Helicopter rotor abnormity detecting method driven by vibration data

Abstract

The invention discloses a helicopter rotor abnormity detecting method which comprises the steps of analyzing and processing original vibration data; extracting a helicopter rotor state characteristic; training a support vector data model by means of a rotor data characteristic in a normal state; and finally performing abnormity detection on the rotor according to the established model. The helicopter rotor abnormity detecting method is advantageous in that the effective fault characteristic is extracted for aiming at non-smooth and nonlinear vibration data; and on condition that only normal state data are available, the helicopter rotor abnormity detecting method according to the invention satisfies a requirement of abnormal characteristic data in a routine method.

Description

technical field [0001] The invention relates to a vibration data-driven helicopter rotor abnormality detection method, which is an abnormal detection method specially aimed at the helicopter rotor vibration data, and belongs to the cross field of aeronautical engineering and information science. Background technique [0002] As a lifting surface and a control surface, the rotor of a helicopter not only provides power for forward movement, but also a source of power for various attitude changes. The rotor system works in a periodically changing aerodynamic environment and bears complex aeroelastic loads, such as the unbalanced periodic alternating loads in the process of forward flight. What's more, the vibration load will cause fatigue damage to the important flight components of the helicopter, which will cause the rotor to fail and cause accidents. The rotor failure rate is as high as 20% in helicopter failures, and 35% of helicopter first-degree accidents are related to ...

AI Technical Summary

Problems solved by technology

In the real scene, considering that the unknown failure modes of the helicopter rotor are various and unpredictable, it is impossible to obtain a large amount of failure data in various states in advance; the data in the normal state is easy to obtain, and the rotor may have been damaged in the fault state; and because The cost of fault simulation is very high, and it is often not allowed in practice, resulting in the difficulty of capturing fault state samples and resulting in severe scarcity

Images