基于金枪鱼群优化算法的Jensen模型参数求解  

Calculating the Coefficients in the Jensen Model Using the Tuna Swarm Optimization Algorithm

作　　者：薛萍 刘玲 王仰仁 孙书洪 XUE Ping;LIU Ling;WANG Yangren;SUN Shuhong(College of Computer and Information Engineering,Tianjin Agricultural University,Tianjin 300384,China;College of Hydraulic Engineering,Tianjin Agricultural University,Tianjin 300384,China)

机构地区：[1]天津农学院计算机与信息工程学院,天津300384 [2]天津农学院水利工程学院,天津300384

出　　处：《灌溉排水学报》2022年第11期22-29,共8页Journal of Irrigation and Drainage

基　　金：现代都市农业智慧灌溉技术项目(XB202016)。

摘　　要：【目的】利用智能优化算法求解Jensen模型参数。【方法】将分布估计引入金枪鱼群优化算法(TSO)中,形成基于分布估计的金枪鱼群优化算法(ITSO)。将改进的基于分布估计的金枪鱼群优化算法(ITSO)与其他算法在CEC2017测试集上进行性能验证,并利用山西潇河灌溉试验站非充分灌溉试验结果对该算法与其他方法求解的精准性进行对比。【结果】(1)在CEC2017测试集上,对比ITSO、TSO、GWO、WOA、SSA和BOA共6种算法的寻优性能表明,ITSO算法寻优能力最强。(2)在山西潇河灌溉试验站非充分灌溉试验结果上分别将ITSO与SPSS软件中非线性回归分析、TSO计算得出的结果进行对比,平均相对误差分别为7.79%、8.13%和7.79%。TSO算法经过50次迭代后找到最优解,而ITSO算法仅需35次迭代后找到最优解。【结论】基于分布估计的金枪鱼群优化算法(ITSO)求解Jensen模型参数,拟合精度高且寻优速度快。【Objective】The Jensen formula is a nonlinear model for calculating the response of crop yield to water and nutrient applications.It contains a number of parameters which need calibration against experimental data.The aim of this paper is to present a method to inversely estimate these parameters using experimental data.【Method】The method is based on the tuna swarm optimization algorithm(TSO).A distribution estimation(ITSO)was used to form the tuna swarm optimization algorithm(TSO),and the performance of the proposed tuna swarm optimization algorithm was verified against other algorithms based on the CEC2017 test.The accuracy and efficiency of the method were compared with other methods based on experimental data obtained from the Xiaohe Irrigation Experimental Station in Shanxi province.【Result】Comparing the performance of ITSO,TSO,GWO,WOA,SSA and BOA methods shows that the proposed algorithm is the best.Comparing ITSO with the nonlinear regression analysis in the SPSS software and TSO shows that the relative error of the proposed method is 7.79%,8.13%and 7.79%,respectively.The TSO algorithm converged in 50 iterations,while the ITSO algorithm found the optimal solution in just 35 iterations.【Conclusion】The tuna swarm optimization algorithm combined with the distribution estimation(ITSO)is efficient for estimating the parameters in the Jensen model.It is highly accurate and converges fast.

关 键 词：水分生产函数 JENSEN模型 模型参数求解 分布估计 金枪鱼群优化算法 

分 类 号：S274[农业科学—农业水土工程]