Mohamed Anis Dhuieb1*, Florent Laroche and Alain Bernard. 1Institut de Recherche en Communications et Cybernétique de Nantes, Ecole Centrale de.
Multi-scale enterprise knowledge structuring: towards context-aware assistant system Mohamed Anis Dhuieb 1 *, Florent Laroche and Alain Bernard 1
Institut de Recherche en Communications et Cybernétique de Nantes, Ecole Centrale de Nantes, 1 rue de la Noë 44300 Nantes, France
*correspondent author
In the era of digital factory, industrial companies are making significant efforts to manage the cost incurred due to the failure of achieving the minimum required product quality. Reducing this cost, generally called the cost of non-quality, is becoming a real issue for any manager who aims to achieve competitiveness in the market. In the case of manufacturing production lines, the most common reason behind the increasing of this cost is the unavailability of the needed support at workplace and in the machine level of the production line comparing to other divisions of the factory. This lack of appropriate assistance in accessing to the information and more generally the knowledge set of the factory affect the factory production system performance and workers efficiency on conducting daily working tasks. In the same perspective, and considering the expansion of digital ICT tools (PLM, ERP, MES…) usage in today’s factory, handling the generated mass of data and information is becoming a tough task. Consequently, the access to the right information is becoming more and more complex. This work is developed under the framework of “Digital Factory Assistant” (DFA) concept [Dhuieb et al., 2013]. The DFA is a knowledge-based system defined as a support for production line workers daily activities. When designing such socio-technical system, and taking into account the continuously changing character of the production line, the adaptation process of the information according to different working situations that might occur is a difficult task. Ambiguous and confusing information may take a long time for the user to interpret and in the case of misunderstanding; it can lead to the disposal of the product or setting inexact process parameters. The literature related to knowledge-based systems in the manufacturing domain particularly showed the limits of these systems in responding to different dynamic working situations of their users [Toro et al., 2007] [Espíndola et al., 2013]. The conducted research work aims at proposing a new approach allowing a contextual access to the knowledge set in the factory. To do so, we propose a multi-scale knowledge structure inspired by the work of Dreyfus related to the incremental expertise acquisition [Dreyfus et al.,1980]. The aim of this approach is to give the factory actor the possibility to explore the set of knowledge in a better manner that serves both simplifying the complexity of the decision-making process and enhancing the learning by doing practice in factory production line through incremental knowledge acquisition. In order to address the right set of information to the right user, we relies on the context notion proposed in computer science works as a pillar of ubiquitous computing vision [Weiser, 1996]. We propose a context model aiming to help the assistant in perceiving the current working situation of the assistant user and then address him/her with the related knowledge set.
By means of the proposed contextual knowledge approach, the assistant user is able to navigate between the set of knowledge in a structured way and in a given situation during the manufacturing process execution. Key words: Knowledge Management, Context-awareness, decision support.
References Dhuieb, M. A., Laroche, F., & Bernard, A. (2013). Digital Factory Assistant: Conceptual Framework and Research Propositions. In Product Lifecycle Management for Society (pp. 500-509). Springer Berlin Heidelberg. Dreyfus, S. E., & Dreyfus, H. L. (1980). A five-stage model of the mental activities involved in directed skill acquisition (No. ORC-80-2). California Univ Berkeley Operations Research Center. Espíndola, D. B., Fumagalli, L., Garetti, M., Pereira, C. E., Botelho, S. S., & Ventura Henriques, R.: A model-based approach for data integration to improve maintenance management by mixed reality. Computers in Industry (2013). Toro, C., Sanín, C., Vaquero, J., Posada, J., & Szczerbicki, E.: Knowledge based industrial maintenance using portable devices and augmented reality. In Knowledge-Based Intelligent Information and Engineering Systems (pp. 295-302). Springer Berlin Heidelberg (2007). Weiser M., The Computer of the 21St Century, (1996).