Search

International audience; Monitoring activities in industry may require the use of wireless sensor networks, for instance due to difficult access or hostile environment. But it is well known that this type of networks has various limitations like the amount of disposable energy. Indeed, once a sensor node exhausts its resources, it will be dropped from the network, stopping so to forward information about maybe relevant features towards the sink. This will result in broken links and data loss which impacts the diagnostic accuracy at the sink level. It is therefore important to keep the network's monitoring service as long as possible by preserving the energy held by the nodes. As packet transfer consumes the highest amount of energy comparing to other activities in the network, various topologies are usually implemented in wireless sensor networks to increase the network lifetime. In this paper, we emphasize that it is more difficult to perform a good diagnostic when data are gathered by a wireless sensor network instead of a wired one, due to broken links and data loss on the one hand, and deployed network topologies on the other hand. Three strategies are considered to reduce packet transfers: (1) sensor nodes send directly their data to the sink, (2) nodes are divided by clusters, and the cluster heads send the average of their clusters directly to the sink, and (3)averaged data are sent from cluster heads to cluster heads in a hop-by-hop mode, leading to an avalanche of averages. Their impact on the diagnostic accuracy is then evaluated. We show that the use of random forests is relevant for diagnostics when data are aggregated through the network and when sensors stop to transmit their values when their batteries are emptied. This relevance is discussed qualitatively and evaluated numerically by comparing the random forests performance to state-of-the-art PHM approaches, namely: basic bagging of decision trees, support vector machine, multinomial naive Bayes, AdaBoost, and Gradient Boosting. Finally, a way to couple the two best methods, namely the random forests and the gradient boosting, is proposed by finding the best hyperparameters of the former by using the latter.

International audience; Along with the rising concern of environmental performance, eco-labeling is becoming more and more popular. However, the complex process of eco-labeling is demotivating manufacturers and service providers to be certificated. The knowledge contained in eco-labeling criteria documents is not semantically exploitable to computers. Traditional knowledge base in relational data model is not inter-operable, lacks inference support and is difficult to be reused. In our research, we propose a comprehensive knowledge base composed of interconnected OWL (Ontology Web Language) ontologies. This ontology based knowledge base allows reasoning and semantic query. In this paper, a modularization scheme about ontology development is introduced and it has been applied to EU Eco-label (European Union Eco-label) laundry detergent product criteria. This scheme separates entity knowledge and rule knowledge so that the ontology modules can be reused easily in other domains. Reasoning and inference based on SWRL (Semantic Web Rule Language) rules in favor of eco-labeling process is also presented.

International audience; The bidding process is one of the most important phases for system contractors. A successful bid implies defining and implementing attractive and realistic systems solutions that fulfil customer expectations. An additional challenge arises with the increase in systems diversity resulting from growing customization needs. As a result, for standard customizing offers, bidders find good quality support with configuration software for assemble/make-to-order situations. But when requirements exceed the standard offers, bidders need extended support to fulfil Engineering-to-Order requirements. In this context, this article shows how configuration knowledge models, which support configuration in assemble/make-to-order situations (AMTO), can be extended and used in engineer-to-order situations (ETO). Modeling is achieved assuming that the configuration problem is considered as a constraint satisfaction problem. Six key requirements that differentiate ETO from AMTO are identified and modeling extensions are proposed and discussed. An example illustrates all the contributions.

For many years, industrial performance has been implicitly considered as deriving from the optimisation of technological and material resources (machines, inventories, etc.), made possible by centralized organisations. The topical requirements for reactive and flexible industrial systems have progressively reintroduced the human workforce as the main source of industrial performance. Making this paradigm operational requires the identification and careful formalisation of the link between human resource and industrial performance, through concepts like skills, competencies or know-how. This paper provides a general survey of the formalisation and integration of competence-oriented concepts within enterprise information systems and decision systems, aiming at providing new methods and tools for performance management.