Design of electric powertrains to achieve NVH performance using autoencoders and a physical meaningful latent space

作     者：Ricardo Souza, Marcos Offner, Guenter Soltoggio, Andrea Mohammadpour, Mahdi Theodossiades, Stephanos 

作者机构：Wolfson School of Mechanical Electrical and Manufacturing Engineering Loughborough University Loughborough United Kingdom AVL List GmbH Graz Austria Computer Science Department School of Science Loughborough University Loughborough United Kingdom 

出 版 物：《Neural Computing and Applications》 (Neural Comput. Appl.)

年 卷 期：2025年第37卷第16期

页      面：1-22页

核心收录：

学科分类：0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 070206[理学-声学] 0701[理学-数学] 0702[理学-物理学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The authors would like to express their gratitude to the Engineering and Physical Sciences Research Council (EPSRC) for the financial support extended to the \u201CAutomotive electric powertrain whistling and whining: fundamental root cause analysis to novel solutions\u201D [Grant No. EP/V053353/1]. We would also to thank AVL List GmbH and Arrival Ltd. for their technical support and the Loughborough University Lovelace High-Performance Computing Service 

主　　题：Internal combustion engines 

摘      要：One of the fundamental differences in the perception of electric (e-) vehicles is how their radiated noise is perceived with respect to classic internal combustion engines. Even though e-vehicles are usually quieter, the tonal content of the radiated noise can be more annoying. This paper proposes a novel approach that starts from the assumed radiated noise spectrum profile as input to a neural network that can return powertrain design parameters that would lead to generation of that specific noise profile. The proposed network acts as an autoencoder where the latent space is forced to have a physical meaning. As diverse combinations of powertrain parameters can result in similar noise profiles, a variational autoencoder is used to learn a structured latent representation, ensuring continuity and smooth transitions between possible solutions. The network predictions are validated against results of a three-dimensional CAE e-powertrain model. Overall, the mean absolute error is around 5 dBA for this feasibility study, which aims to demonstrate the concept. This work takes an inverse approach to the optimisation problem by starting from the user-perceived noise to predict the parameters required to achieve that. Although this study focuses solely on gear teeth microgeometry changes and bearing preloads, additional powertrain parameters could be incorporated as needed. © The Author(s) 2025.