Davy Monticolo

A collaborative Design for Usability approach supported by Virtual Reality and a Multi-Agent System embedded in a PLM environment

This paper details a collaborative workstation design approach integrating knowledge based on engineering process, using a Multi-Agent System (MAS) on a Virtual Reality (VR) platform. The MAS supports R&D teams to extract and re-use engineering knowledge so as to improve their efficiency in developing new products. Our research targets the development of a knowledge engineering system integrated into a PLM-Product Life cycle Management-environment linked with virtual reality tools. A PLM is a strategic business approach with a consistent set of methodologies and software solutions. It is meant to promote collaborative creation, management, delivery and proper use of this life cycle definition and information product in multinational companies. This system is used by engineers to carry out projects in a collective way while conveying a defined process. The MAS allows capitalization, and to annotate knowledge according to the actions of the designers inside a PLM environment. Then, this knowledge is used by VR tools to analyze various aspects of the virtual prototype such as manufacturing, maintenance, reliability or ergonomics. Consequently, we use expert knowledge to pilot the design process of a virtual prototype inside a three-dimensional immersive virtual reality platform. In this context, our paper describes our knowledge management approach applied to improve ergonomics and collaborative design in industrial areas.

A meta-model for knowledge configuration management to support collaborative engineering

This paper describes a model called KCModel to specify knowledge configuration used in engineering project.A method called KCModel method is used to manage knowledge configurations according to the KCModel.Some examples are given to highlight the problem of conflicts management between different knowledge configurations.A description of a tool, which was developed to support the KCModel is given.A industrial use case of knowledge configuration management illustrated the KCModel method. This paper focuses on industrial design and simulation processes especially in automotive and aerospace areas. Designers use business models (called expert models) such as CAD (computed aided design) and CAE (computed aided engineering) models to optimize and streamline the engineering process. Each expert model contains information such as parameters, expert rules, mathematic relations (parametric models, for example) which are shared by several users and in several different domains (mechanical, thermal, acoustic, fluid, etc.). This information is exploited at the same time in a concurrent engineering context. It is the basis of an imperfect collaboration process due to the fact that existing tools do not manage encapsulated information well and are unable to ensure that parameters and rules are consistent (same value of parameters for example) throughout different heterogeneous expert models. In this context, we propose an approach to manage knowledge using configurations synchronized with expert models which enable designers to use parameters consistently in a collaborative context. Our approach is called KCModel (knowledge configuration model): it allows acquisition, traceability, re-use and consistency of explicit knowledge used in configuration.

An agent-based system to build project memories during engineering projects

Engineering projects are organizations where several actors with different professional fields and know-how work together to carry out the same aim: to develop a new product. Inside these organizations, heterogeneous and distributed information has to be managed in order to create project memories that will be useful in future projects. In this paper we describe a Multi-Agent System (MAS), which is based on the social and cooperative approach to support the knowledge management process all along mechanical design projects. Indeed, this multi-agent system, called KATRAS, aims to capitalize and reuse knowledge according to the roles involved in the design projects. We will present in this paper how the agents capitalize six different types of knowledge (professional vocabulary, process, expertise, project evolution, and return of experience) and how they help the professional actors to reuse knowledge.

An e-Groupware based on Multi Agents Systems for Knowledge Management

This article presents a knowledge management experiment in a company of four hundred employees. Our researches concerns the development of a MAS associated to e-Groupware in order to build project memories. In SMEs, the development of a product requires a multidisciplinary team where professional actors work together to achieve the same goal. In this collaborative world we observe many exchanges (engineering data, report...) and interactions (meetings, decisions...). Each of these types of communication is at the origin of the emergent knowledge. Consequently we propose an approach based upon the modelling of activities with an organizational meta-model and the use of MAS to trace knowledge and automatically build project memories.

OCEAN: A Semantic Web Service to Extract Knowledge in E-Groupwares

Some research programs are focused on the use of web services and semantic web approach to design tools for knowledge management. These tools help to share information among business applications. We will prove in this paper the benefit to combine semantic and web services approaches to identify and annotate knowledge in a heterogeneous and distributed information landscape. We present here, a comprehensive explanation of our approach which integrates an intelligent reuse module of knowledge that allows engineers to capitalize their know-how. This knowledge will be extracted by web services that enable communication between several business applications. Then in the second section, we describe different ontologies which are created by users depending on their needs to define knowledge. These are extracted from business applications thanks to semantic web service. At the end, this knowledge will be annotated and saved in a RDF file.

An organizational approach to designing an intelligent knowledge-based system

Knowledge-based engineering (KBE) approaches are designed to reduce the time and cost of product development by capturing, retaining and re-using design knowledge. They currently focus on repetitive design tasks where knowledge is considered as a static resource. However, knowledge is intrinsically linked to the organizations and people who use it. Thus, to be efficient, these knowledge-based systems (KBS) have to be able to take into account all the mechanisms of knowledge creation, sharing and evaluation made by the users. Using the agent paradigm, new knowledge-based systems can be designed in order to address this research issue. Indeed, the agents have social abilities and are able to achieve very complex tasks. These two features are necessary for making a knowledge-based system efficient. However, there still exists today a lack of approaches and methodologies to help design such applications. This paper presents DOCK, a methodology to design an intelligent knowledge-based system that aims to support the knowledge management process. In order to take into account all the mechanisms of knowledge generation, sharing and re-use, DOCK is based on the hypothesis that efficient modelling of human organizations, by highlighting their roles, collaborations, skills, goals and knowledge, will help the KBS designer to specify an adapted knowledge-based system. Finally, DOCK is implemented to design the SMA SNOTRA that is dedicated to supporting a decision-making process for design projects.

Content management based on multi-agent system for collaborative design

Collaborative design methods are increasingly integrated into industrial systems in order to reduce costs and lead time, but also to improve product quality and value. Design tasks involve many actors throughout the product lifecycle, which starts with product requirements, functional specification, product modelling, manufacturing and ends with its recycling. Software supporting collaborative design, such as Product Lifecycle Management (PLM) systems, is needed to help design team members in their project tasks. The Atelier Cooperatif de Suivi de Projet in French (ACSP) platform is a web-based PLM system. It supports the design team members in carrying out collaborative activities in product-process-design projects. An improvement of the ACSP platform has been proposed by introducing multi-agent systems at several levels of the ACSP architecture. This improvement is based on the Role, Interaction and Organisation methodology and on many FIPA specifications. By implementation of multi-agent systems for content and knowledge management in collaborative engineering, one can develop autonomy, reactivity, pro-activity and social ability in the man–machine relationships.

A Semantic Wiki to Share and Reuse Knowledge into Extended Enterprise

This paper aims to present an approach in order to share knowledge between the business actors of the extended enterprise. This approach is based on a semantic wiki that access the organizational memory of our knowledge management system OCEAN. This principle allows us, firstly to share knowledge in order to facilitate the individual work, and secondly to reuse capitalized knowledge automatically.

A Metamodeling and Transformation Approach for Knowledge Extraction

Among the goals of Knowledge Management (KM) we can cite the identification and capitalization of the know-how of companies in order to organize and disseminate them. KM is recognized as a non-trivial task. In the context of extended enterprises it is even more difficult because they are geographically distributed and use heterogeneous information systems. Indeed, informations from which knowledge is derived from are stored in different databases, distributed in different sites across the entire network of the extended enterprise. This paper proposes a semi-automatic approach for knowledge extraction from several databases. This knowledge will be stored in an organizational memory (OM). The approach is based upon the definition of ontologies for knowledge exchange and Model Driven Engineering concepts such as meta-models and transformation to process requests.

A multi-sources knowledge management system

Abstract Nowadays the development of a product involves different types of actors (employees, managers, board of directors) which must be able to share knowledge, experiences and work together efficiently. Each actor has a professional specialty and use one or several software tools (CAO, project management, PLM tools …) dedicated to his specific skills. Each of these software tools produces different information sources (databases, XML files, text files) which are distributed through the enterprise network. We present in this paper a Knowledge Management System (KMS) which allows the capitalization of the distributed and heterogeneous knowledge all along the development of mechanical product projects on the basis of the heterogeneous and distributed information sources.