The vibro-acoustic performance of a vehicle is a critical factor in customer perception of quality and comfort. Optimizing for Noise, Vibration, and Harshness (NVH), particularly road noise, presents a persistent challenge in the automotive development cycle. While modern FEM analysis is essential, the increasing complexity and sheer volume of CAE simulation data often overwhelm manual interpretation, potentially leading to prolonged development times or sacrifices in resulting comfort quality.
To address these challenges, this paper introduces the application of CDH/ACE (Autonomous Computational Experiments), a framework that combines conventional CAE simulation workflows with machine learning in an iterative cyclic process. This creates a self-learning and self-correcting system that autonomously defines, performs, and learns from computational experiments. By building predictive models from simulation data, the framework intelligently guides the design exploration to achieve predefined engineering objectives. Typical areas of application range from conducting design of experiments, performing design optimization up to robustness and tolerance analysis.
We explain the underlying ideas and demonstrate this methodology through a full-vehicle road noise optimization study, detailing the process of defining design parameters, configuring acoustic targets, and initiating the autonomous learning cycle. The results highlight the effectiveness and user-friendliness of the workflow, showing a significant reduction in road noise, the identification of key design parameters influencing acoustic performance, as well as the highly automated nature of the overall process.
The paper presents the tangible benefits of this approach, including improved NVH performance at a lower mass and reduced manual engineering effort. Finally, the current advantages and limitations of the concept will be assessed and an outlook is provided on future applications of this autonomous methodology in modern vehicle development.