Simulation-driven product development involves numerous computer aided engineering (CAE) model iterations, where each version represents a critical difference. Usually, these multiple model versions are generated by hundreds of simulation engineers working in teams distributed across the globe, making functional collaboration a key to effective product development. To manage vast amounts of CAE data generated by engineers working simultaneously on a project, it is imperative to have a robust version management system to track changes in the CAE data. A robust version management is the backbone of an effective simulation data management (SDM) system. It involves capturing and documenting model changes at every design iteration. Accurate documentation of the model changes is crucial as it helps in understanding the model evolution and collaboration among engineers. However, documenting is usually considered a boring and tedious task by many engineers. This often leads to bad change documentation, which in turn reduces data discoverability and causes knowledge loss. With the onset of artificial intelligence (AI) in engineering simulations, engineers can now learn even more from their simulation data. In this paper, authors have explored an AI-assisted approach for facilitating the change documentation by augmenting the change comments via automatically extracted details, as studied in the SAFECAR-ML research project. The project is funded by the German Federal Ministry of Education and Research (BMBF) under the “KI4KMU” initiative (Research, Development, and Use of AI Methods in SMEs). The main goal of SAFECAR-ML is to develop an AI model that understands the nature of design changes and automatically generates change descriptions. When a detailed and informative change documentation is available, large language model (LLM)-based generative AI can be used for discovering and creating simulation-related content in an SDM system, for example by using retrieval augmented generation (RAG) approaches.
A long-term outlook is to build an AI-assisted capability to perform complex tasks in an SDM system, like search and summarization of the data, automatic evaluation of simulation results, and thinking models for researching the available simulation data making recommendations on further model changes.