one of the most important organizations” concern so as to remain competitive in the current economical context. In this paper, we present experience feedback as an alternative solution to usual knowledge management systems. By the end of the paper, the main characteristics of the experience feedback process and architecture will be presented and then an example of knowledge extraction concerning a risk indicator will be introduced.

Contribution to Multiagent Machine-Tool Control: Intelligent Sensors for Feeddrive Monitoring

This survey aims at proposing a contribution to the multiagent control of machine tools in order to improve their availability and the quality of the machined parts. This contribution consists in an agent that realises the monitoring of a machine tool feeddrive. This agent is designed according to the intelligent sensor concept. So, the paper firstly discusses the interests of multiagent systems and presents the intelligent sensor concept. A multiagent system organisation dedicated to NC machines is then proposed. After having presented the interests of feeddrives monitoring, it presents the treatments enabling this monitoring. This is followed by experimental results.

Distributed Smart Sensors and Actuators for Machining Control and Monitoring

Abstract The study of Smart Sensors/Actuators led, during the past few years, to the development of facilities which improve traditional Sensors/Actuators in a necessary way to automate production systems. In an other context, many studies were carried out aiming at defining a decisional structure for production activity control and the required reactivity led to the autonomisation of decisional levels close to the operational system. We suggest in this paper to study the natural convergence between these two approaches and we propose an integration architecture enabling the exploitation of Distributed Smart Sensors/Actuators in the decisional system dealing with machine tool monitoring and machining.