Structural optimization for crashworthiness criteria is of particular significance especially at early stage of design. The comparative study of Kriging and radial basis function network （RBFN） was performed in orde...Structural optimization for crashworthiness criteria is of particular significance especially at early stage of design. The comparative study of Kriging and radial basis function network （RBFN） was performed in order to improve the crashworthiness effects of honeycomb. Improving the crashworthiness characteristic of honeycomb was achieved using LS-OPT~ and domain reduction strategy. This optimization is performed on the basis of validated numerical simulation to establish the approximated model to illustrate the relationship between the responses and design variables. The results showed that Kriging meta-model is excelled in accuracy, robustness and efficiency compared to radial basis function （RBF） and crashworthiness characteristic of honeycomb is improved by 4%.展开更多
土壤风蚀是北方干旱和半干旱地区土地沙化和沙尘暴灾害的首要环节和主要动力过程之一.选取影响内蒙古自治区土壤风蚀演化的相关指标,运用GIS技术提取各指标数据,构建径向基函数神经网络(Radial Basis Function Network,RBFN);根据不同...土壤风蚀是北方干旱和半干旱地区土地沙化和沙尘暴灾害的首要环节和主要动力过程之一.选取影响内蒙古自治区土壤风蚀演化的相关指标,运用GIS技术提取各指标数据,构建径向基函数神经网络(Radial Basis Function Network,RBFN);根据不同风蚀危险程度标准,选取12个市、县(旗)相关数据进行训练,确定网络模型参数,进而对内蒙古自治区88个市、县(旗)的土壤风蚀危险度进行了评价.结果表明:内蒙古自治区西部为土壤风蚀发生的极强危险区,西北为强危险区,中部为中度危险区,而东部为轻度危险区;利用其他研究对该评价结论进行对比验证,结果较为理想.展开更多
基于径向基神经网络(Radial Basis Function Network,简称RBFN)及支持向量机(Support VectorMachine,简称SVM)的类似性,文章采用相同的符号体系,推导了RBFN及SVM在进行函数拟合时的表达式,指出这2种表达式形式上类似,主要区别是参数的...基于径向基神经网络(Radial Basis Function Network,简称RBFN)及支持向量机(Support VectorMachine,简称SVM)的类似性,文章采用相同的符号体系,推导了RBFN及SVM在进行函数拟合时的表达式,指出这2种表达式形式上类似,主要区别是参数的计算方法有所不同;以RBFN及SVM的拟合结果为响应面,基于蒙特卡罗模拟法进行了边坡的可靠度分析。计算结果表明,基于RBFN的蒙特卡罗模拟法与基于SVM的蒙特卡罗模拟法具有较高的计算精度及效率,2种方法在计算精度上没有明显的区别。展开更多
因无人机机载激光雷达(Light detection and ranging,LiDAR)数据具有离散性,在生成数字高程模型(Digital elevation model,DEM)时需选择有效插值方法。以荒漠植被区为研究背景,使用零均值标准化方法归一化点云回波强度,利用肘方法确定...因无人机机载激光雷达(Light detection and ranging,LiDAR)数据具有离散性,在生成数字高程模型(Digital elevation model,DEM)时需选择有效插值方法。以荒漠植被区为研究背景,使用零均值标准化方法归一化点云回波强度,利用肘方法确定最佳聚类数目,采用K-means方法对点云强度值聚类得到地面点云。在此基础上,采用克里金(Kriging)方法插值抽稀率为20%和80%的地面点云数据,且将点云高程作为变量,建立RBF神经网络预测模型,并通过线性回归检验方法对模型进行精度分析,采用Delaunay三角网内插生成高精度DEM。结果表明:采用K-means方法实现最佳聚类数目为4的聚类,得到地面点云48722个,在点云较优抽稀率20%的情况下,径向基函数神经网络(Radical basis function neural network,RBFNN)训练时间为56s,点云高程预测的决定系数R2为0.887,均方根误差RMSE为0.168m。说明使用RBFNN对K-means聚类滤波得到的地面点云进行高程预测效果较好,可为基于点云构建高精度DEM提供参考。展开更多
Catalytic cracking experiments of FCC cycle oil were carried out in a fixed fluidized bed reactor. Effects of reac- tion conditions, such as temperature, catalyst to oil ratio and weight hourly space velocity, were in...Catalytic cracking experiments of FCC cycle oil were carried out in a fixed fluidized bed reactor. Effects of reac- tion conditions, such as temperature, catalyst to oil ratio and weight hourly space velocity, were investigated. Hydrocarbon composition of gasoline was analyzed by gas chromatograph. Experimental results showed that conversion of cycle oil was low on account of its poor crackability performance, and the effect of reaction conditions on gasoline yield was obvi- ous. The paraffin content was very high in gasoline. Based on the experimental yields under different reaction conditions, a model for prediction of gasoline and diesel yields was established by radial basis function neural network （RBFNN）. In the model, the product yield was viewed as function of reaction conditions. Particle swarm optimization （PSO） algorithm with global search capability was used to obtain optimal conditions for a highest yield of light oil. The results showed that the yield of gasoline and diesel predicted by RBF neural network agreed well with the experimental values. The optimized reac- tion conditions were obtained at a reaction temperature of around 520 ~C, a catalyst to oil ratio of 7.4 and a space velocity of 8 h~. The predicted total yield of gasoline and diesel reached 42.2% under optimized conditions.展开更多
Hybrid loader 's comprehensive performance mainly depends on the performance of hydraulic torque converter during its driving and working. Hybrid loader and hydraulic torque converter are taken for the research ob...Hybrid loader 's comprehensive performance mainly depends on the performance of hydraulic torque converter during its driving and working. Hybrid loader and hydraulic torque converter are taken for the research objects. The primary characteristic curve of hydraulic torque converter and the traction curve of hybrid loader are acquired by analyzing the characteristic parameters of hydraulic torque converter, the characteristic parameters of engine, the characteristic parameters of battery pack and geometric parameters of hybrid loader. The gear shift curves based on the best energy saving performance and the best power performance are acquired respectively with the opening of throttle,the speed of pump wheel and the speed of turbine as parameters. Then the two curves are combined to get the comprehensive gear shift curve. Radical basis function( RBF) neural network is applied to building the gear shift strategy to keep hybrid loader with the best power performance and energy saving performance. The experimental bench is set up for experimental verification. It proves that both of the power performance and energy saving performance of hybrid loader are improved effectively by using the automatic shift strategy.展开更多
文摘Structural optimization for crashworthiness criteria is of particular significance especially at early stage of design. The comparative study of Kriging and radial basis function network （RBFN） was performed in order to improve the crashworthiness effects of honeycomb. Improving the crashworthiness characteristic of honeycomb was achieved using LS-OPT~ and domain reduction strategy. This optimization is performed on the basis of validated numerical simulation to establish the approximated model to illustrate the relationship between the responses and design variables. The results showed that Kriging meta-model is excelled in accuracy, robustness and efficiency compared to radial basis function （RBF） and crashworthiness characteristic of honeycomb is improved by 4%.
文摘土壤风蚀是北方干旱和半干旱地区土地沙化和沙尘暴灾害的首要环节和主要动力过程之一.选取影响内蒙古自治区土壤风蚀演化的相关指标,运用GIS技术提取各指标数据,构建径向基函数神经网络(Radial Basis Function Network,RBFN);根据不同风蚀危险程度标准,选取12个市、县(旗)相关数据进行训练,确定网络模型参数,进而对内蒙古自治区88个市、县(旗)的土壤风蚀危险度进行了评价.结果表明:内蒙古自治区西部为土壤风蚀发生的极强危险区,西北为强危险区,中部为中度危险区,而东部为轻度危险区;利用其他研究对该评价结论进行对比验证,结果较为理想.
文摘基于径向基神经网络(Radial Basis Function Network,简称RBFN)及支持向量机(Support VectorMachine,简称SVM)的类似性,文章采用相同的符号体系,推导了RBFN及SVM在进行函数拟合时的表达式,指出这2种表达式形式上类似,主要区别是参数的计算方法有所不同;以RBFN及SVM的拟合结果为响应面,基于蒙特卡罗模拟法进行了边坡的可靠度分析。计算结果表明,基于RBFN的蒙特卡罗模拟法与基于SVM的蒙特卡罗模拟法具有较高的计算精度及效率,2种方法在计算精度上没有明显的区别。
文摘因无人机机载激光雷达(Light detection and ranging,LiDAR)数据具有离散性,在生成数字高程模型(Digital elevation model,DEM)时需选择有效插值方法。以荒漠植被区为研究背景,使用零均值标准化方法归一化点云回波强度,利用肘方法确定最佳聚类数目,采用K-means方法对点云强度值聚类得到地面点云。在此基础上,采用克里金(Kriging)方法插值抽稀率为20%和80%的地面点云数据,且将点云高程作为变量,建立RBF神经网络预测模型,并通过线性回归检验方法对模型进行精度分析,采用Delaunay三角网内插生成高精度DEM。结果表明:采用K-means方法实现最佳聚类数目为4的聚类,得到地面点云48722个,在点云较优抽稀率20%的情况下,径向基函数神经网络(Radical basis function neural network,RBFNN)训练时间为56s,点云高程预测的决定系数R2为0.887,均方根误差RMSE为0.168m。说明使用RBFNN对K-means聚类滤波得到的地面点云进行高程预测效果较好,可为基于点云构建高精度DEM提供参考。
文摘针对光伏发电功率受气象因素影响而具有波动性与随机性问题,提出一种基于最优相似度与IMEARBFNN的短期光伏发电功率预测方法。利用相关性分析与平均影响值(Mean Impact Value,MIV)算法选取出温度、湿度、辐照度3个气象因素作为输入指标,通过最优相似度理论计算得到预测日的相似日。将相似日数据与预测日气象数据作为输入,采用改进思维进化算法(Improved Mind Evolutionary Algorithm,IMEA)优化径向基神经网络(Radical Basis Function Neural Network,RBFNN)模型对预测日光伏发电功率进行预测。结果表明改进思维进化算法优化径向基神经网络可以提高模型预测精度,为光伏发电功率预测提供一种有效方法。
基金support of the Chinese National Program for Fundamental Research and Development(973 program)(2012CB215006)
文摘Catalytic cracking experiments of FCC cycle oil were carried out in a fixed fluidized bed reactor. Effects of reac- tion conditions, such as temperature, catalyst to oil ratio and weight hourly space velocity, were investigated. Hydrocarbon composition of gasoline was analyzed by gas chromatograph. Experimental results showed that conversion of cycle oil was low on account of its poor crackability performance, and the effect of reaction conditions on gasoline yield was obvi- ous. The paraffin content was very high in gasoline. Based on the experimental yields under different reaction conditions, a model for prediction of gasoline and diesel yields was established by radial basis function neural network （RBFNN）. In the model, the product yield was viewed as function of reaction conditions. Particle swarm optimization （PSO） algorithm with global search capability was used to obtain optimal conditions for a highest yield of light oil. The results showed that the yield of gasoline and diesel predicted by RBF neural network agreed well with the experimental values. The optimized reac- tion conditions were obtained at a reaction temperature of around 520 ~C, a catalyst to oil ratio of 7.4 and a space velocity of 8 h~. The predicted total yield of gasoline and diesel reached 42.2% under optimized conditions.
基金The Youth Foundaticn Projects of the National Natural Science Foundation of China(No.61403236)
文摘Hybrid loader 's comprehensive performance mainly depends on the performance of hydraulic torque converter during its driving and working. Hybrid loader and hydraulic torque converter are taken for the research objects. The primary characteristic curve of hydraulic torque converter and the traction curve of hybrid loader are acquired by analyzing the characteristic parameters of hydraulic torque converter, the characteristic parameters of engine, the characteristic parameters of battery pack and geometric parameters of hybrid loader. The gear shift curves based on the best energy saving performance and the best power performance are acquired respectively with the opening of throttle,the speed of pump wheel and the speed of turbine as parameters. Then the two curves are combined to get the comprehensive gear shift curve. Radical basis function( RBF) neural network is applied to building the gear shift strategy to keep hybrid loader with the best power performance and energy saving performance. The experimental bench is set up for experimental verification. It proves that both of the power performance and energy saving performance of hybrid loader are improved effectively by using the automatic shift strategy.
