Sound Quality Evaluation on Noise Caused by Electric Power Steering Wheel Utilizing Convolutional Neural Network based on Sound Metrics

Abstract

<div class="section abstract"><div class="htmlview paragraph">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 steering (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. Abnormal operation of the steering device worse the operating noise of the steering system. In the paper, the method classifying noise source of the steering device is developed and a sound quality index (SQI) evaluating the sound quality of operating noise of the steering system is proposed. The sound quality index is developed based on multiple regression model. The convolutional neural network (CNN) is used for the classification of labels of noise source. Images of specific loudness for the noise data measured from steering device is used for input data of CNN. 207 operational noise signals are measured in the anechoic chamber and recorded. Labels of these noise signal are used for the target of CNN. Images of specific loudness of these noise signals is used for the input of CNN.</div></div>