A neural network approach for the development of modular product architectures
| Autor: | John Pandremenos, George Chryssolouris |
|---|---|
| Přispěvatelé: | Laboratory for Manufacturing Systems and Automation, University of Patras [Greece] |
| Jazyk: | angličtina |
| Rok vydání: | 2011 |
| Předmět: |
Structure (mathematical logic)
0209 industrial biotechnology Artificial neural network business.industry Computer science Mechanical Engineering Aerospace Engineering 02 engineering and technology Modular design computer.software_genre Computer Science Applications [SPI]Engineering Sciences [physics] 020901 industrial engineering & automation Development (topology) Product (mathematics) Physical Sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Data mining Electrical and Electronic Engineering business Cluster analysis computer Modular product |
| Zdroj: | International Journal of Computer Integrated Manufacturing International Journal of Computer Integrated Manufacturing, Taylor & Francis, 2011, ⟨10.1080/0951192X.2011.602361⟩ |
| ISSN: | 0951-192X 1362-3052 |
| Popis: | International audience; The clustering of a product's components into modules is an effective means of creating modular architectures. This paper initially links the clustering efficiency with the interactions of a product's components and interesting observations are extracted. A novel clustering method utilizing Neural Network algorithms and Design Structure Matrices (DSMs) is then introduced. The method is capable of reorganizing the components of a product in clusters, in order for the interactions to be maximized inside and minimized outside the clusters. Additionally, a multi-criteria decision making approach is used, in order for the efficiency of the different clustering alternatives, derived by the network, to be evaluated. Finally, a case study is presented to demonstrate and assess the application of the method. The derived algorithmic clustering proved to be more efficient compared with the empirical one and thus, it can be used by design engineers as an effective tool for the derivation of product clustering alternatives. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|