X-type four-rotor unmanned aerial vehicle control method based on fault diagnosis result

Abstract

The invention discloses an X-type four-rotor unmanned aerial vehicle control method based on a fault diagnosis result. The method comprises the following steps: step 1, establishing a kinematic model of an X-type four-rotor unmanned aerial vehicle; step 2, designing a position and posture PID controller; step 3, establishing an execution mechanism fault model; and step 4, intelligently adjusting parameters of the PID controller. According to the control method, the PID controller is combined with a reinforcement learning parameter adjustment technology, under the condition that the four-rotor unmanned aerial vehicle has an execution mechanism fault, based on reinforcement learning, the PID control parameters of attitude control and position control are self-tuned according to the self state of the four-rotor unmanned aerial vehicle and a fault diagnosis result, the stable control of the four-rotor unmanned aerial vehicle pose system is realized, the reliability and safety of the four-rotor unmanned aerial vehicle pose system are ensured, the arrival and stability of the pose are realized, and the safety of autonomous flight of the four-rotor unmanned aerial vehicle is improved.

Description

technical field [0001] The invention relates to a control method for an X-type quadrotor unmanned aerial vehicle based on fault diagnosis results, and belongs to the technical field of intelligent control of unmanned aerial vehicles. Background technique [0002] With the rapid development of artificial intelligence technology, the combination of traditional control framework and artificial intelligence technology is getting more and more attention in the field of aerospace. With its structural characteristics, the quadrotor UAV can fly through a simpler control method. However, due to its four-input, six-degree-of-freedom characteristics, the system has the characteristics of nonlinearity, underactuation, and strong coupling. It is a typical uncertain nonlinear system. At the same time, the design of the control system must meet the minimum human intervention , to enhance its anti-interference ability. [0003] For the position and attitude control of quadrotor drones, th...

AI Technical Summary

Problems solved by technology

These methods can stabilize the pose, but they also have the following limitations: 1) In the process of autonomous flight, the four-rotor UAV is fatally hit by failures such as system crashes, and it is necessary to add a fault-tolerant control system to To ensure that the system can handle sudden failures spontaneously, but in the existing control methods, the manual setting of the control gain in the controller is relatively complicated, which hinders the improvement of control performance and cannot meet the requirements of the quadrotor unmanned system for spontaneously handling sudden failures. The safety of autonomous flight cannot be guaranteed; 2) For the field of aerospace control with high safety requirements, the existing control methods are difficult to accurately describe the expected function of the system, and lack the guarantee of the robustness of the system

Images