PREVIS -- A Combined Machine Learning and Visual Interpolation Approach for Interactive Reverse Engineering in Assembly Quality Control

TL;DR

PREVIS is a visual analytics tool that combines machine learning and visual interpolation to improve reverse engineering and quality control in engineering, enabling real-time parameter adjustments and impact visualization.

Contribution

It introduces a novel toolchain integrating model comparison, error impact visualization, and real-time visual interpolation for interactive engineering analysis.

Findings

Effective in automotive engine hood optimization

Enables real-time interactive parameter adjustments

Improves understanding of regression errors in geometry analysis

Abstract

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.