Answers are grounded in this paper and cite their sources.
For: Special Issue on Data-driven methods and applications of artificial intelligence in vibroacoustics In modern vehicle design processes, the demand for reliable and cost-efficient tools to predict noise, vibration, and harshness at an early stage in the automotive design cycle is constantly increasing. The ongoing development of computer hardware and increased capabilities in Machine Learning have led to a growing interest among automotive engineers to apply learning based techniques for acoustic design tasks. However, the correct application of such approximation tools to conduct early-stage predictions still requires a comprehensive knowledge of the engineer and is seldom straightforward. In this paper, the authors propose to utilize Artificial Neural Networks to predict narrowband sound pressure level spectra for the interior noise of a full vehicle system based on different steering-wheel movement conditions. Tri-axial acceleration measurements at the connector points of the steering system, on the electric drive, on the tie rods, and close to the steering column serve as input for the calculations. Different hyperparameter sets have been automatically analyzed to prove the robustness and versatility of the framework for the acoustic engineer. The results show promising prediction qualities in the frame of an early-stage design process. The proposed Machine Learning approach targets cost-efficiency in model generation and convenient application to enable industrial usability.
No takes yet. Share an insight, caveat, or question.
Tsokaktsidis et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: