SmartDFRelevance: A Holonic Agent Based System for Engineering Industrial Projects in Concurrent Engineering Context
In the era of industry 4.0, the design of complex engineered systems is a challenging mission, and most researchers would argue that it is linked to intentional action and it cannot emerge out of complexity. In fact, to achieve the common ‘cost/quality/de
- PDF / 836,808 Bytes
- 21 Pages / 439.37 x 666.142 pts Page_size
- 12 Downloads / 218 Views
Abstract In the era of industry 4.0, the design of complex engineered systems is a challenging mission, and most researchers would argue that it is linked to intentional action and it cannot emerge out of complexity. In fact, to achieve the common ‘cost/quality/delay’ targets, engineers must work together to create the best overall solution from their individual components, and exploit and regenerate the required intellectual capital (Knowledge). Therefore, to be effective, we need a knowledge based system that takes into consideration all the users’ needed methods to create share reuse and evaluate knowledge. Thus, using complex adaptive system theory, mainly Distributed Artificial Intelligence (holonic agent paradigm), a new knowledge-based system can be designed to address this research issue. In this regard, the purpose of this paper is first to provide a comparative analysis of the appropriate method that considers the global challenges for designing a product in a concurrent engineering context. Second, a holonic multi-agent system, called SmartDFRelevance is proposed based on Agent-oriented Software Process for Complex Engineering Systems methodology. Keywords Complex adaptive system theory · Knowledge based system · Distributed artificial intelligence · Concurrent engineering · Holonic multi-agents system
A. C. Benabdellah (B) · I. Bouhaddou LM2I Laboratory ENSAM, Moulay Ismaïl University, Meknès, Morocco e-mail: [email protected] I. Bouhaddou e-mail: [email protected] A. Benghabrit LMAID Laboratory, ENSMR, Mohammed V University, Rabat, Morocco e-mail: [email protected] © Springer Nature Switzerland AG 2021 T. Masrour et al. (eds.), Artificial Intelligence and Industrial Applications, Advances in Intelligent Systems and Computing 1193, https://doi.org/10.1007/978-3-030-51186-9_8
103
104
A. C. Benabdellah et al.
1 Introduction Industries are engaging in constant performance enhancement activities in the current economic and industrial environment to remain competitive in their core business. In general, performance enhancement levers can concern (1) maximizing product efficiency and organizational design processes or (2) improving internal process efficiency or even (3) improving human performance by valorizing knowledge and competences. The first axis is well recognized and investigated by enterprises. It embeds methods and tools such as functional analysis, dependability, statistical process control or modelling and simulation. The second axis integrates, for instance, all the methodologies and tools of project management, agile methodologies, engineering system, or quality management systems. While the third one remain complex due to the intrinsic nature of the knowledge and its volatile dimension. In fact, the design of a new product in terms of cost, flexibility, assembly, quality, safety, serviceability and environmental issues has specific characteristics that directly affect how knowledge is performed. In addition, giving an outline of a project or recalling the collaborativ
Data Loading...
