Base types selection of PSS based on a priori algorithm and knowledge‐based ANN. Issue 2 (25th April 2019)

• Record Type: Journal Article
• Authors: Zhang, Zaifang; Chai, Nana; Liu, Yuan; Xia, Beixin
• Is Part Of: IET collaborative intelligent manufacturing. Volume 1:Issue 2(2019)
• Page Start: 29
• Page End: 38
• Publication Date: 2019-04-25
• Subjects: customer services -- neural nets -- computerised numerical control -- machine tools -- production engineering computing -- learning (artificial intelligence) -- product customisation; product service system -- configuration design -- PSS development -- selecting -- combining appropriate product -- individual customer requirements -- customer requirement attributes -- PSS base type -- CNC machine tools -- a priori algorithm -- knowledge‐based artificial neural network -- historical configuration instance data sets -- domain knowledge -- knowledge‐based ANN -- base types selection -- related services; Production management -- Periodicals; Production engineering -- Periodicals; Production management; Production engineering; Electronic journals; Periodicals; 658.5
• DOI: 10.1049/iet-cim.2018.0003
• Languages: English
• ISSNs: 2516-8398

Abstract

Abstract : Manufacturers tend to bundle a product with its related services as a product service system (PSS), to create more values for customers and gain competitive advantages for themselves. Configuration design is the key process of PSS development. Configuring a PSS involves selecting and combining appropriate product and service components, to satisfy individual customer requirements. This study studies the mapping relationship between customer requirement attributes and PSS base types in PSS for CNC machine tools, which provides a great reference value for engineers in configuration design. Owing to the high complexity and non‐linearity between customer requirement and product, an integrated intelligent learning method based on a priori algorithm and knowledge‐based artificial neural network (ANN) is proposed in this study. First, the data of historical configuration instance data sets are processed and then a priori algorithm is used to extract the effective rules as domain knowledge. Domain knowledge is used to build the initial structure of ANN. Moreover, data sets are used to further optimize the network. The knowledge‐based ANN is used to realize the mapping between customer requirement attributes and PSS base types. The proposed method is validated in the selection of the PSS base type for CNC machine tools.