Image Mining for Real Time Fault Detection within the Smart Factory

Abstract

Quality management in real time enables increased efficiency of a production process. A multitude of sensors make it possible to collect a large amount of data and builds the basis for a real time fault detection in the Smart Factory. Hence, it is important that this data, the resulting information, and the knowledge generated by the algorithmic analysis is available at the right time. Therefore, appropriate network architectures such as Edge Computing are required for efficient data transfer. In this context, the paper deals with the challenges of analyzing data gathered by an image sensor in production. The consideration is based on the implementation of an Im-age-Mining-Application for real time error detection in production, which was developed by a design science research approach. In addition to identifying the challenges in this area, algorithms with a high accuracy of fit could be identified. Thus, the results obtained form an important basis for the use of Image-Mining-Applications in Smart Factories.