By Bruce Jenkins, President, Ora Research
Simulation-based design exploration and optimization studies often produce large data sets for which it is useful to have software tools for post-processing the data—and presenting it in ways that facilitate visual discernment of patterns and trends in the data. Visual data mining and analytics tools allow plots and tables to be viewed, queried and operated on to better understand the design space, explore design sensitivities, visualize correlations and investigate tradeoffs. Many design space exploration and design optimization software products include these capabilities to a greater or lesser degree, as do most mainstream CAE product lines. At the same time, some of the best regarded technology comes from developers focused exclusively on this area.
One highly capable example is Tecplot Chorus from Tecplot Inc., which lets engineers and analysts explore design spaces in a unified environment that includes integrated CFD post-processing, field and metadata management, and an analytics tool. The software is designed to help users manage and analyze collections of CFD simulations, evaluating overall system performance by visually comparing tens or thousands of simulation cases in a single view. Customer use cases include design studies to modify the wake behind Formula racing cars to make passing easier, airframe design and optimization for a supersonic UAV, and others.
The company terms Chorus a “simulation analytics” tool that provides a framework for managing CFD projects requiring multiple simulation cases with tools to evaluate the resulting metadata. Tecplot usefully describes simulation analytics as “the application of visualization, data management, statistics, and data mining to related collections of datasets generated by computer-aided engineering (CAE) codes. In particular, simulation analytics involves the coupled analysis of the detailed field data and the associated meta-data for a related collection of datasets.”
Another respected product with a long history in this area is EnSight from CEI (Computational Engineering International) Inc., for visualizing, analyzing and communicating data from computer simulations and/or experiments. EnSight is used for CSM (computational structural mechanics such as FEA and crash), CFD and other CAE processes in automotive, aerospace, defense, combustion, energy production, high-tech manufacturing and other markets that require very high precision in computer-based physics modeling.
A recent, innovative entry is LIONsolver from LIONlab and Reactive Search srl. An integrated software package for data mining, business intelligence, analytics and modeling, LIONsolver originated from the founders’ research into “reactive search optimization” using self-tuning search schemes. Designed to let users build and visualize models to improve engineering and business processes, the software aids and enables decision-making based on data and quantitative models. Its architecture supports interactive multi-objective optimization, with a user interface for visualizing results and facilitating the solution analysis and decision-making process.
LION (for “machine Learning and Intelligent OptimizatioN”) Laboratory says its mission is to “foster research and development in intelligent optimization and reactive search optimization (RSO) techniques for solving relevant problems arising in different application areas, including marketing automation and e-commerce, telecommunication networks, ICT, mobile services, big data, cost management, social networks, clustering and pattern recognition in bio-informatics.” LIONoso is a version of the software available for nonprofit research and academic use.