Knowledge Discovery in Engineering Applications Using Machine Learning Techniques

Abstract

Abstract Sensorial acquired process data combined with machine learning (ML) algorithms are fundamental for mastering the challenges of modern production systems, however, their potential is rarely exploited in real-world manufacturing applications. In this context, the literature presents systematic procedure models to generate knowledge from data, such as the cross industry standard process for data mining (CRISP-DM) model, which is used as a standard methodology for conducting data mining in industrial applications. However, these models do not take into account boundary conditions of manufacturing processes as well as the characteristics of the sensorial acquired data within these systems to generate knowledge. Therefore, this work presents a novel procedure model for knowledge discovery in time series and image data in engineering applications (KDT-EA). A holistic view of knowledge discovery in manufacturing processes becomes feasible with a strong focus on data acquisition, data preprocessing, and data transformation to generate reliable input data for ML models estimating the actual state of manufacturing processes. The process model supports operators in industry setting up a suitable measurement chain acquiring high-quality data and selecting preparation techniques depending on superimposed disturbances. Furthermore, it suggests data transformation techniques reducing the amount of data without losing informational value and establishing a basis for product-related inline monitoring. To quantify the benefits of KDT-EA and the impact of its phase on the quality of the generated knowledge, the novel procedure model is applied to an application in the field of inline wear detection on a sheet metal forming tool.