Research On Identification And Control Strategy Of Servo System Of Rocket Fire Extinguishing Vehicle

Rocket fire extinguishing vehicle plays an important role in modern fire accident,especially in the critical moment.As the complication of city construction and fire size,the response speed,firing accuracy and overall performance of the fire fighting truck are put forward higher requirements,whereas the accuracy and stability of fighting cannon mainly depends on the performance of position servo system.In order to improve the performance of the rocket fire-distinguishing car,system identification and control strategy are researched,based on the engineering background of rocket fire truck,which has important theory value and practical significance in the aspect of ensuring national economy and people’s life and property security to some extend.First of all,the position servo system composition structure and working principle of rocket fire-distinguishing car are analyzed in detail.Aiming at the executive component of servo system,permanent magnet synchronous motor’s two phase coordinate system model is established by vector control method.On the basis of the motor model,three-loop control mathematical model of the current loop,velocity loop and position loop are established respectively.In addition,nonlinear and uncertain factors of the system are analyzed,which lays theoretical foundation for system identification and control strategy.Secondly,as a result of the existence of complicated nonlinear and uncertain factors,these factors will have impact on the system accuracy,static and dynamic performance when using mechanism analysis,which is hard to represent all the features of the system.So the system identification method is used for modeling.The structure and algorithm of BP,RBF and double hidden layer RBF-BP neural network identification are respectively introduced.At the same time,the structure of RBF-BP composite neural network identification is optimized by genetic algorithm.Simulation results show that the genetic algorithm to optimize RBF and BP double hidden layer neural network identification model has better recognition effect.Thirdly,on the basis of the identification model for control strategy research and combined with the classical PID control,adaptive control and neural network adaptive control system’s structure characteristics and working principle,RBF neural network PID adaptive control is designed.Moreover,genetic algorithm to optimize RBF and BP neural network PID adaptive compound control is put forward,which takes GA-RBF-BP as identifier and uses BP-PID as controller.In comparison with the former,the numerical simulation results show that the latter compound control has the advantages of fast response speed,high control precision and strong stability,that can well satisfy the performance index of the system.Finally,the hardware in the loop simulation experiment platform of fire-distinguishing car servo system is set up.With its performance indicators as the basis for testing,the control strategies mentioned in this paper are verified by step and sine comprehensive experiment.The experimental results prove that the genetic algorithm to optimize RBF and BP neural network PID adaptive hybrid control strategy can improve the control precision of rocket fire fighting car’s AC servo system,and meet the performance indicators system,which verifies the correctness and effectiveness of the control strategy analysis theory.