基于响应面法和NSGA-II算法的麦弗逊悬架优化

应用响应面法和经过改进的非支配排序遗传算法(NSGA-II)进行悬架结构参数优化.在ADAMS/Insight软件中进行设计参数的灵敏度分析，针对灵敏度较大的设计参数，建立车轮定位参数在车轮跳动过程中最大变化量的2阶响应面近似数学模型对该模型进行稳定性分析，并且应用加入精英保持策略和去除重复个体算法的NSGA-II优化算法对多目标响应面模型进行优化求解.优化结果表明该方法具有较高的精确性与有效性.     

基于产量品质及水肥利用率的核桃水肥耦合方案优化

针对干旱区核桃水肥利用效率低及高效水肥制度不明晰的问题,以新疆阿克苏地区核桃树为研究对象,以核桃提质增效为目标,研究水肥耦合条件下对滴灌核桃的生理生长指标、果实品质、产量的影响。为了更精准地预测水肥制度,以灌水量（225 m³·hm^-2,W1;300 m³·hm^-2,W2;375 m³·hm^-2,W3）、施肥量（常规施肥量0.5倍（236.93 kg·hm^-2）,F1;常规施肥量（473.85 kg·hm^-2）,F2;常规施肥量2倍（947.7 kg·hm^-2）,F3）为试验因素,通过建立关于核桃的果实品质、产量、水分利用效率和肥料偏生产率的二元二次回归模型,并采用二代非支配排序遗传算法（NSGA-II）对该回归模型进行验证求解,从而模拟出最优水肥制度。结果表明：灌水量和施肥量两因子及其耦合效应对核桃的生长指标均有显著影响,核桃的果实品质、产量和水肥利用率随着灌水量和施肥量的增加呈现先增加后减小的趋势,在各处理情况下,W2F2处理为最优的灌溉施肥处理。通过NSGA-II模拟出的最优水肥制度为灌水量和施肥量分别是336.93 m³·hm^-2和715.21 kg·hm^-2。最终对应的蛋白质含量、产量、水分利用效率和肥料偏生产率分别是21.36%、2 971.66 kg·hm^-2、8.76 kg·mm^-1·hm^-2和1.02。     

面向番茄植株相近色目标识别的多波段图像融合方法

针对温室番茄智能化管理需要，研究茎秆、叶片和绿果等3类相近色目标的多波段图像融合方法，以凸显目标与背景亮度差异，提高目标视觉识别效率。根据其各自在300~1000 nm范围的反射光谱特征差异，建立了针对其光谱数据分类的Lasso正则化逻辑回归模型。基于模型的稀疏解特征，确定具有较大权值系数的450、600和900 nm等3个波段作为最优成像波段，在此基础上构建了温室番茄植株多波段图像在线采集系统。结合最优成像波段下相近色目标图像特征分析，提出了基于NSGA-II的多波段图像加权融合方法，以增强特定目标与近色背景物体的图像亮度差异。最后通过现场试验对多波段图像融合效果进行评估。结果表明，分别以茎秆、叶片和绿果器官作为识别目标，通过多波段图像融合处理后，目标与背景之间的图像灰度差异绝对差值相应达到单波段图像的2.02、8.63和7.89倍，即被识别目标与其他近色背景的亮度差异显著增强，且背景物的亮度波动得到抑制。本研究结果可以为农业环境近色目标视觉识别相关研究提供参考。     

Multi–objective Function Optimization for Environmental Control of a Greenhouse Based on a RBF and NSGA-Ⅱ

To better meet the needs of crop growth and achieve energy savings and efficiency enhancements,constructing a reliable environmental model to optimize greenhouse decision parameters is an important problem to be solved.In this work,a radial-basis function (RBF) neural network was used to mine the potential changes of a greenhouse environment,a temperature error model was established,a multi-objective optimization function of energy consumption was constructed and the corresponding decision parameters were optimized by using a non-dominated sorting genetic algorithm with an elite strategy (NSGA-II).The simulation results showed that RBF could clarify the nonlinear relationship among the greenhouse environment variables and decision parameters and the greenhouse temperature.The NSGA-II could well search for the Pareto solution for the objective functions.The experimental results showed that after 40 min of combined control of sunshades and sprays,the temperature was reduced from 31℃ to 25℃,and the power consumption was 0.5 MJ.Compared with the three days of July 24,July 25 and July 26,2017,the energy consumption of the controlled production greenhouse was reduced by 37.5%,9.1% and 28.5%,respectively.     

基于模拟优化模型的干旱风沙草原区水-粮食-能源关系

定量分析干旱风沙草原区水-粮食-能源(WFE)关系,可为制定草原区生产、经济和生态环境等政策提供科学的支持.采用基于Python语言的 MODFLOW模型——FloPy,在考虑研究区牧草产量和灌溉能源消耗的基础上,构建了一个紧密耦合干旱风沙草原区WFE系统理想案例的多目标模拟优化模型,并使用多目标优化工具Pymoo框架下的NSGA-Ⅱ算法进行了求解.结果表明:所构建的模拟优化模型可以定量计算干旱风沙草原区的WFE关系,Pymoo提供的NSGA-II算法在WFE关系多目标优化中具有较好的搜索效率与稳定性;使用权重w_x对设定的6种方案进行对比分析,一般年(方案1—3)与干旱年(方案4—6)的地下水水位差最大值分别为1.15,1.43,1.34,0.96,1.26,1.15 m;一般年和干旱年灌溉水量最大可减少136.90%和134.37%,作物产量增加18.60%和18.31%,节省能源26.94%和27.89%.     

Optimal Design of Vortex Pump Using Approximate Model and the Non-dominated Sorting Genetic Algorithm北大核心CSCD

【Objective】The cavity width L, blade width b2 and the number of blades Z are the most important geometric parameters affecting the performance of vortex pump. This paper aims to present a method to optimize the vortex pump. 【Method】The study was based on approximate model and the non-dominated sorting genetic algorithm II (NSGA-II), in which the pump cavity length, blade width and the number of blades were calculated using the central composite design of DoE (design of experiment). The performance of the designed pump was examined using CFD, and the effect of L, b2 and Z on vortex pump efficiency and shear stress on the blade wall was calculated using the Kriging model. The NSGA-II was used to optimize the geometric parameters.【Result】The optimal parameters calculated from the methods were L=25 mm, Z=8, b2=26.45 mm.【Conclusion】We proved that CFD and NSGA-II can be used in a combination to calculate the optimal parameters of the vortex pump, and they can significantly improve efficiency of the pump and reduce the shear stress on the blade. Our results revealed that the optimization can reduce the width of the non-blade cavity by 16.67%, and increase the number of blades of the impeller and the outlet width of the blade by 1 and 25.95% respectively. At the design flow rate, the optimal design increased pump efficiency by 1.06% and reduced the average shear stress on the blade from 274.37 Pa to 204.57 Pa. The optimal design made the shear stress on the blade more uniform, in addition to reducing the shear stress on the outlet of the blade. © 2019 Authors. All rights reserved.