Font Size: a A A

Design And Research Of Aerial Tri Axial Ptz Control System Based On ARM

Posted on:2019-06-08Degree:MasterType:Thesis
Country:ChinaCandidate:L ShuFull Text:PDF
GTID:2348330542956394Subject:Detection Technology and Automation
Abstract/Summary:PDF Full Text Request
China's steady PTZ technology started late.With the rapid development of UAV technology,airborne pan-tilt-zoom(PTZ)technology has been produced y,the steady PTZ can make UAV have fast target search and track capabilities.As the PTZ often performs tasks in complex environments,it will be affected by wind resistance,mechanical vibration,load disturbance and other factors.These random factors and non-linear factors lead to the PTZ control accuracy decreased,and even cause damage to the control system hardware platform.The traditional PTZ control system adopts the classical PID according to the error between the control target and the actual feedback to determine the control strategy to eliminate errors.However,in complex environments,the traditional PID cannot track the change of the mutation quantity due to the external disturbance,which results in decreased control accuracy and slow response speed.This paper designs a neural network-based PTZ control system.Neural network control algorithm is a new kind of artificial intelligence algorithm,which has the advantages of fast convergence speed and strong global approximation ability,and can overcome the problem of poor control effect of traditional PID in the field of nonlinear control.This design of the neural network PTZ control system is a new type of PTZ control system,ARM is used as a digital core processor in hardware,attitude sensor using MPU6050 accesses PTZ attitude signal.The hardware system executes the PTZ control algorithm to control the DC brushless motor and drive the PTZ load.The software algorithm adopts double closed-loop control,and the speed loop and position loop of the PTZ are controlled stably by artificial neural network control algorithmMATLAB simulation shows that:Neural Network Controllers outperform Traditional PID Controllers in Step Response,Sine Wave Fitting and Immunity.Hardware experiments show that:In the case of constant wind direction and wind speed 5.95m/s.the stable control of the PTZ can be achieved in the design with the PTZ attitude angle error within plus or minus five degrees.
Keywords/Search Tags:UAV, PTZ, PID, ARM, neural network
PDF Full Text Request
Related items