An artificial neural network (ANN) approach to model Tire-Pavement interaction noise (TPIN) based on tire noise separation

Abstract

Tire-pavement interaction is a dominant noise source for passenger cars and trucks above 25 mph (40 km/h) and 43 mph (70 km/h), respectively. For the same pavement, tires with different tread patterns and constructions generate noise of different levels and frequencies. An analogous trend is observed when the same tire rolls on different pavement surfaces. Based on substantial experimental data collected for tire noise and pavement profile, two artificial neural networks (ANN) were developed to predict the tread pattern (ANNTPN) and the non-tread pattern related noise (ANNNTPN) components of tire noise, separately. The major inputs of ANNTPN are the coherent tread profile spectrum and the air volume velocity spectrum calculated from the digitized 3D tread pattern. The major input of ANNNTPN is the tread rubber hardness. The vehicle speed is also included as input for the two ANNs. Furthermore, parameters such as tire size and the two-dimensional pavement profile are used as inputs to predict non-tread pattern related noise for different tire sizes and pavement surfaces. The experimental data used to train and test these ANNs include tire noise collected for thirty-seven different tires tested over a range of speeds (45–65 mph, i.e., 72–105 km/h) on a non-porous asphalt pavement. Additionally, five tires out of the thirty-seven were tested on twenty-six different pavement surfaces (Virginia Tech Transportation Institute SMART Road). Moreover, pavement profile data was obtained at both testing sites. Finally, the once-per-revolution signal of the wheel was recorded and employed to monitor the vehicle speed and, more importantly, to perform the order tracking analysis. This is to break down the tire noise into the tread and non-tread pattern related noise components (denoted as TPN and NTPN, respectively). The optimized ANNs are able to predict the tire-pavement interaction noise well for different tires on different non-porous pavement surfaces tested.