An integrated solution—KAGFM for mass customization in customer-oriented product design under cloud manufacturing environment

The global prosperous development of Internet has revolutionized the traditional business mode of manufacturing industry (e.g., the emergence of agile mass customization) as it ubiquitously provides the stable and high-speed Internet access for conveniently gathering huge quantities of raw data (e.g., personal information, product reviews, sales, and other context information) during the process that end-users enjoy their products and services. Thus, based on the outputs of deep processing of these data, manufacturing enterprises have the potential to respond rapidly to the changing customer needs and markets under the dynamic environment of multi-site design and cloud manufacturing, which is becoming a core competitiveness of enterprises. However, due to a large amount of data scattered in various distributed databases or clouds of enterprises has not yet been exploited effectively, this valuable competence gained from mass customization is still not practically available in the modern manufacturing industry. In order to provide a feasible treatment for mass customization in product design under cloud manufacturing environment, the three critical problems identified in this paper must be solved comprehensively. Thus, this research has proposed a novel integrated solution (named “KAGFM”) to realize effective mass customization for customer-oriented product design in an intelligent computerized manner based on big data mining, that is, manufacturing enterprises can adjust product design schemes keenly adapting with the specific requirements of a certain group of customers. By taking advantage of the cloud manufacturing, this solution can extract a set of fuzzy IF-THEN rules from huge quantities of raw data through integrating the artificial neural network (ANN), genetic algorithm (GA), and fuzzy rules seamlessly together to precisely extract and express semantic relationships between individual data sets (including personal attributes and preferences) and key product design elements. This paper tests and evaluates the proposed solution through a case study on mass customization for concept mobile phone design. Experimental results have showed that it can provide a better customized product design mode in context of cloud manufacturing through reducing data processing time, improving data utilization rate and facilitating enterprises to make a quick and correct response to changes of customer preferences.