Reduction of tire noise by modifying tread pattern characteristics

The complexity of tire/road noise generation and amplification mechanisms has made it challenging for tire builders to reduce emitted sound. Statistical methods help to model complex problems. This paper predicts tire noise level by a superior regression method in machine learning, relevance vector machine, with a total noise prediction error of 0.62 dB(A). The tire’s noise sensitivity to its parameters is analyzed by applying a small central composite design to the developed model. The effect of grooves’ shapes on tire noise is preserved in the results, unlike the previous publications. For a case study, grooves’ depth has been recognized as critical in controlling tire noise. Based on the variance analysis results, the interaction of this parameter with the number, length, and width of transverse grooves has also been identified as significant. According to the parametric study’s striking tips, two sets of tread pattern specifications are proposed for noise reduction, utilizing the response surface method. They reduce the noise level by 1.72 and 1.54 dB(A) for a tire with a measured noise of 75.88 dB(A)