Research On Driving Control Based On Genetic And BP Optimization And Mixing

At present,the electric car drive system is generally controlled by PID algorithm.The electric car's drive system is a nonlinear system,and it's more difficult to control.Using PID algorithm,the control effect is not ideal.The main problem is that the dynamic response is slow,the constant error is larger,the resistance is weak,and the dynamic motor is pulsating.Directly,these issues are reducing the driving comfort of electric cars;In addition,the energy consumption in the traditional PID control process is higher,which indirectly reduces the driving distance of electric cars.The load of new energy electric vehicle used for sites is changeable,and the traffic environment is complex.In order to deal with this kind of complex traffic environmen of electric vehicles,genetic and BP algorithm optimization and hybrid algorithm(IGA-IBP)was adopted,and use this algorithm to design a PID controller with parameter self-learning capability.Apply this controller to the drive control system of a electric vehicle,an improved genetic BP neural Network(IGA-IBP)algorithm is proposed.Based on the proposed algorithm,a parameter self-learning PID controller is designed And applied to the driving system of the electric vehicle.The analysis results show that the IGA-IBP algorithm is compared with The GA-BP,anti disturbance ability,the speed of the electric vehicle response,noise in the process of driving,motor torque ripple have all improved.In addition,the energy consumption is reduced in the starting process of the electric vehicle in the field,so that the field electric vehicle has to continue to make the mileage longer.In this paper,firstly,the error function of BP neural network algorithm is slow down,and it is easy to fall into the local extremum problem.The optimization algorithm of the optimized additional momentum and the adaptive learning rate adjustment method are improved.Then,the problem of crossing rate and mutation rate of genetic algorithm is improved.Finally,using the accumulation and update of ant colony algorithm pheromone,the improved genetic BP neural network algorithm converges to the optimal path,and the IGA-IBP algorithm is obtained.IGA-IBP is designed to be easy and adaptive,plays an important role in the promotion and application of the electric field.