Sound Quality Evaluation on Noise Caused by Electric Power Steering Wheel Utilizing CNN based on Sound Metrics 2024-01-2963

This research aims presents the method classifying the noise source and evaluating the sound quality of the noise caused by operating of electric power steering wheel in an electric vehicle. The steering wheel has been operated by the motor drive by electric power and it called motor-driven electric power (MDPS) system. If the motor is attached to the steering column of the steering device, it is called C-MDPS system. The steering device of the C-MDPS system comprises of motor, bearings, steering column, steering wheel and worm shaft. Among these components the motor and bearings are main noise sources of C-MDPS system. When the steering wheel is operated in an electric vehicle, the operating noise of the steering device inside the vehicle is more annoying than that in a gasoline engine vehicle since the operating noise is not masked by engine noise. Defects in the C-MDPS system worsen the operating noise of the steering system. In the paper, the method classifying defect source of the C-MDPS system is developed and a sound quality index evaluating the sound quality of operating noise of the steering system is proposed. The classification of defection and the sound quality index are developed based on artificial neural network (ANN). The convolutional neural network (CNN) is used for the classification of defections and the images of sound metric for the noise data measured from R-MDPS system are the input data of CNN. The shallow neural network (SNN) for the production of sound quality index is used and the sound metrics correlated to the subjective rating of measured noise data are input vectors of the SNN since these metrics represents the features of sound quality.