Unmanned aerial vehicle sensor vibration noise suppression method

Abstract

The invention discloses a time convolution network-based vibration noise suppression method for a small unmanned aerial vehicle sensor. The method comprises the following steps that: an external high-precision measurement system is utilized to obtain high-precision measurement values of an attitude angle and an angular speed during flight of a unmanned aerial vehicle, and at the same time, a gyroscope angular speed measurement value of an onboard MEMS inertial measurement unit of a flight control system under the influence of internal noise of the unmanned aerial vehicle is recorded, and a training data set and a test set after data are constructed after data cleaning and time synchronization processing are performed; a multi-layer time convolution network is built for training and testing, a trained model is called on a small embedded system for test flight verification. Experimental data shows that the time convolution network can effectively retain original signal characteristics and greatly reduce the influence of noise on a gyroscope measurement result.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicle systems, in particular to a method for suppressing vibration and noise of an unmanned aerial vehicle sensor. Background technique [0002] With the rapid development of MEMS sensor (micro-electromechanical system) technology in recent years, MEMS inertial measurement units are widely used in small unmanned aerial vehicles, unmanned vehicles and other unmanned systems due to their small size, rapid response and high sampling rate. [0003] With the development of the miniaturization design of the UAV system, its structure is becoming more and more compact. The high-frequency vibration generated by the power components such as the rotor and the motor of the aircraft will affect the gyroscope and the MEMS inertial measurement unit in the small-sized fuselage. The accelerometer produces a large noise effect, which affects its attitude accuracy. [0004] Although methods such as low-pa...

AI Technical Summary

Problems solved by technology

[0009] The technical problem to be solved by the present invention is: Aiming at the problem that the MEMS gyroscope sensor of the UAV is easily disturbed by the vibration noise of the aircraft aerodynamic and power system in the measurement of angular velocity, a temporal convolutional neural network is introduced, and a time-based convolutional network is proposed. (TCN) small UAV MEMS inertial sensor attitude angle measurement signal noise reduction method

Images