PAVED: Pareto Front Visualization for Engineering Design

Abstract

Design problems in engineering typically involve a large solution space and several potentially conflicting criteria. Selecting a compromise solution is often supported by optimization algorithms that compute hundreds of Pareto‐optimal solutions, thus informing a decision by the engineer. However, the complexity of evaluating and comparing alternatives increases with the number of criteria that need to be considered at the same time. We present a design study on Pareto front visualization to support engineers in applying their expertise and subjective preferences for selection of the most‐preferred solution. We provide a characterization of data and tasks from the parametric design of electric motors. The requirements identified were the basis for our development of PAVED, an interactive parallel coordinates visualization for exploration of multi‐criteria alternatives. We reflect on our user‐centered design process that included iterative refinement with real data in close collaboration with a domain expert as well as a summative evaluation in the field. The results suggest a high usability of our visualization as part of a real‐world engineering design workflow. Our lessons learned can serve as guidance to future visualization developers targeting multi‐criteria optimization problems in engineering design or alternative domains.

Optimization of excess brines disposal methods at potash mining and processing plants

“…However, as a rule, the company solves not only the tasks of minimizing financial costs for disposal, but also a number of technical and technological tasks (ensuring the geomechanical stability of the mine field, ensuring the environmental friendliness of disposal processes, rational development of the subsoil) [25,26].…”

“…The additional way of brine utilization is membrane technologies. A huge number of foreign and domestic publications, both fundamental and applied works, are devoted to the description of membrane technologies [21,[24][25][26][27][28][29][30][31][32][33], describing in detail the nuances of the membrane behavior in various processes.…”

RfX: A Design Study for the Interactive Exploration of a Random Forest to Enhance Testing Procedures for Electrical Engines

“…Furthermore, our evaluation only involves five domain experts. This is a relatively common situation in design studies, where the presented visualizations often tackle very specific problems, which can be addressed by only a few experts [BSKR19, CMMK20, SIB*11, SFMB12, SMF*20]. A second limitation is that we only use a binary classifier.…”

“…Design studies in the automotive sector are mostly carried out for engineering design and anomaly detection. In the case of engineering design, efforts have been made to visualize in‐car communication networks [SIB*11, SFMB12] or the exploration of multi‐criteria alternatives for rotor designs [CMMK20]. Recent studies have been carried out making use of anomaly detection to detect error‐prone produced parts in test stations of large‐scale manufacturing processes [SMF*20, EJS*20].…”

Understanding How In-Visualization Provenance Can Support Trade-Off Analysis

“…Although trade-off analysis and provenance visualization are prominent areas of research, little work exists that looked at exploiting provenance information to specifically assist trade-off analysis. An exception is recent work by Cibulski et al [34], who developed an interactive Pareto front visualization tool to explore multi-criteria alternatives in engineering design. Since their focus is on trade-off analysis, they describe 13 design requirements for this domain, such as showing criteria ranges for simulation steering, supporting selections, and highlighting conflicting criteria; but they also describe one additional requirement for provenance pertaining to storing favorite alternatives for future comparison.…”