Method for predicting residual life of rotary kiln main exhaust fan bearing based on membership degree

CN115901254BActive Publication Date: 2026-05-12ANSTEEL GROUP MINING CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ANSTEEL GROUP MINING CO LTD
Filing Date
2022-10-28
Publication Date
2026-05-12

AI Technical Summary

Technical Problem

Existing technologies make it difficult to accurately predict the remaining life of the rolling bearings of the main exhaust fan of the rotary kiln in pellet production, resulting in a high bearing failure rate and problems with untimely or premature replacement.

Method used

Wavelet packet decomposition technology is used to decompose the vibration and temperature signals into frequencies. Combined with kurtosis and margin factor analysis, fuzzy reasoning and evidence theory are used for fault classification. Fuzzy reasoning is performed through membership function and fuzzy rule base. Finally, the remaining life of the bearing is obtained by inverse fuzzy reasoning.

Benefits of technology

This improved the accuracy and real-time performance of rotary kiln main exhaust fan bearing fault diagnosis, reduced human error, and ensured the accuracy and reliability of bearing remaining life prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115901254B_ABST
    Figure CN115901254B_ABST
Patent Text Reader

Abstract

The application relates to a membership-based rotary kiln main exhaust fan bearing residual life prediction method, characterized in that a wavelet packet decomposition is adopted to divide the frequency of a vibration frequency signal, the efficiency of analyzing local frequency characteristics is improved, kurtosis and margin factors are adopted to represent the frequency characteristics of different frequency bands, and artificial experience errors are avoided; in the process of fuzzification, a combination mode of a triangular membership function and a trapezoidal membership function is selected, the continuity of a fault period on a domain is ensured, and the rationality of domain division is ensured; a hierarchical fuzzy reasoning mode is adopted, on one hand, the anti-interference capability of the system can be improved, and on the other hand, the prediction can be ensured to be carried out under reasonable working conditions, so that the accuracy is ensured; evidence theory is adopted to fuse the fuzzy reasoning results, the reliability of the prediction is improved; reverse fuzzy reasoning is adopted to convert the fault period information of the main exhaust fan bearing into specific residual life prediction information, so that the prediction results are more accurate and intuitive.
Need to check novelty before this filing date? Find Prior Art