Improvement Of Dragonfly Algorithm And Its Application In Sugarcane Harvester

At present,there exists some problems such as serious blocking,high breaking rate and poor cutting quality in the process of sugarcane mechanization harvesting,which leads to the low germination rate of sugarcane perennials in the coming year,and greatly affects the yield of sugarcane and the promotion of sugarcane mechanization.Among them,the performance of the stripping system is the key to the impact of blocking,and the cutter is one of the key components that affect the cutting quality directly.In this paper,the adaptive,fault-tolerant and robustness of the intelligent optimization algorithm are used to improve the stripping performance and to explore the influence of complex factors on the axial vibration and cutting quality of cutter and then realize the prediction and control of cutting quality.Dragonfly algorithm is a novel meta-heuristic optimization algorithm,which is inspired by the dragonflies predatory and migration swarming behaviors in nature.In the algorithm,the process of exploration and exploitation simulates dragonflies in navigation,hunting and avoid enemies.This algorithm is simple,easy to implement,and has strong optimization capability.However,when solving some complex optimization problems,it is easy to fall into local optimum and in a certain extent affected the optimization of the sugarcane harvester.In order to improve the performance of the sugarcane harvester stripping system and the accuracy of cutting quality prediction,this paper analyzes and improves the shortcomings of the basic Dragonfly algorithm,and applies the improved algorithm to solve the optimization problem of sugarcane harvester.The main work of this paper is as follows:1.By introducing the elite opposition-based learning strategy to ensure the diversity of the population and to expand the scope of the search area.At the same time,in the iteration of the dragonfly individual location update using theexponential function step to replace the original linear step,effectively improved the algorithm convergence speed,and the global exploration ability and convergence speed of the algorithm are enhanced.2.The optimization of the PID controller parameters of the stripping system is realized by the improved algorithm,which solves the problem that the traditional PID parameter optimization method is time-consuming and can not guarantee the optimal parameters.At the same time,the PID control realizes the speed matching problem of the stripping and conveying process,which effectively alleviates the blocking problem.3.In order to solve the problem that the traditional prediction method has low accuracy and blind selection of parameters,a new prediction model of cutter vibration for sugarcane harvester based on support vector machine and Dragonfly algorithm is proposed.In this method,the optimization of the support vector machine parameters is realized by the process of dragonfly populations optimization,and then use the optimized support vector machine to achieve cutter vibration prediction.The experimental results show that the support vector machine prediction model based on dragonfly algorithm has higher prediction precision and generalization ability,and the prediction of the vibration of the cutter of sugarcane harvester is realized effectively.4.The immune selection operator is introduced,by using the immune selection operation to update the dragonfly population,it can effectively suppress the premature stagnation phenomenon which is easy to occur in the convergence process,so as to improve its global optimization ability and optimization precision.Then use the optimization algorithm to optimize the parameters of support vector machine,so an optimal support vector machine prediction model is obtained.Finally,use the optimal support vector machine to predict the cutting quality of sugarcane harvester.The simulation results show that the support vector machine optimized by the improved Dragonfly algorithm has better prediction performance.