PREVIS -- A Combined Machine Learning and Visual Interpolation Approach for Interactive Reverse Engineering in Assembly Quality Control
This tool addresses the need for fast and accountable online change management in assembly quality control, particularly for automotive engineering, but it is incremental as it builds on existing interpolation methods.
The authors tackled the problem of analyzing machine learning regression models in engineering by developing PREVIS, a visual analytics tool that enables direct model comparison and visualizes regression errors on part geometry, demonstrating its effectiveness with an ex-ante optimization of an automotive engine hood.
We present PREVIS, a visual analytics tool, enhancing machine learning performance analysis in engineering applications. The presented toolchain allows for a direct comparison of regression models. In addition, we provide a methodology to visualize the impact of regression errors on the underlying field of interest in the original domain, the part geometry, via exploiting standard interpolation methods. Further, we allow a real-time preview of user-driven parameter changes in the displacement field via visual interpolation. This allows for fast and accountable online change management. We demonstrate the effectiveness with an ex-ante optimization of an automotive engine hood.