Prediction of tire pattern noise in early design stage based on convolutional neural network. (15th January 2021)

• Record Type: Journal Article
• Authors: Lee, Sang-Kwon; Lee, Hwajin; Back, Jiseon; An, Kanghyun; Yoon, Youngsam; Yum, Kiho; kim, Sungdae; Hwang, Sung-Uk
• Is Part Of: Applied acoustics. Volume 172(2021)
• Publication Date: 2021-01-15
• Subjects: Artificial neural network -- Convolutional neural network -- Tire pattern noise prediction -- RMSprop algorithm -- 2D wavelet transform -- Tire noise prediction; Acoustical engineering -- Periodicals; Periodicals; 620.2
• DOI: 10.1016/j.apacoust.2020.107617
• Languages: English
• ISSNs: 0003-682X

Abstract

Highlights: A novel convolutional neural network (CNN) model for predicting tire pattern noise. Two learning algorithms, i.e., stochastic gradient descent (SGD) and RMSProp were studied in the CNN model for the comparison of their learning performance. Then, the RMSProp algorithm was selected for the CNN model. A two-dimensional wavelet transform was proposed for the compression of tire image data, which were then used as inputs of the CNN model. An artificial neural network (ANN) model was proposed for predicting the pattern noise in the development stage, and its utility was compared with that of the CNN model. Pattern noises for 28 tires were measured in an anechoic chamber and used for the training of the ANN and CNN. Abstract: In early design stage of tire pattern, it is very useful to predict noise level associated with tire pattern. Artificial neural network (ANN) was used for development of the model for the prediction of tire pattern noise recently. The ANN used supervised training method which extracts the feature applying Gaussian curve fitting to the tread profile spectrum of tire pattern and used it as the input of ANN. This method requests laser scanning for tire pattern of a real tire. In early design, there is no real tire. In this study, the convolutional neural network (CNN) to predict tire pattern noise was developed based on non-supervised training method. Two Learning algorithms such as stochastic gradient descent (SGD) and RMSProp were studied in the CNN model for the comparison of their learning performance. RMSProp algorithm was suggested for the CNN model. In this case, a pattern image of a tire to be designed was used as the input of CNN. The CNN to predict tire pattern noise was developed and its utility in the early design stage of tire was discussed. In the study, pattern noise for 28 tires were measured in the semi- anechoic chamber and their pattern images were scanned. For the training of ANN and CNN, pattern noise for 24 tires and their pattern images were used. The trained ANN and CNN were validated respectively with 4 tires which were not used for the training of two neural networks. Finally, two networks were successfully developed and validated for the prediction of tire pattern noise. The trained CNN can be used for the prediction of pattern noise for a tire to be designed in early design stage using the only drawing image of tire whilst ANN can be used for the prediction of pattern noise for a real tire in development stage.