Hydroelectric generating set group shafting vibration fault holographic identification method

Abstract

The invention discloses a hydroelectric generator group shafting vibration fault holographic identification method and belongs to the field of hydroelectric generator group fault identification. The method comprises steps of taking a rotor and stator collision and abrasion force, an unbalanced magnetic pull force, a sealing excitation force, a hydraulic unbalanced force, a rotor bow-shaped rotation force, a rotating wheel bow-shaped rotation force, an oil film force, and a rotating wheel vortex strip eccentric force as external excitation vibration sources; establishing a nonlinear vibration model of the hydroelectric generating set group, solving to obtain vibration simulation information of the hydroelectric generating set group, solving a holographic spectrum of the hydroelectric generating set group, and analyzing to obtain a corresponding relation between each holographic spectrum characteristic and a shafting vibration fault; for the vibration actual measurement signal of the guide bearing, solving a holographic spectrum and extracting holographic spectrum features, and if extraction fails, judging that no shafting vibration fault occurs; and otherwise, judging that a shafting vibration fault occurs, searching the shafting vibration fault corresponding to the holographic spectrum feature, and taking the searched shafting vibration fault as a fault identification result. The method can accurately and effectively realize fault identification of shaft system vibration of the hydroelectric generating set group.

Description

technical field [0001] The invention belongs to the field of fault identification of hydropower group units, and more particularly relates to a holographic identification method for shaft system vibration faults of hydropower group groups. Background technique [0002] With the continuous penetration of conventional hydropower and pumped storage in the power system, hydropower, as a clean and renewable energy source, has an increasing proportion of its capacity in the power system, and has become the backbone of the global double carbon target. However, as a key component of energy conversion, shafting has long been operating in a complex and harsh hydroelectric-electromechanical coupling environment, which greatly reduces the safety and reliability of hydropower systems. [0003] In recent years, a large number of scholars in the world have conducted a lot of research on shafting vibration fault identification, which can be roughly divided into two categories. The first is...

AI Technical Summary

Problems solved by technology

Faulty shafting fault diagnosis method based on vibration mathematical model, a model can only diagnose a specific fault, but in the actual operating environment, there are still many faults in the shafting that cannot be described by mathematical theory

The shafting fault diagnosis method based on machine learning or deep learning, due to the complexity of the hydropower group system and its operating environment, cannot obtain enough fault history data for learning, and the accuracy of fault diagnosis cannot be guaranteed. , these methods will lose a lot of effective information in the process of signal processing, further reducing the effectiveness of diagnosis

[0005] In general, the existing methods cannot accurately and effectively realize the fault identification of the vibration of the shafting system of the hydropower group

Images