Rotor Misalignment State Identification Method Based on Improved d-s Evidence Fusion

Abstract

The invention relates to a rotor misalignment state recognition method based on improved D‑S evidence fusion. The method comprises the steps of: obtaining acceleration vibration data of the rotor misalignment state; obtaining an initial evidence source of D-S evidence theory according to the acceleration vibration data; obtaining mutual information measurement between evidence bodies and obtaining evidence body according to the mutual information measurement between evidence bodies The similarity measure function between; obtain the evidence body E according to the similarity measure function i The total similarity of the total similarity; according to the total similarity to obtain the credible function of the body of evidence; according to the credible function to obtain the credibility of each body of evidence; according to the credibility of each body of evidence to modify the initial source of evidence, to The corrected evidence source is obtained; the corrected evidence source is synthesized by using the D-S synthesis rule to obtain the fault state identification result of multi-source decision fusion. Therefore, the above method greatly optimizes the fault identification process and improves the identification accuracy of the rotor misalignment state.

Description

technical field [0001] The invention relates to the technical field of double rotor misalignment fault identification, in particular to a rotor misalignment state identification method based on improved D-S evidence fusion. Background technique [0002] The rotor system is the core component of aero-engine, steam turbine, wind power generator and other equipment. Due to manufacturing and installation errors, support bearing wear, rotor winding and thermal deformation, etc., the rotor is in various forms of misalignment. The vibration of the whole machine is too large, and the whole rotor system is damaged, which threatens the safe and stable operation of the equipment. Misalignment faults are inevitable, but if the rotor system misalignment status (type, location, degree) can be grasped in time, maintenance measures can be taken in time to reduce the accident rate caused by misalignment faults. [0003] In practical engineering applications, the rotor system is generally in...

AI Technical Summary

Problems solved by technology

However, the commonly used distance measure function still cannot accurately express the conflict between evidences in some cases.

Images