Motor rotor fault diagnosis method based on neutrosophic set

Abstract

The invention discloses a motor rotor fault diagnosis method based on a neutrosophic set. The method comprises the following steps: 1, establishing a fault library Gaussian model according to a motorrotor fault sample data set; 2, establishing a Gaussian test model of a test sample detected by a sensor; 3, generating a neutrosophic set representation on each fault feature under each fault type according to matching of a fault library Gaussian model and a test sample Gaussian model; 4, fusing the neutrosophic set representation on each fault feature under each fault type by using an SNWA operator; 5, judging the fault type of the test sample according to the fusion result in the step 4. According to the invention, on the basis of a Gaussian model; in combination with the advantages of processing uncertainty and fuzzy information of a neutrosophic set theory, a Gaussian test model and a fault library Gaussian model are matched to generate neutrosophic set representation on each fault feature under each fault type, and the neutrosophic set representation is fused, so the fault type of a test sample is identified, the uncertainty information can be flexibly and effectively processed,and the fault diagnosis accuracy is improved through fusion.

Description

technical field [0001] The invention belongs to the field of fault diagnosis, and in particular relates to a method for diagnosing faults of motor rotors based on Zhongzhiji. Background technique [0002] The motor rotor is the rotating part in the motor. Due to the difficulty of commutation and high speed, it is often prone to failure, which reduces the life of the motor. The safety of the motor rotor is a crucial issue. Timely fault diagnosis of the motor rotor can effectively detect its operating status and avoid safety accidents. [0003] Fault diagnosis mainly studies how to effectively identify and locate the motor running state and fault type. Existing fault diagnosis methods include model-based methods, signal-processing-based methods, data-driven methods, and knowledge-based methods. As electrical equipment tends to become more complex and larger, the randomness and ambiguity of fault information collected by sensors should also be taken into account. In addition...

AI Technical Summary

Problems solved by technology

In addition, due to factors such as environmental noise, system noise, and measurement errors, fault information is generally uncertain or even conflicting, which may lead to large errors in fault diagnosis results.

Images