Benoît Iung

Overview on Bayesian networks applications for dependability, risk analysis and maintenance areas

In this paper, a bibliographical review over the last decade is presented on the application of Bayesian networks to dependability, risk analysis and maintenance. It is shown an increasing trend of the literature related to these domains. This trend is due to the benefits that Bayesian networks provide in contrast with other classical methods of dependability analysis such as Markov Chains, Fault Trees and Petri Nets. Some of these benefits are the capability to model complex systems, to make predictions as well as diagnostics, to compute exactly the occurrence probability of an event, to update the calculations according to evidences, to represent multi-modal variables and to help modeling user-friendly by a graphical and compact approach. This review is based on an extraction of 200 specific references in dependability, risk analysis and maintenance applications among a database with 7000 Bayesian network references. The most representatives are presented, then discussed and some perspectives of work are provided.

Formalisation of a new prognosis model for supporting proactive maintenance implementation on industrial system

The importance of the maintenance function has increased because of its role in keeping and improving system availability and safety, as well as product quality. To support this role, the maintenance concept has undergone several major developments that have led to proactive considerations mainly based on a prognosis process, which normally allows selection of the best maintenance action to be carried out. This paper proposes the deployment and experimentation of a prognosis process within an e-maintenance architecture. The deployment follows a methodology based on the combination of both a probabilistic approach for modelling the degradation mechanism and of an event one for dynamical degradation monitoring. The feasibility and benefits of this new prognosis process is investigated with an experiment using a manufacturing TELMA (TELe-MAintenance) platform supporting the unwinding of metal bobbins.

A multi-agents based E-maintenance system with case-based reasoning decision support

Abstract Today, one challenge of a manufacturer is to maintain with the consumer, the expected service of the supplied product during the whole product life cycle, no matter where the product and the consumer are located. The combination of modern information processing and communication tools, commonly referred to as Tele-service, offers the technical support required to implement this remote service maintenance. However, this technical support is insufficient to face new remote maintenance decision-makings which requires not only informational exchanges between customers and suppliers but also co-operation and negotiation based on the sharing of different complementary and/or contradictory knowledge. It requires an evolution from Tele-service to E-service and e-Maintenance in particular where the maintenance decision-making results from collaboration of maintenance processes and experts to form a Distributed Artificial Intelligence environment. For this purpose, a Problem-Oriented Multi-Agent-Based E-Service System (POMAESS) is introduced in this paper. The protocol of negotiation for multi-agents and the “Case-Based Reasoning”-based decision support function within this system are discussed, emphasised at the service maintenance problem solving. A prototype system based on these methodologies is developed to demonstrate the feasibility.

From remote maintenance to MAS-based e-maintenance of an industrial process

One of the main consequences of the extended enterprise is the emergence of new forms of relationships between the customer and the supplier in order to ensure the quality of service of the object throughout the life cycle. Innovative communication and co-operation methods are needed to support these new relationships. The combination of modern information processing and communication tools, commonly referred to as tele-service, offers the technical support required to access remote information. Indeed, it is easier to transfer information and knowledge to different actors than to move an actor to the site. However, even if this technical support is necessary for information communication, it is insufficient to develop a co-operation-based working situation that involves many self-motivated customers and suppliers sharing a common goal. This synergy is an emergent property of the system as a whole, and it is not expected to be obtained as a simple sum of its components. For example, a challenging problem in the field of product manufacturing is to assist the operator in its decision-making, when the system functioning is degraded, to preserve the system under service at maximum (anticipation of the failure) while remaining it in a space of allowed operation (to avoid consequences of an error in judgement). That means an evolution from tele-service to e-work and e-maintenance in particular where the assistance to operator results from collaboration of maintenance processes and experts. Consequently, this paper examines some issues and challenges involved in the evolution from the tele-maintenance of an industrial platform to the e-maintenance, and then proposes a multi-agent system-based collaboration as a solution to implement the e-maintenance experiments.

Generic prognosis model for proactive maintenance decision support: application to pre-industrial e-maintenance test bed

Proactivity in maintenance, which is mainly materialized by degradation-based anticipation, becomes essential to avoid failure situation with negative impact on product and/or system conditions. It leads to make emerging the E-maintenance philosophy to move from “fail and fix” maintenance practices to “predict and prevent” strategies. Within these new strategies, the anticipation action is fully supported by prognosis business process. Indeed it analyses the degradation impact on the component itself but also on the global performances of the production system in order to predict future failures of the system and investigate (future maintenance) actions. However, only few research works focuses on generic and scalable prognostic approach. Existing methods are generally restricted on component view and for solving the failure prediction issue. Consequently, the contribution presented in this paper aims at developing a global formalization of the generic prognosis business process. This generic process can be used after, from an instantiation procedure, to develop specific prognosis processes related to particular application such as shown in this paper with the case of E-maintenance platform developed within DYNAMITE Project.

Maintenance alternative integration to prognosis process engineering

Purpose – This paper proposes the extension of a prognosis process by means of the integration of maintenance alternative impacts in order to develop a maintenance decision‐making tool.Design/methodology/approach – The deployment of this extended prognosis process follows a methodology based both on probabilistic and on event approaches.Findings – The importance of the maintenance function has increased due to its role in keeping and improving the system availability and safety but also the product quality. To support this new role, the maintenance concept has undergone several major developments to lead to proactive considerations mainly based on prognosis process allowing one to select the best maintenance plan to be carried out.Practical implications – Studies over the last 20 years have indicated that around Europe the direct cost of maintenance is equivalent to between 4 and 8 per cent of total sales turnover. The indirect cost of maintenance is likely to be a similar amount. Thus, in the countries w...

Industrial system knowledge formalization to aid decision making in maintenance strategies assessment

Abstract High competitiveness and the emergence of new Information and Communication Technologies in industrial enterprises require a higher understanding and mastering of their operation systems to improve expected performances. In that sense, managers should take decisions about the strategies to be implemented as well as the resources to be used to achieve the target performances. Decisions result either from subjective considerations either from models allowing performances assessment. To help managers in the decision making process, it is necessary to represent industrial systems by means of models to better control them. However, this task underlines two major issues. The first one deals with the development of these models which is time and money consuming for the enterprises. This issue leads the consideration of formalizing generic knowledge by means, for example, of generic patterns, as a relevant solution to support models capitalization. The second issue deals with the degree of confidence of the models regarding to the reality of the industrial systems in order to avoid unrealistic assumptions, decreasing complexity etc. To face these challenges, this paper presents a methodology to represent, in a generic way, the key concepts of an industrial system and the relationships between the concepts materialized by semantic rules. More precisely, this methodology is investigated in the domain of dependability in order to assess performances, from the concepts formalization of both the production system and the maintenance one, based on the maintenance strategies applied. Thus generic patterns are cogent to support knowledge capitalization and reuse for leading to Components Off The Shelf (COTS). Patterns are built on a Probabilistic Relational Model (PRM) and can be instantiated then assembled to form a global model of a specific industrial system. The global model allows simulation step for maintenance strategies assessment helping the decision making process. The feasibility and added-value of this methodology, mainly in terms of patterns capitalization and reuse, are shown on two case studies: a pumping system and a real harvest production system. Moreover, lessons-learned issued from these applications are discussed.

A structured approach for the assessment of system availability and reliability using Monte Carlo simulation

Purpose – This paper proposes a method to model and assess the availability and reliability of a system when numerous factors such as system complexity, wide range of failure modes, environment, and sustainability may influence system behaviour.Design/methodology/approach – The approach for reliability/availability study is using continuous time stochastic simulation (Monte Carlo simulation) and is based on seven steps for covering logical phases from system description to simulation result discussion. The feasibility and benefits of this approach are shown in a case study on cogeneration plant.Findings – Owing to the factors influencing the system behaviour, the opportunity to carry out system availability/reliability assessment through analytical models will be many times very restrictive. Thus a general approach to this problem is proposed based on Monte Carlo (stochastic) simulation. The simulation of the systems life process will be carried out in the computer, and estimates will be made for the des...

Sustainable management of end-of-life systems

In a sustainable development context, the stakes of the last stage of system life cycle, the end-of-life stage, have increased over recent years. End-of-life systems have to be de-manufactured in order to be valued so as to respond to environmental concerns. The aim of a disassembly strategy consists in issuing a solution to the whole decision problem raised during the end-of-life stage of systems. Indeed, decision makers have to select valuable components according to technical, economical and environmental criteria and then design and optimise a disassembly support system that will generate these products. The solution obtained is what we refer to in this article as a disassembly trajectory. The work presented in this article is about planning these trajectories on different horizons integrating several arrivals of end-of-life systems. The proposed approach, with Bayesian networks and influence diagrams as the underlying mathematical tools, enables dynamically defined uncertainties to be taken into account.

Evaluating the Role of Maintenance Maturity in Adoption of New ICT in the Process Industry

The paper provides the results of an investigation on the perception of new Information and Communication Technologies (ICTs) in the process industry. A research question is the main focus of the investigation: which are the technological components enabling the development and improvement of maintenance operations? Since this topic covers a lot of stuff, the research focus is restricted in this paper, according to two guidelines: first, the comprehensive research scope focuses on the new ICT enabling the improvement of Condition Based Maintenance activities; secondly, the paper focuses on the results retrieved through a case study analysis in the process industry. The investigation is based on the assessment of the maintenance maturity of the companies cooperating in the research, in view of the fact that new ICT perception can be influenced by the maintenance management context in which the technologies are evaluated.