High-Fidelity NVH Model Development for Electric Motors Using Deep Learning and Machine Learning Algorithms

<div class="section abstract"><div class="htmlview paragraph">Electric motor whine is a significant source of noise in electric vehicles (EVs). To improve the noise, vibration, and harshness (NVH) performance of electric propulsion systems, it is essential to develop a physics-based, high-fidelity stator model. In this study, a machine learning (ML) model is developed using an artificial neural network (ANN) method to accurately characterize the material properties of the copper winding, varnish, and orthotropic stator laminate structure. A design of experiments (DOE) approach using Latin hypercube sampling of parameters is implemented after evaluating alternative surrogate models. A finite element (FE) model is constructed using the nominal stator design parameters to train the ANN model using 121 DOE variables and 72,000 data points. The ML-trained ANN model is then verified to predict the driving point frequency response function (FRF) spectrum with reasonable accuracy. Subsequently, modal tests are conducted on the electric stator, and the acquired driving-point FRF data are employed to train the ANN model. A machine learning algorithm is used, following an evaluation of suitable optimization techniques to identify the optimal stator design parameters that minimize the discrepancy between the predicted and measured FRF data across a broad frequency range, extending up to 6 kHz. The ML-trained meta model shows promise for developing a generative AI model for future quiet electric drive systems. A good correlation is observed at critical motor orders, thereby validating the accuracy of the proposed NVH analysis method. The ML-trained meta-model demonstrates potential for the development of a generative AI model for future quiet electric drive systems.</div></div>