As one of the core parts, the brake discs directly impact the braking and safety performance of vehicles. Traditional surface detection methods of the brake disc have poor robustness due to their reliance on manual fe...As one of the core parts, the brake discs directly impact the braking and safety performance of vehicles. Traditional surface detection methods of the brake disc have poor robustness due to their reliance on manual feature extraction. A detection instrument was designed to focus on the detection. The features were extracted using the improved Gaussian difference algorithm and Hough transform algorithm(IGD-IHT). An identification method for brake disc surface defects was designed in this paper based on the Perception-based Image Quality Evaluator and Dempster rule-improved sparrow search algorithm-Nonlinear echo state network(PIQEDS-ISSA-NESN) to better identify. It was shown in the experiment that the accuracy was more than 97%, the false alarm rate was less than 1.5%, and the false alarm rate was less than 1.5%.展开更多
基金bankrolled by the West Coast New Area University President Fund Special Project of Qingdao Technical College (Grant No.39100101)the National Key Research and Development Plan (Grant No.2017YFF0108100)+2 种基金the Basic Research Projects of Science,Education,and Industry Integration Pilot Project of the Qilu University of Technology (Shandong Academy of Sciences)(Grant No. 2023PX031)the Natural Science Foundation of Qingdao under Grants No. 23-2-1-121-zyyd-jchthe project ZR2023QE212 supported by Shandong Provincial Natural Science Foundation。
文摘As one of the core parts, the brake discs directly impact the braking and safety performance of vehicles. Traditional surface detection methods of the brake disc have poor robustness due to their reliance on manual feature extraction. A detection instrument was designed to focus on the detection. The features were extracted using the improved Gaussian difference algorithm and Hough transform algorithm(IGD-IHT). An identification method for brake disc surface defects was designed in this paper based on the Perception-based Image Quality Evaluator and Dempster rule-improved sparrow search algorithm-Nonlinear echo state network(PIQEDS-ISSA-NESN) to better identify. It was shown in the experiment that the accuracy was more than 97%, the false alarm rate was less than 1.5%, and the false alarm rate was less than 1.5%.
