Search

UIDB/04647/2020 UIDP/04647/2020 Since the 1970s, the application of microprocessor in industrial machinery and the development of computer systems have transformed the manufacturing landscape. The rapid integration and automation of production systems have outpaced the development of suitable human design criteria, creating a deepening gap between humans and systems in which human was seen as an important source of errors and disruptions. Today, the situation seems different: the scientific and public debate about the concept of Industry 4.0 has raised awareness about the central role humans have to play in manufacturing systems, the design of which must be considered from the very beginning. The future of industrial systems, as represented by Industry 4.0, will rely on the convergence of several research fields such as Intelligent Manufacturing Systems (IMS), Cyber-Physical Systems (CPS), Internet of Things (IoT), but also socio-technical fields such as social approaches within technical systems. This article deals with different human social dimensions associated with CPS and IoT and focuses on their conceptual evolution regarding automated production systems’ sociability, notably by bringing humans back in the loop. Hereby, this paper aims to take stock of current research trends to show the importance of integrating human operators as a part of a socio-technical system based autonomous and intelligent products or resources. Consequently, different models of sociability as a way to integrate humans in the broad sense and/or the develop future automated production systems have been identified from the literature and analysed. publishersversion published

International audience; Several sawmill simulators exist in the forest-product industry. They are able to simulate the sawing of a log to generate the set of lumbers that would be obtained by transforming a log at a sawmill. In particular, such simulators are able to use a 3D scan of the exterior shape of the logs as input for the simulation. However, it was observed that they can be computationally intensive. Therefore, several authors have proposed to use Artificial Intelligence metamodel, which, in general, can make predictions extremely fast once trained. Such models can approximate the results of a simulator using a vector of descriptive features representing a log, or, alternatively, the full 3D log scans. This paper proposes to use dissimilarity to representative log scans as features to train a Machine Learning classifier. The concept of class Medoids as representative elements of a class will be presented, and a Simlarity Discrimant Analysis was chosen as a good candidate ML classier. This classifier will be compared with two others models studied by the authors.

International audience; It is now accepted that using multi-agent systems (MAS) improve the reactivity to treat perturbation(s) within flexible manufacturing system. Intelligent algorithms shall be used to address these perturbation(s) and all smart decision entities within their environment have to continuously negotiate until their common and final goal is achieved. This paper proposes a negotiation-based control approach to deal with variability on a manufacturing system. It has initially formulated and modeled an environment in which all contributing entities or agents operate, communicate, and interact with each other productively. Then after, simulation and applicability implementation experiments on the basis of full-sized academic experimental platform have been conducted to validate the proposed control approach. Product and resource entities negotiate considering different key performance measures in order to set best priority-based product sequencing. This has been done with expectations that the applicability of the negotiation-based decision-making will be more adaptable to deal with perturbation(s) than another alternative decision-making approach called pure reactive control approach. The result showed that negotiation among the decisional entities has brought significant improvement in reducing makespan and hence conveyed better global performance of a manufacturing system.

International audience; Although digital simulations are becoming increasingly important in the industrial world owing to the transition toward Industry 4.0, as well as the development of digital twin technologies, they have become increasingly computationally intensive. Many authors have proposed the use of Machine Learning (ML) metamodels to alleviate this cost and take advantage of the enormous amount of data that are currently available in industry. In an industrial context, it is necessary to continuously train predictive models integrated into decision support systems to ensure the consistency of their prediction quality over time. This led the authors to investigate Active Learning (AL) concepts in the particular context of the sawmilling industry. In this paper, a method based on AL is proposed to combine simulation and an ML metamodel that is trained incrementally using only selected data (smart data). A case study based on the sawmilling industry and experiments are shown, the results of which prove the possible advantages of this approach.

It is now accepted that using the multi-agents system (MAS) augments the reactivity to treat disturbances within flexible manufacturing system. Each agent could have different capability (evolution, learning, etc.) and the whole physical and control system, based on the agent interaction, could lead emerging behaviors to dynamically adapt a production schedule. Intelligent control algorithms shall be used to define these variables and all smart entities within their environment have to continuously negotiate for their final common goal. This paper proposes a negotiation-based reactive control approach to deal with the variability on manufacturing processes. A simulation experiment on the basis of full sized academic experimental platform was used to test how the negotiation-based reactive control approach could optimize priority based product sequencing. The product and resource agents have been built to negotiate considering different production performance measures. This has been done with expectations that the applicability of the negotiation-based reactive decision making process will be more adaptable to a production change than myopic decisions.

International audience; In recent times, the manufacturing processes are faced with many external or internal (the increase of customized product rescheduling , process reliability,..) changes. Therefore, monitoring and quality management activities for these manufacturing processes are difficult. Thus, the managers need more proactive approaches to deal with this variability. In this study, a proactive quality monitoring and control approach based on classifiers to predict defect occurrences and provide optimal values for factors critical to the quality processes is proposed. In a previous work (Noyel et al. 2013), the classification approach had been used in order to improve the quality of a lacquering process at a company plant; the results obtained are promising, but the accuracy of the classification model used needs to be improved. One way to achieve this is to construct a committee of classifiers (referred to as an ensemble) to obtain a better predictive model than its constituent models. However, the selection of the best classification methods and the construction of the final ensemble still poses a challenging issue. In this study, we focus and analyze the impact of the choice of classifier types on the accuracy of the classifier ensemble; in addition, we explore the effects of the selection criterion and fusion process on the ensemble accuracy as well. Several fusion scenarios were tested and compared based on a real-world case. Our results show that using an ensemble classification leads to an increase in the accuracy of the classifier models. Consequently, the monitoring and control of the considered real-world case can be improved.

Nowadays complex control systems are rising and especially hybrid control architectures which are developed to face the manufacturing control challenges that occur with the last industrial revolution and the emerging of industry 4.0. This work presents an application, on a testing platform, of a scheduling algorithm, with multi-criteria objectives, developed for Acta-Mobilier company suffering from high rework rate. This algorithm will inscribe itself in a hybrid control system based on smart entities. The main objective is to validate the contribution of the proposed algorithm in a disturbed environment. The platform, implemented with a multi-agent's system, allows to measure the reliability of the proposed algorithm used on a complex system in the particular case of high rework rate.

In order to ensure an overall efficient production performance, the industrial experiences and research activities have demonstrated the interest of hybrid control systems, which couple a predictive scheduling with a distributed reactive control. In this context, it is commonly accepted that using the multi-agent systems (MAS) paradigm enhances the reactivity to treat disturbances and improves the decision making process of a shop floor. Each agent can have different capabilities (evolution, learning etc.) and the whole system, based on the agent interaction, leads emerging behaviours to dynamically adapt the production schedule. This paper is aimed to develop and simulate a negotiation scenario to deal with disturbed manufacturing processes. The scenario was implemented on the basis of TRACILOGIS test-bed platform. The negotiation protocol consists in setting the best sequential priority based on some performance indicators. This protocol is compared with a purely reactive production mode.

Best track paper (1/20); International audience; Today, sustainability becomes one of the biggest challenges. It represents a key issue in every production activity. To face this issue, a possible solution is to enhance knowledge usage in manufacturing and sustainability domains. In this paper, we extend the ONTO-PDM ontology for formalizing sustainable manufacturing knowledge. An industrial case is presented for instantiating the extension. Moreover we design a knowledge-based system, which exploits sustainable manufacturing knowledge for supporting design and process planning with sustainability proposals, generating machine code starting from product specifications.

International audience; Appeared in 80's, Just in Time (JiT) leads to more flexibility, reactivity and more Work in Process control. This philosophy gives autonomous decision making possibilities to shop floor operators. Coming from holonic manufacturing paradigm, Product Driven System (PDS) Concept is still emergent and leads to give information and decision capacities to products. In this paper, we show that in the specific JiT context, PDS are pertinent for decision making process and operational tasks automation. A control architecture is also proposed. This architecture is composed by a control system, an emulator, a data base and interfaces. Two industrial applications are presented. In perspectives, we initiate the optimisation module integration problem.

IF=3.035; International audience; Nowadays, industrials are seeking for models and methods that are not only able to provide efficient overall production performance, but also for reactive systems facing a growing set of unpredicted events. One important research activity in that field focuses on holonic/multi-agent control systems that couple predictive/proactive and reactive mechanisms into agents/holons. Meanwhile, not enough attention is paid to the optimization of this coupling. The aim of this paper is to depict the main research challenges that are to be addressed before expecting a large industrial dissemination. Relying on an extensive review of the state of the art, three main challenges are highlighted: the estimation of the future performances of the system in reactive mode, the design of efficient switching strategies between predictive and reactive modes and the design of efficient synchronization mechanisms to switch back to predictive mode. indicator of the production system, discrete-event observer, flexible manufacturing system.

Part 22: Sustainable Collaborative Networks III; International audience; To cope with the customer-oriented business model in a global competitive market, enterprises tend to be networked for achieving mass customisation: i.e. offering customisable products with the same efficiency as mass production. This scenario highlights two faces of variability: variability of needs (on customer side) and variability of organisations (on production side). Both types of variability induce a huge number of specified products, namely configurations. This configuration variability must be efficiently managed. This position paper discusses trends and issues for rationalising the number of configurations: i.e. engineering the right number of configurations that match both the customer needs and the production strategy. After this positioning, we propose a systemic perspective for addressing the discussed issues from a sustainability point of view. Finally we give a perspective for a product line definition method that leads to models that meet the discussed variability rationalisation.

International audience; Sustainability is one of the biggest challenges of this century either for the environment or economical growth. The required cultural shift needs challenging action that will involve deeply software and hardware aspect of manufacturing processes. In this paper, the software part of the matter is addressed by proposing a product centric ontology, in which concepts of product, processes and resources are associated to functions and sustainable manufacturing knowledge. The aim is to design a knowledge-based system that, simulating a sustainable manufacturing expert, is able to automatically identify change opportunities and to propose alternatives on the basis of the existing production scenario.

International audience; In this paper, we address a way to improve a classic kanban control system, by using kanban cards as an informational/decisional entity in order to enrich shop-floor information/decision. The real-time information collected and the simulation tool proposed enable to coordinate distributed decision according to a unique and global performance indicator. Our proposition consists in enabling any shop-floor decision maker to evaluate different kanban priority scenarios according to a unified objective, taking into account the global situation of the workshop. Models of the data collection and decision support system are presented. A generic information system enables to provide a relevant view of shop-floor status. Such information will be useful to efficiently feed a real-time simulation tool in order to evaluate solutions .The application is illustrated using the case of an industrial furniture manufacturer.

International audience; For decades now, manufacturing systems have grown in size and complexity. Between new consumption habits and hypercompetitive markets, manufacturing systems have started a race towards the industry of the future. Still, many technological and societal issues are paving their way: connectivity, resilience and human integration being among the most critical ones. The idea of this paper is to bring a new framework to help answering these issues by bringing resilience to systems, improving their interoperability, enhancing Data acquisition, transmission & processing, enabling the establishment hierarchical levels among agents, or by facilitating the system acceptance by human agents and the human integration within the system. To this end, this article brings a new formal framework for Social Holonic Control Architectures, based on an analysis of the existing literature. An UML-based modelling framework will equally be proposed to ease understanding and implementation of this new Social Holonic Control Architecture, illustrated by a concrete application on a small-scale Multi-Agent System.