首页> 外文期刊>Journal of Applied Biological Sciences >Modeling Drop Size Emitted from Irrigation Impact Sprinklers using Gene Expression Programing and Multiple Linear and Nonlinear Regression Methods
【24h】

Modeling Drop Size Emitted from Irrigation Impact Sprinklers using Gene Expression Programing and Multiple Linear and Nonlinear Regression Methods

机译:使用基因表达程序以及多元线性和非线性回归方法对灌溉冲击喷头散发的液滴大小进行建模

获取原文
       

摘要

Thecharacteristicsofdropsproducedbysprinklershaveimportantroleindesigning,evaluationofsprinklerirrigation,determiningwinddriftandevaporationlossesandsoilcompaction.Predictingthesizeofemitteddropscanimprovetheaccuracyofabovementionedissues.InthisresearchGeneExpressionPrograming(GEP)asoneofartificialintelligentmethodsandmultiplelinearandnonlinearregressionmethods(MLRandMNLR)wereappliedformodelingthesizeofthedropsproducedbysprinklers.Theinputdatawereincludednozzlediameter,operationpressure,andthedistancefromsprinklerandtheoutputswastheaveragesizeoflandeddropsinagivendistancesfromsprinkler.Theexperimentswereconductedin22combinationsofnozzlediametersandoperationpressureandinawindlesscondition.Ineachexperiment9to14measurementstationswereconsideredwith1.5metersspacingintervalsfromsprinkler.Usingdigitalphotographymethodandanalyzingthetakenphotos,hydrodynamicalpropertiesofdropsinphotosweredetermined.Obtaineddatawereclassifiedinthenozzlesdiameters,operationpressures,distancesfromsprinklerinonesideandaveragesizeoflandeddropsineachstationintheotherside.FinallytheGEPmethodandMLRandMNLRmethodswereappliedtodevelopmodelsforpredictinglandeddropsizeincertaindistances.Comparisonsbetweenmodelsoutputsandexperimentaldataweredonetoevaluatemodelsperformances.TheresultsshowedthatinGEPmethod,F5modelwithR=0.9599andRMSE=0.4060mm,andinMNLRmethodL1modelwithR=0.9333andRMSE=0.5442mm,havegoodaccuracytobeproposedaspropermodelsforpredictingemitteddropsizefromirrigationimpactsprinklers.
机译:Thecharacteristicsofdropsproducedbysprinklershaveimportantroleindesigning,evaluationofsprinklerirrigation,determiningwinddriftandevaporationlossesandsoilcompaction.Predictingthesizeofemitteddropscanimprovetheaccuracyofabovementionedissues.InthisresearchGeneExpressionPrograming(GEP)asoneofartificialintelligentmethodsandmultiplelinearandnonlinearregressionmethods(MLRandMNLR)wereappliedformodelingthesizeofthedropsproducedbysprinklers.Theinputdatawereincludednozzlediameter,operationpressure,andthedistancefromsprinklerandtheoutputswastheaveragesizeoflandeddropsinagivendistancesfromsprinkler.Theexperimentswereconductedin22combinationsofnozzlediametersandoperationpressureandinawindlesscondition.Ineachexperiment9to14measurementstationswereconsideredwith1.5metersspacingintervalsfromsprinkler.Usingdigitalphotographymethodandanalyzingthetakenphotos,hydrodynamicalpropertiesofdropsinphotosweredetermined.Obtaineddatawereclassifiedinthenozzlesdiameters,operationpressures,distancesfromsprinklerinonesi deandaveragesizeoflandeddropsineachstationintheotherside.FinallytheGEPmethodandMLRandMNLRmethodswereappliedtodevelopmodelsforpredictinglandeddropsizeincertaindistances.Comparisonsbetweenmodelsoutputsandexperimentaldataweredonetoevaluatemodelsperformances.TheresultsshowedthatinGEPmethod,F5modelwithR = 0.9599andRMSE =0.4060毫米,andinMNLRmethodL1modelwithR = 0.9333andRMSE =0.5442毫米,havegoodaccuracytobeproposedaspropermodelsforpredictingemitteddropsizefromirrigationimpactsprinklers。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号