Four-rotor unmanned aerial vehicle intelligent fault diagnosis method based on convolutional neural network

Abstract

The invention provides an intelligent fault diagnosis method based on a stack pruning sparse denoising automatic encoder and a convolutional neural network, which is called sPSDAE-CNN for short. According to the method, original input data is processed by using the stack denoising automatic encoder, and more training data is obtained by using a data enhancement method. The stack sparse pruning and noise reduction self-encoder comprises a full-connection automatic encoding network, and the characteristics extracted at the front layer of the network are used for performing the operation of the subsequent layer, which means that some new connections appear between the front and rear layers of networks, so that the information loss is reduced, and more effective characteristics are obtained; meanwhile, pruning operation is introduced, so that the training efficiency and precision of the network are improved, higher training speed and high adaptability to noise signals are achieved, and the overfitting problem of the convolutional neural network is suppressed to a certain extent; according to the method, the flight data of the quad-rotor unmanned aerial vehicle are input into the model, and high fault diagnosis accuracy is obtained under the condition of high noise interference.

Description

technical field [0001] The invention relates to a control system of a multi-rotor aircraft, and designs a fault diagnosis algorithm based on a convolutional neural network, belonging to the technical field of fault diagnosis. Background technique [0002] UAVs are very suitable for performing tasks in indoor and outdoor spacious environments, such as personnel search and rescue, material transportation, military patrols and surveillance, pesticide spraying, crop sowing, etc. Due to the increasing complexity of tasks performed by aircraft, the aircraft on board Sensors and actuators are becoming more and more complex, so when performing tasks, the reliability of the aircraft is required to be higher and higher. Once the UAV has a serious failure during flight, it will cause serious property damage. In such a case, personal injury or death may result. During the flight of the aircraft, any tiny fault can easily cause the aircraft itself to malfunction, thereby affecting the s...

AI Technical Summary

Problems solved by technology

Acquisition of sound signals and strict requirements on the environment cannot be applied in practice

In a related study, the author introduces the convolutional neural network with a wide convolution kernel into the fault diagnosis method, and diagnoses the bearing data analysis through the convolutional neural network, which improves the anti-interference of the convolutional neural network to a certain extent. Ability, for the data containing a lot of noise in the actually collected UAV data, the demerits of the algorithm are not ideal, and it is prone to fault false positives and overfitting

[0008] At present, many scholars have proposed a new type of neural network fault diagnosis algorithm, but the actual application on the quadrotor UAV is still relatively small, and further research is needed.

Images