Motor equipment health management method based on fuzzy association rule algorithm

Abstract

The invention relates to a case-based reasoning motor equipment health management technology based on a fuzzy association rule algorithm. The method comprises the following steps: (1) acquiring a large number of motor fault cases, and processing the motor fault cases to form a fault case library; and (2) for the case library, a feature attribute reduction model based on a fuzzy association rule algorithm is established, the number of feature attributes is reduced, and the case reasoning time is shortened. And (3) weighting residual feature attributes after reduction by using an entropy weight algorithm, so as to further improve the calculation precision. And (4) determining a case most similar to the target case by applying a case reasoning technology, and solving a current fault problem by applying a solution of the most similar case.

Description

technical field [0001] The invention belongs to the field of electrical equipment health management, in particular to a method for electrical equipment health management based on a fuzzy association rule algorithm. Background technique [0002] Motor equipment is indispensable as the power source of mechanical equipment in most enterprises. If the motor fails, it will directly affect the overall operation of the enterprise. During the working process of the motor, with the increase of the service life, the probability of equipment failure or failure will increase accordingly, and there are many parts of the motor equipment, the causes of failure are diverse, and the maintenance is too difficult. Once the maintenance time is too long, it will Bring huge economic loss and delay of work progress. In the health management of electrical equipment, it is extremely important to make accurate judgments on fault analysis and improve the efficiency of its maintenance. [0003] At t...

AI Technical Summary

Problems solved by technology

However, the existing research is based on the connection between signal feature processing and fault diagnosis, which has certain limitations and the detection is not comprehensive enough.

Moreover, for enterprises, there are a large number of input and output variables, and there are highly similar relationships between variables, which increases the difficulty of data information extraction

At the same time, the traditional health management technology of electrical equipment cannot clearly give the causal relationship between the fault phenomenon, fault cause and solution, and people's subjective thinking in fault diagnosis will affect the maintenance process and fault diagnosis basis; therefore, with the enterprise's With the development and the increasing number of motors used, enterprises have accumulated a large number of fault cases and data. How to use historical fault case data to improve the accuracy and efficiency of fault diagnosis has become a technical problem that this field has been eager to solve.

[0004] As a new problem-solving method, case-based reasoning technology can analyze the characteristic attributes of new problems, and extract historical cases that are similar to new cases by establishing a case library. The troubleshooting measures of historical cases can be used as a reference for maintenance personnel. However, in the process of implementation, there are still some problems

The specific manifestation is: the current case reasoning technology assigns different feature attributes to the same weight for calculation, resulting in low accuracy of reasoning results

In actual performance, the importance of different feature attributes to cases is different, and the reasoning results at this stage are relatively one-sided, failing to provide operators with optimal solutions

Images