Carbon Dioxide Optimal Control Model Based on Support Vector-Improved Fish Swarm Algorithm

XIN Pingping;ZHANG Zhen;WANG Zhiyong;HU Jin;SHAO Zhicheng;ZHANG Haihui;College of Mechanical and Electronic Engineering,Northwest A&F University;Key Laboratory of Agricultural Internet of Things,Ministry of Agriculture;

CO2 optimal regulation model;;support vector machine algorithm;;improved fish swarm algorithm;;photosynthetic rate;;saturation point of CO2

CO_2was one of the main raw materials for plant photosynthetic rate,CO_2 optimal regulation model to meet the crops' requirements was pivotal to afford a fine growth environment in crops' whole life cycle.CO_2 optimal regulation model fusing the support vector machine-improved fish swarm algorithm was proposed to provide a quantitative basis for precise regulation of CO_2 in greenhouse.Taking the cucumber plant as research object,considering the mechanism of its photosynthesis,a photosynthesis rate nest-test with three-factor combinations consisted of temperature, photon flux density and CO_2 concentration was constructed.In the test,temperatures,photon flux densities and CO_2 concentrations were set at 9,7,10 gradients,respectively.Totally 630 groups of CO_2 response data were obtained by LI-6400 XT portable photosynthesis rate instrument,in which 81% of the data was employed to construct the support vector machine(SVM) photosynthetic rate prediction model,while the remaining data was used for model validation.Furthermore,through improved fish swarm algorithm with SVM photosynthetic rate prediction model network as input,optimized photosynthetic rate values were acquired with variety of variables.Accordingly,CO_2 saturation points were generated at different temperatures and photon flux density conditions for CO_2 optimal regulation model.Compared the proposed SVM photosynthetic rate prediction model with conventional non-linear regression(NLR) prediction model and error back propagation(BP) prediction model,results showed that SVM prediction model was obviously superior to NLR prediction model and BP prediction model with correlation coefficient of 0.994 and mean absolute error of 0.879 μmol/(m~2·s).Then,XOR checkout was adopted to validate the CO_2 optimal regulation model,results showed that the correlation coefficient between the simulated values and measured values was 0.965 and the maximum relative error was 3.056%, which indicated that the proposed CO_2 optimization model could be applied to predict CO_2 saturation points dynamically and provide a feasible way for CO_2 concentration precise controlling for plants in greenhouse.