Rolling bearing is a very important mechanical part and extensively applied in mechanical equipment. It provides stable support and rotation accuracy for the rotor in rotating machines. The health of rolling bearing is essential to guarantee the reliable operation of the entire rotating machines. In this paper, a vision-based data-driven method of fault diagnosis for rolling bearings in rotating machinery is proposed. Firstly, the displacement information under different fault states is acquired from the obtained vibration images, and its frequency-domain feature can be obtained after fast Fourier transform. Secondly, a linear model is established to obtain a mapping function that can reflect the correspondence between vibration characteristics and fault types. Thirdly, fault diagnosis can be realized based on the vibration data under different fault states and acquired mapping function. Finally, the experimental results prove that the method presented in this article can achieve rolling bearing fault diagnosis with relatively high correct rate.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Vision-Based Data-Driven Method of Fault Diagnosis for Rolling Bearings in Rotating Machinery


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Yan, Liang (editor) / Duan, Haibin (editor) / Yu, Xiang (editor) / Liu, Bin (author) / Peng, Cong (author) / Zhu, Mengting (author)


    Publication date :

    2021-10-30


    Size :

    11 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English





    Rolling bearings in shipbuilding and ship-machinery construction

    Muller-Rentzsch | Engineering Index Backfile | 1924



    Rolling Bearings Fault Diagnosis Method Based on EWT Approximate Entropy and FCM Clustering

    Bai, Lin / Zhu, ChunLin / Ye, Zhen et al. | Springer Verlag | 2020


    Rolling Bearings Fault Diagnosis Method Based on EWT Approximate Entropy and FCM Clustering

    Bai, Lin / Zhu, ChunLin / Ye, Zhen et al. | British Library Conference Proceedings | 2020