Flux RSS

ORKID

Les travaux de cet axe visent à élaborer des outils d’aide à la décision à base de connaissances, pour aider les acteurs en charge de projets de développement de nouveaux produits/systèmes/services dans leur prise de décisions. Les connaissances manipulées, ainsi que les risques évalués, concernent autant le produit/système/service à développer, que le projet de développement, ou encore son processus d'obtention.

Responsable d'axe : Élise Vareilles

Contexte

Les travaux de cet axe visent à spécifier, élaborer et mettre en œuvre des outils d’aide à la décision, basés sur l'utilisation de connaissances, pour répondre aux besoins des décideurs en charge de projets de développement de nouveaux produits. Les connaissances manipulées, ainsi que les risques évalués, concernent autant le produit à développer, le projet de recherche et développement, que les processus d'obtention. Les travaux ont pour objectifs :

  • d’une part d'aider les activités de management de projets, de portefeuille de projets et de processus de conception ou de développement de nouveaux produits, de nouveaux systèmes et de nouveaux processus. Les outils employés sont principalement issus de la gestion de projet.
  • et d’autre part, d'aider les activités entrant dans les projets et processus de conception ou de développement de produits, de systèmes, de services et de processus. Les outils employés sont le plus souvent issus de l’intelligence artificielle et exploitent de la connaissance capitalisée. Ces travaux entrent dans le courant du KBE pour « Knowledge Based Engineering ».

La spécificité et l’originalité de ces travaux sont liées aux contextes ou situations dans lesquelles ils sont conduits. Ces situations se caractérisent par :

  • la prise en compte de risque projet ou processus plus ou moins fort,
  • la disponibilité de connaissance ou d’expertise typant la conception de routinière à créative,
  • une incertitude modulée par l’horizon de conception ou par le stade d’avancement du projet,
  • la présence d’acteurs variés et plus ou moins nombreux.

Aide à la conduite de projets par l'évaluation des risques

Les travaux relatifs à l’aide à la conduite de projets s’intéressent aux projets et processus de développement de produits/systèmes/services innovants caractérisés par de fortes incertitudes/risques. Dans ce contexte, piloter un projet nécessite d’identifier et d’évaluer et les risques puis de proposer les stratégies de traitement pertinentes pour assurer du succès du projet. Les incertitudes/risques portent, entre autres, sur les activités de réalisation et de pilotage du projet, sur la faisabilité des sous ensembles techniques, sur la disponibilité des ressources et sur l'organisation mise en place pour assurer le développement.

Il est ainsi difficile pour les décideurs (responsable projet, responsable portefeuille, dirigeant), d’évaluer avec précision les répercussions des décisions et les scénarios de projet possibles qui en découleraient. Il en résulte ainsi un besoin en modèles/méthodes/outils pour modéliser et évaluer ces différents scénarios. Nos contributions visent à aider l’évaluation et le pilotage des projets (sélection des projets, hiérarchisation des projets/variantes).

L'approche retenue vise à proposer des modèles d'aide à la décision basés sur la prise en compte et la modélisation des connaissances relatives aux incertitudes/risques. Ces modèles sont capables :

  • de générer l’ensemble des scénarios de projets possibles intégrant les combinaisons de survenue possible des risques et leurs conséquences sur le déroulé du projet,
  • de caractériser chacun des scénarios avec des indicateurs ad hoc,
  • d'évaluer les conséquences des incertitudes/risques sur les activités métier ainsi que de management,
  • d'aider à choisir les stratégies d'action à préconiser dans un contexte d'information incomplète.

Aide à la décision à base de connaissance en ingénierie

Nos travaux de recherche trouvent leurs fondements dans les constats suivants :

  • la durée de vie des produits, systèmes, services et processus tend à se réduire,
  • les conceptions et les actualisations des produits mis sur le marché sont de plus en plus fréquentes entraînant des cycles de conception sont toujours plus brefs,
  • les technologies employées en constante évolution nécessitent une acquisition de connaissance permanente,
  • la diversité des produits offerte sur les marchés ne cesse de croître allant des produits personnalisables ou configurables jusqu’aux produits sur-mesure ou conçus à la commande.

Ces tendances et la masse d’informations et de connaissances à traiter en découlant exigent des concepteurs toujours plus d’attention et un travail cognitif toujours plus intense. Il en résulte une augmentation des risques, que le produit réponde imparfaitement aux besoins du demandeur, qu’il soit difficilement réalisable ou fabricable, ou encore qu’il le soit à un coût prohibitif. L’objectif de nos travaux est donc de limiter ces risques et erreurs en proposant des outils logiciels et des environnements méthodologiques destinés à capitaliser et exploiter des connaissances générales, contextuelles, académiques, expertes ou métier pour aider la conception.

Les travaux effectués sur différentes problématiques industrielles nous conduisent à prendre en considération deux natures de connaissances relevant du « domaine produit » et de la « diversité produit » conduisant à des problématiques industrielles différentes :

  • la première nature de connaissance recouvre aussi bien des aspects scientifiques et techniques que des règles métier, elle est nécessaire pour la définition du produit et débouche sur des problématiques d’aide à la conception de produit/système/service,
  • la seconde nature est une connaissance liée à la diversité des produits, qui débouche sur les problématiques d’aide à la personnalisation ou configuration de produit/système/service.

Nous visons à aider un type de conception plutôt « routinier » où de la connaissance de différentes natures et de divers types existe du fait de la récurrence de l’activité. Nous considérons que l’aide à la conception ou configuration peut se formaliser, complètement ou partiellement, comme un problème de satisfaction de contraintes (CSP). Dans ce cadre, nous nous intéressons plus spécifiquement à l’aide à la décision interactive exploitant les principes de filtrage ou de propagation de contraintes. La diversité des connaissances formalisées sous forme de CSP et l’interaction avec l’utilisateur nous conduisent à assembler et adapter des algorithmes de filtrage dans un moteur générique de propagation de contraintes, intégré à notre solution logicielle CoFiADe.

En complément, nous associons à ce formalisme à base de contraintes CSP :

  • des ontologies pour structurer les connaissances et faciliter leur réutilisation sur l'ensemble du cycle de développement,
  • des approches par analogie exploitant de la connaissance contextuelle encapsulée dans des cas afin de proposer à l’utilisateur des recommandations quant aux choix de valeurs,
  • des approches évolutionnaires pour optimiser la recherche des solutions de manière multicritère.

Publications significatives

  • Building renovation adopts mass customization: Configuring insulating envelopes

    Références :
    Andrés Felipe Barco Santa, Élise Vareilles, Paul Gaborit et Michel Aldanondo. « Building renovation adopts mass customization: Configuring insulating envelopes ». In : Journal of Intelligent Information Systems 49.1 (août 2017). P. 119--146. ISSN : 0925-9902, 1573-7675. DOI : 10.1007/s10844-016-0431-6.
    This work is motivated by an industrial need of manufacturing façades insulating envelopes in order to reduce energy consumption in residential buildings. An insulating envelope is a configuration of a set of rectangular panels that respects a set of limitations. Due to the number of façades to be renovated and the number of possible configurations for a single façade, the envelope configuration is both a mass customization problem as well as a combinatorial one. The paper then introduces a decision support system based on the framework of constraint satisfaction, as it fits neatly the constrained nature of the problem. Two configuration tasks have been identified as prerequisite to envelopes configurations: (1) the configuration of a questionnaire for information inputs and (2) the configuration of a constraint satisfaction problem for each one of the façades to be renovated. The system architecture promotes maintenance, modularity and efficiency as different configuration tasks are divided into web-services. Conception and implementation of the massive building thermal renovation are then supported.
  • A method to select a successful interoperability solution through a simulation approach

    Références :
    François Galasso, Yves Ducq, Matthieu Lauras, Didier Gourc et Mamadou Camara. « A method to select a successful interoperability solution through a simulation approach ». In : Journal of Intelligent Manufacturing 27.1 (févr. 2016). P. 217--229. ISSN : 0956-5515, 1572-8145. DOI : 10.1007/s10845-014-0889-4.
    Enterprise applications and software systems need to be interoperable in order to achieve seamless business across organizational boundaries and thus realize virtual networked organizations. Our proposition can be considered as an interoperability project selection approach and is based on three steps: (1) Modelling both collaborative business processes and potential related interoperability projects; (2) Evaluating the accessibility of each project regarding the current state of the organization; (3) Simulating each project and assessing the associated performance. These results are finally projected on a comparison matrix used as a decision support to select the most appropriate interoperability solution. An application case extracted from the French aerospace sector demonstrates the applicability and the benefits of the proposition.
    Keywords: Collaborative network, Control, Robotics, Mechatronics, Decision support system, Interoperability, Manufacturing, Machines, Tools, Performance measurement system, Production/Logistics/Supply Chain, Simulation
  • System design and project planning: Model and rules to manage their interactions

    Références :
    Élise Vareilles, Thierry Coudert, Michel Aldanondo, Laurent Geneste et Joël Abeille. « System design and project planning: Model and rules to manage their interactions ». In : Integrated Computer-Aided Engineering 22.4 (27 août 2015). P. 327--342. ISSN : 1069-2509. DOI : 10.3233/ICA-150494.
    This article proposes a model and rules dealing with the management of the interaction between system design processes and project planning ones. An industrial benchmark analysis has reinforced our belief that the interaction between the two processes has to be supported by models, processes and relevant tools. Firstly, after presenting the results of the analysis, the different entities are defined and the one-to-one relationship or bijection between the structure of the system and the structure of the project is made. Then, a model, taking into account design activities and planning activities as well as management of interactions, is proposed in compliance with existing project and design standards. A process of interaction is presented to carry out design and project management. Two interaction modes have been proposed. On the one hand, the structural interaction establishes links between entities of the two domains. On the other hand, the behavioral interaction (subject of this paper) is based on the definition of states for each entity following feasibility and verification criteria, and can thus manage the changes between states. Some rules are defined (precedence and synchronous rules) to forbid certain changes when they are inconsistent and to synchronize them.
    Keywords: aiding decisions, knowledge based systems, Project planning, System design
  • Strategic decision-making in NPD projects according to risk: Application to satellites design projects

    Références :
    François Marmier, Ioana Filipas Deniaud et Didier Gourc. « Strategic decision-making in NPD projects according to risk: Application to satellites design projects ». In : Computers in Industry 65.8 (oct. 2014). P. 1107--1114. DOI : 10.1016/j.compind.2014.06.001.
    In this paper we present a method for making strategic decisions in New Product Development (NPD) projects based on risks. In NPD the complexity of the process depends both on the nature of the design problem and the difficulties associated with managing the project (activities, risks). To design a complex product several different teams, having different competencies, work on the project. Not one among them controls the entire process. The interactions between product subsystems in NPD often lead to technological arbitration between alternative solutions. In selecting one solution over another, the risk management concerns and the overall project plan are affected. Therefore, the objective is to give the project Manager the means to evaluate the effects of strategic decisions, including those that influence the selection of technological solutions for the project plan as well as those for risk treatment strategies. We propose an integrated process that comprises design, project management and risk management. It takes into consideration the design activities and risk activities to generate a design project planning where design activities and risk activities are folded into the overall design project plan. During the process of project design two different types of strategies are required: one relates to the problem design, the other to the assessment of project risks. Each strategy leads to different possible scenarios. We present a decision tree that shows the decision steps and possible project scenarios. A generic decision support system is proposed. We demonstrate its applicability by applying it to a satellite design project. (C) 2014 Elsevier B.V. All rights reserved.
    Keywords: Complex product, Design project, Project planning, Risk management, Systems engineering
  • Concurrent product configuration and process planning: Some optimization experimental results

    Références :
    Paul Pitiot, Michel Aldanondo et Élise Vareilles. « Concurrent product configuration and process planning: Some optimization experimental results ». In : Computers in Industry 65.4 (mai 2014). P. 610--621. ISSN : 0166-3615. DOI : 10.1016/j.compind.2014.01.012.
    In nowadays industrial competition, optimizing concurrently the configured product and the planning of its production process becomes a key issue in order to achieve mass customization development. However, if many studies have addressed these two problems separately, very few have considered them concurrently. We therefore consider in this article a multi-criteria optimization problem that follows an interactive configuration and planning process. The configuration and planning problems are considered as constraint satisfaction problems (CSPs). After some recalls about this two-step approach, we propose to evaluate a recent evolutionary optimization algorithm called CFB-EA (for constraint filtering based evolutionary algorithm). CFB-EA, specially designed to handle constrained problems, is compared with an exact branch and bound approach on small problem instances and with another evolutionary approach carefully selected for larger instances. Various experiments, with solutions spaces up to 1017, permit us to conclude that CFB-EA sounds very promising for the concurrent optimization of a configured product and its production process. (C) 2014 Elsevier B.V. All rights reserved.
    Keywords: algorithms, Constrained optimization, constraint filtering, Design, differential evolution, evolutionary algorithm, process planning, product configuration, satisfaction
  • Plas'O'Soins: A software platform for modeling, planning and monitoring homecare activities

    Références :
    Rémi Bastide, Pierre Bardy, Bernard Borrel, Catherine Boszodi, Marinette Bouet, Kahina Gani, Éric Gayraud, Didier Gourc, Elyes Lamine, Pierre-Henri Manenq, Michel Schneider et Farouk Toumani. « Plas'O'Soins: A software platform for modeling, planning and monitoring homecare activities ». In : Irbm 35.2 (avr. 2014). P. 82--87. ISSN : 1959-0318. DOI : 10.1016/j.irbm.2014.02.008.
    Demographic changes in recent years have contributed to a shift in care models, with the development of homecare as a new alternative to traditional hospitalization. We present a software platform dedicated to the modeling, planning and monitoring of homecare workflows, developed in the framework of the French research program TecSan. The platform is used on the desktop by care coordinators, and on the go by care workers using mobile devices. (C) 2014 Published by Elsevier Masson SAS.
  • Case-based reasoning and system design: An integrated approach based on ontology and preference modeling

    Références :
    Juan Camilo Romero Bejarano, Thierry Coudert, Élise Vareilles, Laurent Geneste, Michel Aldanondo et Joël Abeille. « Case-based reasoning and system design: An integrated approach based on ontology and preference modeling ». In : Ai Edam-Artificial Intelligence for Engineering Design Analysis and Manufacturing 28.1 (févr. 2014). P. 49--69. ISSN : 0890-0604. DOI : 10.1017/S0890060413000498.
    This paper addresses the fulfillment of requirements related to case-based reasoning (CBR) processes for system design. Considering that CBR processes are well suited for problem solving, the proposed method concerns the definition of an integrated CBR process in line with system engineering principles. After the definition of the requirements that the approach has to fulfill, an ontology is defined to capitalize knowledge about the design within concepts. Based on the ontology, models are provided for requirements and solutions representation. Next, a recursive CBR process, suitable for system design, is provided. Uncertainty and designer preferences as well as ontological guidelines are considered during the requirements definition, the compatible cases retrieval, and the solution definition steps. This approach is designed to give flexibility within the CBR process as well as to provide guidelines to the designer. Such questions as the following are conjointly treated: how to guide the designer to be sure that the requirements are correctly defined and suitable for the retrieval step, how to retrieve cases when there are no available similarity measures, and how to enlarge the research scope during the retrieval step to obtain a sufficient panel of solutions. Finally, an example of system engineering in the aeronautic domain illustrates the proposed method. A testbed has been developed and carried out to evaluate the performance of the retrieval algorithm and a software prototype has been developed in order to test the approach. The outcome of this work is a recursive CBR process suitable to engineering design and compatible with standards. Requirements are modeled by means of flexible constraints, where the designer preferences are used to express the flexibility. Similar solutions can be retrieved even if similarity measures between features are not available. Simultaneously, ontological guidelines are used to guide the process and to aid the designer to express her/his preferences.
    Keywords: Case-based reasoning, decision-making, Design, engineering design, fuzzy-sets, injection mold design, knowledge representation, management, Ontology, Preferences, product design, Retrieval, similarity measures, support, System Engineering
  • A risk oriented model to assess strategic decisions in new product development projects

    Références :
    François Marmier, Didier Gourc et Frédéric Laarz. « A risk oriented model to assess strategic decisions in new product development projects ». In : Decision Support Systems 56 (déc. 2013). P. 74--82. ISSN : 0167-9236. DOI : 10.1016/j.dss.2013.05.002.
    The project management team has to respect contractual commitments: in terms of deadlines and budgets, that are often two antagonistic objectives. At the same time, the market becomes more and more demanding as far as costs and delays are concerned while expecting a high quality level. Then, the project management team has to continuously consider novelty and a risk management strategy in order to determine the best balance between benefits and risks. Based on the principles of a synchronized process between risk management and project management, and on the concepts of risk scenario, we propose a decision-making tool to help the project manager choose the best way to improve project success rate while controlling the level of risks. As a finding, the project manager would be able to evaluate and compare different novelties or development strategies taking into account their repercussions on potential risks and risk treatment strategies. Finally, a case study in the aerospace industry and specifically on satellite integration and tests is developed to validate this approach. (C) 2013 Elsevier B.V. All rights reserved.
    Keywords: Decision support system, management, Project planning, Project variant, Risk management, Scenarios, Treatment strategy
  • Concurrent product configuration and process planning, towards an approach combining interactivity and optimality

    Références :
    Paul Pitiot, Michel Aldanondo, Élise Vareilles, Paul Gaborit, Meriem Djefel et Sabine Carbonnel. « Concurrent product configuration and process planning, towards an approach combining interactivity and optimality ». In : International Journal of Production Research 51.2 (2013). P. 524--541. ISSN : 0020-7543. DOI : 10.1080/00207543.2011.653449.
    In mass customisation, defining concurrently the configured product and the planning of the associated production process is a key issue in the customer/supplier relationship. Nevertheless, few studies propose supporting the decision-maker during the resolution of this significant problem. After studying the decision-maker's needs and problem characterisation (modelling and scale aspects), we propose in this paper a two-step approach with the aid of some tools. The first step allows the customer or internal requirements to be captured interactively with a constraint-based approach. However, this step does not lead to one single solution, e. g. there are many uninstantiated remaining decision variables. In this paper, we suggest adding an original optimisation step to complete this task. Thus, the contribution of the study is twofold: first, methodologically to define a new two-step approach that meets industrial needs; and second, to provide adapted tools especially for the optimisation step. The optimisation step, using a multi-criteria constrained evolutionary algorithm, allows the user to select their own cost/cycle time compromise among a set of Pareto optimised solutions. A conventional evolutionary algorithm is adapted and modified, with the inclusion of filtering processing, in order to avoid generating invalid solutions. Experimentations are described, and a comparison is made with a branch-and-bound approach that outlines the interest in the propositions.
    Keywords: constraint filtering, constraint satisfaction, evolutionary algorithm, evolutionary algorithms, framework, optimisation, optimization, process planning, product configuration, requirements
  • Generic bill of functions, materials, and operations for SAP(2) configuration

    Références :
    Linda L. Zhang, Élise Vareilles et Michel Aldanondo. « Generic bill of functions, materials, and operations for SAP(2) configuration ». In : International Journal of Production Research 51.2 (2013). P. 465--478. ISSN : 0020-7543. DOI : 10.1080/00207543.2011.652745.
    Most available studies on configuration focus on either sales configuration specifying functional features or production configuration addressing product components. It has been well recognised that automating most of the activities associated with specification, engineering, and process planning of customised products and their interactions is one key in achieving product customisation. Thus, treating sales configuration and product configuration separately may not contribute to product customisation from a systematic view although they may lead to the improvement of individual stages. Recognising this limitation of existing studies, in this paper, we propose integrated SAles, Product and Production (SAP(2)) configuration, which helps achieve product customisation from a holistic view. Its rationale lies in automating consistently sales, product and production configuration activities in one system. In view of the importance of configuration models, we focus on the model underpinning SAP(2) configuration called generic bill of functions, materials and operations (GBoFMO) and discuss it in detail. As the core of SAP(2) configuration, GBoFMO can provide companies with an insight into organising the large volumes of data and knowledge in the life cycle of product family development. We also report a case study of light passenger aircrafts to illustrate the GBoFMO.
    Keywords: constraint satisfaction, generic bill of functions, materials and operations, mass customization, product configuration, production configuration, requirements, sales configuration, system, tool
  • Towards a crisis performance-measurement system

    Références :
    Carine Rongier, Matthieu Lauras, François Galasso et Didier Gourc. « Towards a crisis performance-measurement system ». In : International Journal of Computer Integrated Manufacturing 26.11 (1er nov. 2013). P. 1087--1102. ISSN : 0951-192X. DOI : 10.1080/0951192X.2012.684711.
    During a crisis, the main goal for decision-makers consists in restoring a stabilised nominal mode. The stakeholders face considerable pressure and drastic constraints in response time and coordination. This study proposes a method to support these stakeholders in making responsive and accurate decisions while carrying out a performance evaluation of the activities that run during the crisis-response process. This method is composed of four steps: (1) characterisation of the crisis-response system, (2) selection of system components to evaluate in priority, (3) determination of performance dimensions to consider and (4) creation of indicators. Currently, performance evaluation is only used subsequent to a crisis, due to difficulties in gathering and aggregating information into trustable performance indicators. This paper proposes a method to obtain a relevant and dynamic decision-support system. Decision-makers will use it to resolve the crisis based on performance evaluation, in addition to the essential experience they undergo. A case study of crisis management within the French Red Cross non-governmental organisation is developed, through a Web-based prototype, in order to explain how performance indicators can both support crisis-response management and improve the collaboration of stakeholders.
    Keywords: crisis management, disaster management, humanitarian organisation process, management, metrics, performance assessment, performance indicators, performance-measurement system, supply chain performance
  • A decision-making tool to maximize chances of meeting project commitments

    Références :
    Trong-Hung Nguyen, François Marmier et Didier Gourc. « A decision-making tool to maximize chances of meeting project commitments ». In : International Journal of Production Economics 142.2 (avr. 2013). P. 214--224. ISSN : 0925-5273. DOI : 10.1016/j.ijpe.2010.11.023.
    The project management team has to respect contractual commitments, in terms of deadlines and budgets, that are often two antagonistic functions. Then, during the invitation to tender phase or when faced with a risk situation, it has to determine its risk management strategy. Based on the principles of a synchronized process between risk management and project management, we propose a decision-making tool to help the project manager choose the best risk treatment strategy. The methodology developed, called ProRisk, uses the concepts of risk scenario, treatment scenario and project scenario to determine the consequences of possible risks combined or not with preventive and/or corrective treatment actions. As a finding, the project manager is also able to indicate to the sales department if the financial and deadline conditions are sufficiently profitable with regard to the risks. (C) 2010 Elsevier B.V. All rights reserved.
    Keywords: Decision support, Project planning, Risk management, Scenarios, Treatment strategy
  • Innovative process engineering: a generic model of the innovation process

    Références :
    Thomas Pénide, Didier Gourc, Hervé Pingaud et Philippe Peillon. « Innovative process engineering: a generic model of the innovation process ». In : International Journal of Computer Integrated Manufacturing 26.3 (1er mars 2013). P. 183--200. ISSN : 0951-192X. DOI : 10.1080/0951192X.2012.717715.
    Innovation can be represented as a knowledge transformation process perceived with different levels of granularity. The milestones of this process allow assessment for its each step and set up feedback loops that will be highlighted. This innovation process is a good starting point to understand innovation and then to manage it. Best practices being patterns of processes, we describe innovation best practices as compulsory steps in our innovation process. To put into practice, the management of innovation in a concrete organisation, an alignment (in our case a mapping) between a repository of business processes and our typical innovation process, helps to describe which best practice applies to which business process.
    Keywords: alignment, best practices, bpm, business, innovation, modelling
  • How to take into account general and contextual knowledge for interactive aiding design: Towards the coupling of CSP and CBR approaches

    Références :
    Élise Vareilles, Michel Aldanondo, Aurélien Codet de Boisse, Thierry Coudert, Paul Gaborit et Laurent Geneste. « How to take into account general and contextual knowledge for interactive aiding design: Towards the coupling of CSP and CBR approaches ». In : Engineering Applications of Artificial Intelligence 25.1 (févr. 2012). P. 31--47. ISSN : 0952-1976. DOI : 10.1016/j.engappai.2011.09.002.
    The goal of this paper is to show how it is possible to support design decisions with two different tools relying on two kinds of knowledge: case-based reasoning operating with contextual knowledge embodied in past cases and constraint filtering that operates with general knowledge formalized using constraints. Our goals are, firstly to make an overview of existing works that analyses the various ways to associate these two kinds of aiding tools essentially in a sequential way. Secondly, we propose an approach that allows us to use them simultaneously in order to assist design decisions with these two kinds of knowledge. The paper is organized as follows. In the first section, we define the goal of the paper and recall the background of case-based reasoning and constraint filtering. In the second section, the industrial problem which led us to consider these two kinds of knowledge is presented. In the third section, an overview of the various possibilities of using these two aiding decision tools in a sequential way is drawn up. In the fourth section, we propose an approach that allows us to use both aiding decision tools in a simultaneous and iterative way according to the availability of knowledge. An example dealing with helicopter maintenance illustrates our proposals. (C) 2011 Elsevier Ltd. All rights reserved.
    Keywords: Aiding design, Case-based filtering, Case-based reasoning, constraint satisfaction, Constraints satisfaction problem, Helicopters maintenance, management, support, system
  • A general framework for new product development projects

    Références :
    Marc Zolghadri, Philippe Girard, Claude Baron et Michel Aldanondo. « A general framework for new product development projects ». In : International Journal of Technology Management 55.3 (2011). P. 250--262. ISSN : 0267-5730. DOI : 10.1504/IJTM.2011.041951.
    Firms look for procuring a sustainable advantage over their competitors. Therefore, they should be both operationally and strategically efficient. However, as firms work with other companies, they are under threats of misunderstanding, inefficiency, difficult synchronisations, etc. These threats will be transformed into real business traps. In this paper, authors propose a global framework which focuses on collaborative new product development (NPD) projects. The ultimate goal is to minimise harmful potential consequences of collaborations. This framework emphasises critical characteristics of any collaboration among partners. It helps users to have a clearer understanding of the overall environment of such projects. This understanding leads not only managers towards a better definition of their strategy but also guides them to acquire a more resourceful operational efficiency.
    Keywords: business efficiency, Design, new product development framework, npd, supply chain, uncertainties
  • Multi-criteria performance analysis for decision making in project management

    Références :
    Guillaume Marques, Didier Gourc et Matthieu Lauras. « Multi-criteria performance analysis for decision making in project management ». In : International Journal of Project Management 29.8 (déc. 2011). P. 1057--1069. ISSN : 0263-7863. DOI : 10.1016/j.ijproman.2010.10.002.
    This study is focused on decision support in the context of product and service development projects. Decision support requires the capacity to characterize the current state of the project (performance evaluation) and the decision-maker's point of view. However, the different projects' stakeholders do not have the same needs in terms of performance evaluation to support their decision-making processes. Furthermore, in some cases controlling project performance using the elementary components of the Iron Triangle (Cost, Time and Quality) alone seems inefficient. This paper proposes a new multi-dimensional Project Performance Measurement System that would enable managers to deal with the volume of data. The proposition integrates the only character of each project (tasks, objectives, decision-makers personality and competences), several good practices in terms of universal project management dimensions on the one hand, and in terms of performance analysis on the other hand. Then, we show how an aggregation tool called MACBETH is used to analyze the performance measures according to project managers' own performance interests. A case study illustrates the proposed system. (C) 2010 Elsevier Ltd. and IPMA. All rights reserved.
    Keywords: Decision support systems, efficiency, macbeth, model, Multiple criteria analysis, Performance measurement system, Project management, Project performance, system
  • A collaborative demand forecasting process with event-based fuzzy judgements

    Références :
    Naoufel Cheikhrouhou, François Marmier, Omar Ayadi et Philippe Wieser. « A collaborative demand forecasting process with event-based fuzzy judgements ». In : Computers & Industrial Engineering 61.2 (sept. 2011). P. 409--421. ISSN : 0360-8352. DOI : 10.1016/j.cie.2011.07.002.
    Mathematical forecasting approaches can lead to reliable demand forecast in some environments by extrapolating regular patterns in time-series. However, unpredictable events that do not appear in historical data can reduce the usefulness of mathematical forecasts for demand planning purposes. Since forecasters have partial knowledge of the context and of future events, grouping and structuring the fragmented implicit knowledge, in order to be easily and fully integrated in final demand forecasts is the objective of this work. This paper presents a judgemental collaborative approach for demand forecasting in which the mathematical forecasts, considered as the basis, are adjusted by the structured and combined knowledge from different forecasters. The approach is based on the identification and classification of four types of particular events. Factors corresponding to these events are evaluated through a fuzzy inference system to ensure the coherence of the results. To validate the approach, two case studies were developed with forecasters from a plastic bag manufacturer and a distributor belonging to the food retailing industry. The results show that by structuring and combining the judgements of different forecasters to identify and assess future events, companies can experience a high improvement in demand forecast accuracy. (C) 2011 Elsevier Ltd. All rights reserved.
    Keywords: Collaborative forecasting, Demand planning, Fuzzy logic, Judgement, Time series
  • A review of Vendor Managed Inventory (VMI): from concept to processes

    Références :
    Guillaume Marques, Caroline Thierry, Jacques Lamothe et Didier Gourc. « A review of Vendor Managed Inventory (VMI): from concept to processes ». In : Production Planning & Control 21.6 (2010). P. 547--561. ISSN : 0953-7287. DOI : 10.1080/09537287.2010.488937.
    In the modern supplier-customer relationship, Vendor Managed Inventory (VMI) is used to monitor the customer's inventory replenishment. Despite the large amount of literature on the subject, it is difficult to clearly define VMI and the main associated processes. Beyond the short-term pull system inventory replenishment often studied in academic works, partners have to share their vision of the demand, their requirements and their constraints in order to fix shared objectives for the medium/long-term. In other words, the integration of VMI implies consequences for the collaborative process that links each partner's different planning processes. In this article we propose a literature review of VMI. Based on the conceptual elements extracted from this analysis, we suggest a VMI macro-process that summarises both operational and collaborative elements of VMI.
    Keywords: collaboration, determinants, impact, information, model, operating parameters, optimization, replenishment, Risk, supply chain, supply chain management, system, Vendor Managed Inventory
  • Structuring and integrating human knowledge in demand forecasting: a judgemental adjustment approach

    Références :
    François Marmier et Naoufel Cheikhrouhou. « Structuring and integrating human knowledge in demand forecasting: a judgemental adjustment approach ». In : Production Planning & Control 21.4 (2010). P. 399--412. ISSN : 0953-7287. DOI : 10.1080/09537280903454149.
    Demand forecasting consists of using data of the past demand to obtain an approximation of the future demand. Mathematical approaches can lead to reliable forecasts in deterministic context through extrapolating regular patterns in time-series. However, unpredictable events that do not appear in the historical data can make the forecasts obsolete. Since forecasters have a partial knowledge of the context and of the future events (such as strikes, promotions) with some probability, the idea presented in this work is on structuring the implicit and the explicit knowledge in order to easily and fully integrate it in final forecasts. This article presents a judgemental-based approach in forecasting where mathematical forecasts are considered as a basis and the structured knowledge of the experts is provided to adjust the initial forecasts. This is achieved using the identification and classification of four factors characterising events that could not be considered in the initial forecasts. Validation of the approach is provided with two case studies developed with forecasters from a plastic bag manufacturer and a distributor acting in the food market. The results show that structuring the expert knowledge through the identification of factor-related events leads to high improvements of forecast accuracy.
    Keywords: Demand planning, forecasting, information, judgemental factors, judgemental forecasting, time-series
  • Hybridation of Bayesian networks and evolutionary algorithms for multi-objective optimization in an integrated product design and project management context

    Références :
    Paul Pitiot, Thierry Coudert, Laurent Geneste et Claude Baron. « Hybridation of Bayesian networks and evolutionary algorithms for multi-objective optimization in an integrated product design and project management context ». In : Engineering Applications of Artificial Intelligence 23.5 (août 2010). P. 830--843. ISSN : 0952-1976. DOI : 10.1016/j.engappai.2010.01.019.
    A better integration of preliminary product design and project management processes at early steps of system design is nowadays a key industrial issue. Therefore, the aim is to make firms evolve from classical sequential approach (first product design the project design and management) to new integrated approaches. In this paper, a model for integrated product/project optimization is first proposed which allows taking into account simultaneously decisions coming from the product and project managers. However, the resulting model has an important underlying complexity, and a multi-objective optimization technique is required to provide managers with appropriate scenarios in a reasonable amount of time. The proposed approach is based on an original evolutionary algorithm called evolutionary algorithm oriented by knowledge (EAOK). This algorithm is based on the interaction between an adapted evolutionary algorithm and a model of knowledge (MoK) used for giving relevant orientations during the search process. The evolutionary operators of the EA are modified in order to take into account these orientations. The MoK is based on the Bayesian Network formalism and is built both from expert knowledge and from individuals generated by the EA. A learning process permits to update probabilities of the BN from a set of selected individuals. At each cycle of the EA, probabilities contained into the MoK are used to give some bias to the new evolutionary operators. This method ensures both a faster and effective optimization, but it also provides the decision maker with a graphic and interactive model of knowledge linked to the studied project. An experimental platform has been developed to experiment the algorithm and a large campaign of tests permits to compare different strategies as well as the benefits of this novel approach in comparison with a classical EA. (C) 2010 Elsevier Ltd. All rights reserved.
    Keywords: Bayesian network, evolutionary algorithm, Experience feedback, Learning, manufacturing systems, Product preliminary design, Project management
  • Towards a multi-dimensional project Performance Measurement System

    Références :
    Matthieu Lauras, Guillaume Marques et Didier Gourc. « Towards a multi-dimensional project Performance Measurement System ». In : Decision Support Systems 48.2 (janv. 2010). P. 342--353. ISSN : 0167-9236. DOI : 10.1016/j.dss.2009.09.002.
    This paper discusses the difficulty of controlling a complex project caused by the great number of performance indicators. The problem studied is how to allow project managers to better control the performance of their projects. From a literature review we noted several critical aspects to this problem: there are many dimensions for evaluating project performance (cost, time, quality, risk, etc.); performance factors should be able to be relevantly aggregated for controlling the project, but no formalized tool exists to do this. We suggest a method to facilitate project performance analysis via a multi-criteria approach. The method focuses on three particular axes for the analysis of project performance: project task, performance indicator categories, and a breakdown of the performance triptych (Effectiveness. Efficiency, Relevance). Finally, the MACBETH method is used to aggregate performance expressions. An application case study examining a real project management situation is included to illustrate the implementation. (c) 2009 Elsevier B.V. All rights reserved.
    Keywords: decision-support, Decision support systems, Design, efficiency, macbeth, model, Multiple criteria analysis, Performance measurement system, Project management, Project performance
  • How to take into account piecewise constraints in constraint satisfaction problems

    Références :
    Élise Vareilles, Michel Aldanondo et Paul Gaborit. « How to take into account piecewise constraints in constraint satisfaction problems ». In : Engineering Applications of Artificial Intelligence 22.4 (juin 2009). P. 778--785. ISSN : 0952-1976. DOI : 10.1016/j.engappai.2009.01.004.
    A particular data structure named a Quad Tree allows a better representation of solution space of binary continuous constraints C(x(1), x(2)), than classical continuous consistencies. The generation and integration of this data structure do not raise any particular problem for continuous constraints defined by only one mathematical formula [Sam, D., 1995. Constraint consistency techniques for continuous domains. Ph.D. Thesis, Ecole Polytechnique Federale de Lausanne]. In this paper, we propose to extend the method of generating Quad Trees in order to take into account, in CSPs, binary continuous constraints defined by a piecewise constraint, i.e. a set of functions defined on intervals. The first section presents the industrial requirements which led us to take into account this type of constraint in CSP. The second section recalls the principles of the Quad Tree. The last section describes our contributions relevant to Quad Tree extensions dealing with piecewise constraints. (C) 2009 Elsevier Ltd. All rights reserved.
    Keywords: Constraints satisfaction problem, Design, Filtering, Piecewise constraints, Quad Tree
  • Aiding design with constraints: an extension of quad trees in order to deal with piecewise functions

    Références :
    Michel Aldanondo, Élise Vareilles, Khaled Hadj-Hamou et Paul Gaborit. « Aiding design with constraints: an extension of quad trees in order to deal with piecewise functions ». In : International Journal of Computer Integrated Manufacturing 21.4 (2008). P. 353--365. ISSN : 0951-192X. DOI : 10.1080/09511920701575278.
    This paper deals with aiding preliminary design when considered as a constraint satisfaction problem (CSP). In this case, constraint filtering techniques provide some kind of interactive assistance to the designer. However, some kinds of numerical constraints corresponding with numerical relations cannot be filtered precisely with classical analytical filtering techniques such as interval arithmetic or box-consistency; it is therefore necessary to discretize them in order to include them in the CSP. To this end, quad trees (QT) have been proposed for binary constraints, or 2k trees when more than two variables are considered; but QT assume that a constraint must be defined by a single numerical function. The aim of this paper is to show that QT techniques can be extended when a constraint is defined by a piecewise function or by a set of numerical functions defined on intervals. The first section recalls some basics relevant to the preliminary design problem and the interests of the CSP assistance. The second section presents the principles of the QT. The last section describes our contributions relevant to QT extensions dealing with piecewise functions.
    Keywords: constraint satisfaction problem, knowledge-based system, preliminary design, quad trees
  • Configuration for mass customization: how to extend product configuration towards requirements and process configuration

    Références :
    Michel Aldanondo et Élise Vareilles. « Configuration for mass customization: how to extend product configuration towards requirements and process configuration ». In : Journal of Intelligent Manufacturing 19.5 (oct. 2008). P. 521--535. ISSN : 0956-5515. DOI : 10.1007/s10845-008-0135-z.
    In order to develop mass customization, many companies use configuration software to customize their products. Although many studies already exist about Product Configuration, Requirements and Process Configuration have not been studied in detail. As all these three aspects must be considered for mass customization, the aim of this paper is to show how Product Configuration, when considered as a constraint satisfaction problem, can be extended upstream towards Requirements Configuration and downstream towards Process Configuration. Product Configuration basics are first reviewed thanks to a constraint based approach, and an analysis of industrial configuration situations is done in order to clarify mass customization needs in terms of configuration. Then upstream Requirements Configuration and downstream Process Configuration are defined and generic models are proposed. It is shown that the proposed elements allow a global and consistent flow of configuration activities. A detailed example illustrates the different configuration problems and a discussion terminates the paper.
    Keywords: configuration, constraint satisfaction problem, manufacturing process, process modeling, product modeling, systems
  • Evaluation and design: a knowledge-based approach

    Références :
    Élise Vareilles, Michel Aldanondo et Paul Gaborit. « Evaluation and design: a knowledge-based approach ». In : International Journal of Computer Integrated Manufacturing 20.7 (2007). P. 639--653. ISSN : 0951-192X. DOI : 10.1080/09511920701566517.
    aim of this communication is to describe how aiding-design tools can evaluate designed solutions to help users make the best choices, avoid design mistakes and reduce the design time-cycle. First, we will compare the two main methods for aiding design behaviour simulation tools and domain knowledge simulation tools-and look at their advantages and drawbacks. We will focus on tools based on knowledge because of their 'interactivity' and for their ability to represent domain knowledge and show how they can be extended to evaluate designed solutions. We will then concentrate on an aiding-design tool based on constraints and see how a solution can be evaluated using an evaluation function. As such a tool has already been developed as part of a European project to help metallurgists design and evaluate heat treatment operations, we end with the presentation of a real example.
    Keywords: application, consistency, constraints, evaluation of solutions, interactive aiding design, networks
  • Where do we stand with fuzzy project scheduling?

    Références :
    Pierre Bonnal, Didier Gourc et Germain Lacoste. « Where do we stand with fuzzy project scheduling? ». In : Journal of Construction Engineering and Management 130.1 (16 janv. 2004). P. 114--123. ISSN : 0733-9364. DOI : 10.1061/(ASCE)0733-9364(2004)130:1(114).
    Fuzzy project scheduling has interested several researchers in the past two decades; about 20 articles have been written on this issue. Contrary to stochastic project-scheduling approaches that are used by many project schedulers, and even if the axiomatic associated to the theory of probabilities is not always compatible with decision-making situations, fuzzy project-scheduling approaches that Are most suited to these situations have been kept in the academic sphere. This paper starts by recalling the differences one can observe between uncertainty and imprecision. Then most of the published research works that have been done in this field are summarized. Finally, a framework for addressing the resource-constrained fuzzy project-scheduling problem is proposed. This framework uses temporal linguistic descriptors, which might become very interesting features to the project-scheduling practitioners.
    Keywords: activity times, generalized activity networks, pert
  • Mass customization and configuration: Requirement analysis and constraint based modeling propositions

    Références :
    The purpose of this paper is, on the one hand, to identify to define and classify customization requirements and, on the other hand, to evaluate how generic modeling and configuration assistance within the Constraint Satisfaction Problem (CSP) framework can fulfil the requirements. The aim is to provide commercial configurator knowledge base designers with constraint based generic modeling elements for customizable industrial product. A first part recalls the main trends of the configuration problem. In a second part divided in four sections corresponding with different requirement set; each section proposes a definition of the requirement set, some CSP based modeling elements and a discussion about adequacy of relevant configuration assistance techniques.
  • Expert configurator for concurrent engineering: Cameleon software and model

    Références :
    Michel Aldanondo, Sylvie Rougé et Mathieu Véron. « Expert configurator for concurrent engineering: Cameleon software and model ». In : Journal of Intelligent Manufacturing 11.2 (avr. 2000). P. 127--134. ISSN : 0956-5515. DOI : 10.1023/A:1008982531278.
    This paper, dealing with discrete production systems, has two goals. The first one is to identify cases in which the use of expert configurator software is a significant improvement for concurrent engineering achievement. Since the industrial implementation of these configurators is often tricky, the second issue of this paper is to present a model that allows to specify the industrial problem before implementation. This paper is divided into three sections. We first quickly recall the main trends of concurrent engineering and the related expert configurator interests. Then, the basic behavior and solutions for expert configurators are presented and the modeling requirements are pointed out. The third part is dedicated to the presentation, illustrated with an example, of our model and our method.
    Keywords: configuration, information system, product diversity, product modeling
  • A framework for a knowledge-based system for risk management in concurrent engineering

    Références :
    Emmanuel Caillaud, Didier Gourc, Luis Antonio Garcia, Rose Crossland et Chris McMahon. « A framework for a knowledge-based system for risk management in concurrent engineering ». In : Concurrent Engineering-Research and Applications 7.3 (sept. 1999). P. 257--267. ISSN : 1063-293X. DOI : 10.1177/1063293X9900700307.
    Knowledge is a requirement for concurrent engineering, and therefore an approach to capture and organise the different knowledge to be taken into account in concurrent engineering is proposed. This approach, known as the "MEthodology for Knowledge Engineering for Concurrent Engineering" (MEKECE) is a dedicated application of knowledge engineering methodologies to concurrent engineering that involves a combination of case based reasoning and expert systems approaches aimed at managing risk. To manage concurrent engineering specific risks, the knowledge of the different tasks constituting product development must be captured and organised, and information on the causes of risks that have a threshold effect on time and on cost must be available in a convenient form for the participants in the process. The framework of this knowledge based system for risk management in concurrent engineering is presented.
    Keywords: concurrent engineering, Design, knowledge, knowledge based system, manufacturing, Risk management

Projets en cours

  • OPERA

    Débuté le : 01/11/2016

    OPERA : Outils logiciels et ProcEssus pour la Réponse à Appel d’Offres

  • Smart Planning

    Débuté le : 01/11/2016

    Planification intelligente des tournées de transports de marchandises intégrant les dimensions santé, sécurité, environnementale et économique pour la distribution urbaine et régionale de marchandises avec une flotte mixte, composée de véhicules propres et de véhicules dotés d’autres types d’énergie.

Projets terminés

  • ProjEstimate

    Débuté le : 01/09/2012 Fini le : 31/08/2016

    Le succès d'un projet de développement informatique passe, entre autres, par la capacité à le piloter de manière efficiente, incluant la bonne définition des objectifs, des moyens requis et des délais espérés. La maîtrise des techniques d'estimation pour évaluer ces différents indicateurs dès le stade de l'avant-projet devient alors un gage de maturité des processus de pilotage. A ce stade, il est parfois difficile de caractériser avec certitude bon nombre de paramètres du projet (complexité des fonctionnalités, périmètre du projet, compétences des équipes…).

  • CRIBA

    Débuté le : 01/01/2013 Fini le : 31/07/2016

    L'objectif du projet C.R.I.B.A., déposé avec le centre Rapsodee, vise à démontrer la faisabilité d’une solution industrielle globale pour la rénovation de bâtiments d’habitation collectifs datant des années 1960/1970, à très haute performance énergétique (BEPOS) dans des coûts maîtrisés. L’idée est d’isoler ces bâtiments par l’extérieur afin d’améliorer de manière significative leur performance énergétique. De nombreuses entreprises sont déjà sur ce créneau, mais le plus souvent de manière très artisanale.

  • 2PI-MCO

    Débuté le : 01/06/2013 Fini le : 30/06/2016

    L’objet de ce projet consiste à formaliser et exploiter des connaissances en câblage électrique afin d’améliorer le processus de réponse à appel d’offre d’une entreprise spécialisée dans le levage industriel. Dans ce cadre, nous fournissons à l’équipe SDC du LGP de l’ENI de Tarbes un travail de conseil sur l’emploi des contraintes pour modéliser et exploiter certaines connaissances expertes.

  • Plas'O'Soins

    Débuté le : 01/04/2010 Fini le : 31/12/2014

    Pour compléter la prise en charge des patients effectuée par les hôpitaux et cliniques, des
    structures de proximité, HAD, MAD ou SSIAD, se sont développées ces dernières années. Elles
    mobilisent des acteurs de proximité qui se déplacent au domicile du patient. Afin d'améliorer la
    qualité de soins, et dans un souci d'efficience des moyens mobilisés, l’un des enjeux majeurs porte
    sur la coordination de ces différents acteurs. Le projet PlaS'O'Soins a pour objectif de développer

  • SySO

    Débuté le : 28/10/2010 Fini le : 16/12/2013

    Face à l'augmentation de la demande de prise en charge à domicile des personnes âgéesou semi-dépendantes, la mise en place d'un système permettant la coordination et le suivi desinterventions des professionnels de l'aide à domicile devient nécessaire.

  • ISTA-3

    Débuté le : 15/10/2008 Fini le : 14/01/2012

    Le projet ISTA3 (Interopérabilité de 3 e génération pour les sous-traitants de l’Aéronautique) est un projet fortement porté par le pôle GSO de l’InterOp V-LAB. Ces travaux visent à proposer une démarche dirigée par les modèles pour prendre en charge l’interopérabilité entre les sous-traitants d’Airbus. La participation du CGI concerne surtout, pour l’axe IO, la partie transformation de modèles (entre la caractérisation de la collaboration et les modèles permettant d’aboutir à son pilotage) et celle sur la réconciliation sémantique.

  • Hélimaintenance

    Débuté le : 01/07/2008 Fini le : 30/09/2011

    L’objectif du projet Hélimaintenance est de réduire de 30% les coûts de maintenance des hélicoptères civils et militaires en optimisant les processus industriels de maintenance. Dans ce cadre, le lot du CGI était de mettre au point une maquette logicielle permettant de configurer/particulariser toutes les activités du processus de maintenance devant être réalisées lors d’une visite en prenant en compte l’état effectif de la machine. Un ensemble logiciel d’aide associant raisonnement à partir de cas et propagation de contraintes a été mis au point.

  • ATLAS

    Débuté le : 01/12/2007 Fini le : 31/07/2011

    En conception industrielle, les concepteurs sont souvent en conflit avec les gestionnaires. Disposant chacun d’un langage, d’outils et de méthodes spécifiques, leur collaboration et

Thèses terminées