An Artificial Neural Network Model to Predict Tread Pattern-Related Tire Noise

Paper #:
  • 2017-01-1904

Published:
  • 2017-06-05
Abstract:
Tire-pavement interaction noise (TPIN) is a dominant source for passenger cars and trucks above 40 km/h and 70 km/h, respectively. TPIN is mainly generated from the interaction between the tire and the pavement. In this paper, twenty-two tires of the same size (16 in. radius) but with different tread patterns were tested on a non-porous asphalt pavement. For each tire, the noise data were collected using an on-board sound intensity (OBSI) system at five speeds in the range from 45 to 65 mph. The OBSI system used an optical sensor to record a once-per-revolution signal to monitor the vehicle speed. This signal was also used to perform order tracking analysis to break down the total tire noise into two components: tread pattern-related noise and non-tread pattern-related noise. The spatial tread pattern profile of each tire was digitized and quantified using two spectral parameters: the tread profile spectrum characterizing the tread impact mechanism and the air volume velocity spectrum characterizing the air pumping mechanism. The two tread pattern spectra were correlated with the tread pattern-related noise spectrum using an artificial neural network (ANN) model. Multiple ANN model configurations were investigated. The experimental validation shows that the best ANN model is able to predict the tread pattern-related noise very well for typical tire tread patterns of the tire size investigated at normal highway speeds.
Access
Now
SAE MOBILUS Subscriber? You may already have access.
Buy
Attention: This item is not yet published. Pre-Order to be notified, via email, when it becomes available.
Select
Price
List
Download
$27.00
Mail
$27.00
Members save up to 40% off list price.
Share
HTML for Linking to Page
Page URL

Related Items

Training / Education
2017-09-28
Training / Education
2017-07-17
Training / Education
2017-08-01
Technical Paper / Journal Article
2003-11-10
Technical Paper / Journal Article
2003-10-19
Training / Education
2017-08-15