Abstract
To mitigate the safety risks and economic losses caused by wheel damage, this paper proposes an interval valued fuzzy inference-based sound analysis method for wheel damage detection. Firstly, interval valued fuzzy sets are defined to represent various levels of damage severity. A similarity calculation method is then designed, based on the defined interval valued fuzzy sets, to assess the damage level of wheel components. Moreover, the OWA operator is employed to assign higher weights to key features while reducing the influence of noise or redundant features. Finally, a double-threshold interval valued fuzzy inference approach is proposed for comprehensive decision-making regarding the wheel damage degree. The proposed method is applied to wheel damage sound analysis, and a corresponding detection system is developed. Experimental results demonstrate that the proposed method outperforms existing techniques in detection accuracy, response speed, and robustness, and it is adaptable to various wheel operating environments.