Proposition of the methodology for data acquisition, analysis and visualization in support of industry 4.0

Industry 4.0 offers a comprehensive, interlinked, and holistic approach to manufacturing. It connects physical with digital and allows for better collaboration and access across departments, partners, vendors, product, and people. Consequently, it involves complex designing of highly specialized state of the art technologies. Thus, companies face formidable challenges in the adoption of these new technologies. In this paper, critical components of Industry 4.0, their significance and challenges as identified in the literature are presented. Furthermore, a test case framework for the implementation of Industry 4.0 is proposed. The system covers four layers: decision support, data processing, data acquisition and transmission and sensors. Condition monitoring data from machines and shop floor are captured, stored, organized and visualized in real time. Knowledge representation technique of SOEKS/DDNA is used for doing the semantic analysis of the data, Virtual Engineering Object (VEO), Virtual Engineering Process (VEP) and Virtual Engineering Factory (VEF) are used for creating virtual engineering objects, process and factory respectively, Python and its utility Bokeh is used for visualization. The proposed Industry 4.0 framework will make it possible to gather and analyze data across machines, processes and resources supporting faster, flexible, and more efficient control and production of higher-quality goods at reduced costs.