Study on the explainability of deep learning models for time series analysis in sheet metal forming

Procedia CIRP, vol. 126, pp. 727–732

Abstract

In recent research, force signals have been utilized to estimate the wear of tool components in sheet metal processing using, e.g., artificial neural networks (ANNs). ANNs learn predictive models from raw time series signals without requiring prior knowledge and manual feature engineering. However, ANNs are black-box models. Existing research on explainable AI provides methods to increase the transparency of ANNs, but mainly focusses on computer vision problems. This publication proposes an approach to learn explainable ANNs for time series data. The presented approach is applied to a tool wear prediction task using force signals from a fine blanking machine.

Authors 3

1. Marco Becker corresponding Aachen Laboratory for Machine Tools and Production Engineering (WZL)

   RWTH Aachen University

   Affiliation as printed

   Laboratory for Machine Tools and Production Engineering (WZL), RWTH Aachen University, 52074 Aachen, Germany

2. Philipp Niemietz Aachen Laboratory for Machine Tools and Production Engineering (WZL)

   RWTH Aachen University

   Affiliation as printed

   Laboratory for Machine Tools and Production Engineering (WZL), RWTH Aachen University, 52074 Aachen, Germany

3. Thomas Bergs Aachen Fraunhofer Institute for Production Technology Laboratory for Machine Tools and Production Engineering (WZL)

   RWTH Aachen University · Fraunhofer Institute for Production Technology IPT

   Affiliation as printed

   Fraunhofer Institute for Production Technology, 52074 Aachen, Germany

   Laboratory for Machine Tools and Production Engineering (WZL), RWTH Aachen University, 52074 Aachen, Germany