Research On Optimization Method For Growth Environment Of Solanaceous Vegetables In Greenhouse

Solanaceous vegetables are one of the main crops in greenhouse cultivation.How to accurately optimize greenhouse environmental factors and create greenhouse microclimate conditions suitable for crop growth is the key to increase photosynthetic rate and yield.Existing greenhouse environmental factor optimization control methods often have low precision and weak adaptability problems.They either lack the consideration of the actual growth demand of crops,or neglect the complex coupling relationship among multiple environmental factors in the greenhouse,and cannot exert the advantages of greenhouse cultivation.Therefore,it is of great significance to study the optimization of the growth environment of greenhouse solanaceous vegetables and to achieve the precise optimization of greenhouse environmental factors,and to promote the efficient production of solanaceous vegetables and improve the utilization of agricultural resources.In view of the problem that the greenhouse environment optimization cannot be carried out according to the real-time environment of the greenhouse and the crop growth demand,this paper studies the two parts of photosynthetic rate model construction and multi-environment factor optimization.In the construction stage of photosynthetic rate model,the environmental factors affecting crop photosynthesis were analyzed,and the key factors were selected by combining gray correlation degree.A support vector regression algorithm for chemotaxis-improved particle swarm optimization was proposed to construct Photosynthetic rate prediction model of multi-environment factor coupling conditions.Iin the multi-environlent factor optimization stage,a optimization algorithm based on fireworks algorithm is proposed.Firstly,according to the problems existing in the fireworks algorithm,the mapping rules and selection strategies are improved,and the improved fireworks algorithm is proposed.Based on the obtained photosynthetic rate model,the improved fireworks algorithm is used to iteratively optimize the photosynthetic rate,and the carbon dioxide optimization target value under different temperature,humidity and illumination factor coupling conditions is obtained.Finally,considering the time series of crop growth,a multi-factor optimal control model of greenhouse was established by using the support vector regression of chemotaxis-improved particle swarrn optimization,and the optimal control target value of carbon dioxide under the coupling conditions of growth period,temperature,humidity and illumination factors was calculated dynamically.The simulation results verify the effectiveness of the proposed algorithm.Compared with support vector machine(SVM)and particle swarm optimization(PSO),the proposed algorithm has higher prediction accuracy.The improved fireworks algorithm is compared with the existing fireworks algorithm,which shows that the improved algorithm has the advantages of high precision,fast convergence and short time.It can quickly and smoothly solve the environnental factor optimization target value corresponding to the optimal photosynthetic rate.The greenhouse multi-factor optimization control model established by the chemotaxis-modified particle swarm regression support vector machine also showed superior performance in terms of accuracy,which proved the superiority of the proposed dynamic optimization of environmental factors according to crop photosynthetic requirements.