484 research outputs found
Engagement Evaluation in a Virtual Learning Environment via Facial Expression Recognition and Self-Reports: A Preliminary Approach
No full textMulti-Agent Reinforcement Learning Method for Disassembly Sequential Task Optimization Based on Human–Robot Collaborative Disassembly in Electric Vehicle Battery Recycling
No full textInternational audienceAbstract With the wide application of new Electric Vehicle (EV) batteries in various industrial fields, it is important to establish a systematic intelligent battery recycling system that can be used to find out the resource wastes and environmental impacts of the retired EV battery. By combining the uncertain and dynamic disassembly and echelon utilization of EV battery recycling in the remanufacturing fields, human–robot collaboration (HRC) disassembly method can be used to solve huge challenges about the efficiency of retired EV battery recycling. In order to find out the disassembly task planning based on HRC disassembly process for retired EV battery recycling, a dynamic disassembly sequential task optimization method algorithm is proposed by Multi-Agent Reinforcement Learning (MARL). Furthermore, it is necessary to disassemble the retired EV battery disassembly trajectory based on the HRC disassembly task in 2D planar, which can be used to acquire the optimal disassembly paths in the same disassembly planar by combining the Q-learning algorithm. The disassembly task sequence can be completed through standard trajectory matching. Finally, the feasibility of the proposed method is verified by disassembly operations for a specific battery module case
GUI USABILITY IMPROVEMENT FOR A NEW DIGITAL PATTERN TOOL TO ASSIST GEARBOX DESIGN
No full textDesign team can speed up the process of managing information related to gearbox design process by adopting digital pattern tools. These tools, as KBE systems, can assist engineers in re-using previous knowledge in order to improve time-consuming task as retrieval and selection of previous architectures and to modify and virtually test a new gearbox design. A critical point in the development of a KBE system is the interface usability to demonstrate effective reduction of development time and satisfaction in its use. In this paper, the authors face the problem of usability improvement of the Graphical User Interface (GUI) of the KBE system previously proposed. An approach based on Analytic Hierarchy Process (AHP) and Multiple-Criteria Decision Analysis (MCDA) has been used. A participatory test has been performed for evaluating the Usability Index (UI) of the GUI. Taking into account the data analysis some changes have been carried out and a new GUI release has been validated with new experimentations
Perpignan, C., Baouch, Y., Robin, V. and Eynard, B.
No full textNowadays, to deal correctly with sustainable issues, future engineers must have the ability to use non- technical skills. In order to evaluate all interactions and all possible solutions, a systemic vision of problematics should be adopted. We wanted to demonstrate the possibility of integrating all these non- technical competencies in a disciplinary training. For this reason, we developed some examples of activities to provide support to teachers and we proposed a skills and knowledge model to support teachers in creating their own educational. This model was tested to bachelor engineering students. We suggested them an eco-design problem-based learning activity. Objectives of this case study are to identify which type of skill mix was addressed by students and compared them with levels defined in the model. It’s also the opportunity to assess how associations are made between these two kinds of competencies. The paper presents results of our case study. Including improvements needed in our competencies model. Some future work will be drawn at the concluding section to propose the next of our research for integrating sustainable competencies into engineering curricula
Product relationships management enabler for concurrent engineering and product lifecycle management
No full textThe current competitive industrial context requires more flexible, intelligent and compact product lifecycles, especially in the product development process where several lifecycle issues have to be considered, so as to deliver lifecycle oriented products. This paper describes the application of a novel product relationships management approach, in the context of product lifecycle management (PLM), enabling concurrent product design and assembly sequence planning. Previous work has provided a foundation through a theoretical framework, enhanced by the paradigm of product relational design and management. This statement therefore highlights the concurrent and proactive aspect of assembly oriented design vision. Central to this approach is the establishment and implementation of a complex and multiple viewpoints of product development addressing various stakeholders design and assembly planning points of view. By establishing such comprehensive relationships and identifying related relationships among several lifecycle phases, it is then possible to undertake the product design and assembly phases concurrently. Specifically, the proposed work and its application enable the management of product relationship information at the interface of product-process data management techniques. Based on the theory, models and techniques such as described in previous work, the implementation of a new hub application called PEGASUS is then described. Also based on web service technology, PEGASUS can be considered as a mediator application and/or an enabler for PLM that externalises product relationships and enables the control of information flow with internal regulation procedures. The feasibility of the approach is justified and the associated benefits are reported with a mechanical assembly as a case study
Processing and Visual Analyze of Heterogeneous and Multidimensional Data in Biomedical PLM Context
No full textPart 8: Traceability and PerformanceInternational audienceThe emergence of PLM for biomedical imaging lifecycle management highlights the needs for management and analysis of heterogeneous, complex and multidimensional data in PLM systems. Data provenance in biomedical imaging domain is complex, notably provenance of processing data, and to ensure full traceability in a purpose of reuse, processing operations must be integrated to PLM systems and processing provenance must be easily analyzable by users. The DIMP (Data Integrated Management and Processing) method was designed for this objective: it allows user to launch easily processing chains from PLM systems and ensures a full management of provenance. The MDG (Multidimensional Dynamic Graph) representation is introduced to formalize complex provenance and data relationships. JGEX (Json Graph EXchange) file format and NeuroGraphViewer web graph visualization client have been developed to facilitate the analysis of MDG. An application of the DIMP method to the study of functional brain connectivity through MDG analysis encourages further work on analysis of complex relationships in PLM systems
Toward an Extensive Data Integration to Address Reverse Engineering Issues
No full textPart 10: Big Data Analytics and Business IntelligenceInternational audienceMechanical Reverse Engineering has been getting increasingly more attention from the industry. It aims rebuilding a broad Digital Mock Up (DMU) in order to redesign and/or remanufacture a product. Some of the reverse engineering challenges are to perform an efficient knowledge extraction out of the original product, and then to process the data it and consolidate them for further analysis. These data could be extracted from a vast number of different data as such as Manufacturing Data, Technical Reports, Design Data (e.g. CAD Files, technical drawings, etc.), Quality procedures, etc. Moreover, the amount of data stored by the companies’ information system keep on rapidly growing. We propose to use data science in order to cope with the previous issues. This paper aims to detail the different possibilities offered by the data science field of expertize, more precisely in terms of machine learning, text mining and computer vision, but also to give a brief overview on the future works we will research. This paper position itself as a roadmap for our further proceedings
- …
