Data-driven Model Development for Quality Prediction in Forming Technology

In this investigation data recorded from a flexible rolling process is processed by data driven methods to develop a quality prediction model for manufactured blanks. A concept for a incremental prediction method is proposed, which takes into account the specific character of the discrete manufacturing process. The method is evaluated based on a data set of process and quality data provided by a test rig. By the example of a specific quality parameter the effectiveness of the proposed method is confirmed. A precise quality prediction model is developed, which predicts the quality value with a high accuracy.     «

In this investigation data recorded from a flexible rolling process is processed by data driven methods to develop a quality prediction model for manufactured blanks. A concept for a incremental prediction method is proposed, which takes into account the specific character of the discrete manufacturing process. The method is evaluated based on a data set of process and quality data provided by a test rig. By the example of a specific quality parameter the effectiveness of the proposed method is...     »