Predictive maintenance closed-loop method based on fault mode

Abstract

The invention provides a predictive maintenance closed-loop method based on a fault mode, fault information and state monitoring information are precise to a fault mode level which serves as a node connecting predictive maintenance technology and reliability technology, and the predictive maintenance technology and the reliability technology are effectively combined to form a predictive maintenance closed-loop system. The formed predictive maintenance closed-loop system includes future event prediction through reliability retrospect, determining of the current state of equipment through state monitoring and a reliability and predictive maintenance closed loop. The steps of the future event prediction through reliability retrospect include collecting data; obtaining a fault mode of the equipment and parts thereof through data obtained in Step a; establishing a reliability model; utilizing the model in Step c to perform analog simulation; analyzing a result in Step d, and obtaining a shape function and expected life of each failure mode; using a result of Step e to guide implementation of predictive maintenance; and for different shape functions, driving different maintenance policies.

Description

technical field [0001] The invention relates to a method for maintaining equipment, in particular to a closed-loop method for predictive maintenance based on failure modes. Background technique [0002] The availability of equipment or systems (including rotating equipment, static equipment, actuators, and instrumentation equipment) is directly related to enterprise production and safety. [0003] The process of equipment maintenance includes three strategies: post-event maintenance, preventive maintenance, and predictive maintenance. Among them, predictive maintenance technology improves the ability to obtain equipment failure information, predicts the status trend of equipment, optimizes equipment maintenance management, and improves the availability of equipment. . [0004] Predictive maintenance technology pays attention to the failure mode of equipment and the fault characteristic parameters of equipment related to it. Based on the comparison between the trend change ...

AI Technical Summary

Problems solved by technology

This undoubtedly affects production and increases the workload of engineers

[0009] 2. There is a large amount of information based on the failure mode of equipment components in the maintenance history information, and the correlation degree of the parameters of the condition monitoring in the predictive maintenance system is not high;

[0010] In the use of equipment historical fault information, if only the historical fault information analysis at the equipment level is done, only the overall MTBF value of the equipment can be obtained, which is lack of pertinence

And when the condition monitoring results and the historical analysis of the equipment level are both at the equipment level, the two cannot be effectively connected, which will become a major obstacle in the construction of the predictive maintenance closed-loop system

[0011] 3. Predictive maintenance and maintenance history do not form a closed loop, state parameters and failure modes are not related, and the system does not have the ability to optimize and iterate:

[0012] From the perspective of the predictive maintenance system, the existing predictive maintenance is mainly in the stage of condition monitoring and fault diagnosis. The equipment condition monitoring information and historical maintenance records have not been organically integrated. As an analytical tool, it is not applied to forecasting

On the one hand, this causes a waste of information resources. On the other hand, there is no predictive maintenance combined with historical fault information, and a complete closed-loop system of predictive maintenance has not been formed. Its functions are limited to traditional condition monitoring and fault diagnosis, and cannot achieve status More powerful functions such as monitoring interval optimization and precise fault location

Images