Towards a Comprehensive Data Processing Platform

Abstract

For production line level analysis such as bottleneck analysis, distributed manufacturing data must be integrated and cleansed according to domain knowledge. As a result, these data are normally analysed by experts, and could be time-consuming. Although many methods have been proposed to support such progress, there is still no system designed for users without detailed domain knowledge. Hence, we develop a comprehensive data processing platform automatically integrating and cleansing raw manufacturing data according to analysis context specified by user. By applying our proposal to different scenarios and products in a real-life automotive parts factory, we illustrate that the platform can be used by anyone with basic knowledge about target product. As a result, various forms of value can be extracted by even ordinary workers.