Subdivision surface modeling system based on arbitrary topological curves network and combined subdivision

Arbitrary topological curve network has no restriction in topology structure,so it has more powerful representing ability in defining complex surfaces.A complex surface modeling system is presented based on arbitrary topological curve network and the improved combined subdivision method,its functions including creating and editing curve network,and generating and modifying curve network＇s interpolated surface.This modeling system can be used to the process of products＇concept design,and its applications is also significant to the development of subdivision method.

Forecasting Alzheimer’s Disease Using Combination Model Based on Machine Learning

As the acceleration of aged population tendency, building models to forecast Alzheimer’s Disease (AD) is essential. In this article, we surveyed 1157 interviewees. By analyzing the results using three machine learning methods—BP neural network, SVM and random forest, we can derive the accuracy of them in forecasting AD, so that we can compare the methods in solving AD prediction. Among them, random forest is the most accurate method. Moreover, to combine the advantages of the methods, we build a new combination forecasting model based on the three machine learning models, which is proved more accurate than the models singly. At last, we give the conclusion of the connection between life style and AD, and provide several suggestions for elderly people to help them prevent AD.

Grey series time-delay predicting model in state estimation for power distribution networks

A new combined model is proposed to obtain predictive data value applied in state estimation for radial power distribution networks. The time delay part of the model is calculated by a recursive least squares algorithm of system identification, which can gradually forget past information. The grey series part of the model uses an equal dimension new information model (EDNIM) and it applies 3 points smoothing method to preprocess the original data and modify remnant difference by GM(1,1). Through the optimization of the coefficient of the model, we are able to minimize the error variance of predictive data. A case study shows that the proposed method achieved high calculation precision and speed and it can be used to obtain the predictive value in real time state estimation of power distribution networks.

Combined back-analysis method of ground stress based on refined geological modeling

A new back-analysis method of ground stress is proposed with comprehensive consideration of influence of topography, geology and nonlinear physical mechanical properties of rock on ground stress. This method based on non-uniform rational B-spline (NURBS) technology provides the means to build a refined three-dimensional finite element model with more accurate meshing under complex terrain and geological conditions. Meanwhile, this method is a back-analysis of ground stress with combination of multivariable linear regression model and neural network (ANN) model. Firstly, the regression model is used to fit approximately boundary loads. Regarding the regressed loads as mean value, some sets of boundary loads with the same interval are constructed according to the principle of orthogonal design, to calculate the corresponding ground stress at the observation positions using finite element method. The results (boundary loads and the corresponding ground stress) are added to the samples for ANN training. And on this basis, an ANN model is established to implement higher precise back-analysis of initial ground stress. A practical application case shows that the relative error between the inversed ground stress and observed value is mostly less than 10 %, which can meet the need of engineering design and construction requirements.

基于注意力循环神经网络的联合深度推荐模型

为了向用户推荐符合兴趣偏好的项目,设计一种基于注意力循环神经网络的联合深度推荐模型。将双层注意力机制设置于网络中,该模型由五个部分构成,在输入层中生成联合深度推荐模型的输入矩阵,通过序列编码层对项目评论文本语义展开正向和反向编码,获得隐藏状态输出,并将其输入双层注意力机制中,提取项目特征,利用全连接层提取用户偏好特征。在预测层中建立项目与用户的交互模型,获得项目评分,为用户推荐高评分的项目。为了提高模型精度,加权融合MSE损失函数、CE损失函数和RK损失函数建立组合损失函数,对深度联合训练模型展开训练,提高模型的推荐性能。仿真结果表明,所提方法具有良好的推荐效果,能够适应不断变化的市场需求和用户行为。

基于麻雀搜索算法和长短期记忆神经网络的轨道交通站点客流预测

准确的短时客流预测可以为城市轨道交通的良好运营提供保障,但轨道交通的短时客流具有非线性和高随机性等特点,为了提高对短时客流的预测精度,提出将ISSA算法和LSTM模型进行组合,构建城市轨道交通短时客流预测模型.针对SSA算法收敛速度慢,容易陷入局部最优解的问题,引入黄金莱维飞行策略,通过动态调整探索者移动步长的方法,使得它在未知范围内搜索时,能够覆盖更大的范围,提高SSA算法全局搜索的能力.通过使用ISSA算法对LSTM模型的隐含层、学习率和迭代次数的神经元个数进行优化,构建ISSA-LSTM组合预测模型,用于城市轨道交通短时客流的预测.将该模型与BP、LSTM和SSA-LSTM等3种短时客流预测模型进行对比,结果表明:在针对工作日和非工作日客流的预测中,ISSA-LSTM模型预测误差最小,具有较好的预测效果.

Combined Prediction for Vehicle Speed with Fixed Route

Achieving accurate speed prediction provides the most critical support parameter for high-level energy management of plug-in hybrid electric vehicles.Nowadays,people often drive a vehicle on fixed routes in their daily travels and accurate speed predictions of these routes are possible with random prediction and machine learning,but the prediction accuracy still needs to be improved.The prediction accuracy of traditional prediction algorithms is difficult to further improve after reaching a certain accuracy;problems,such as over fitting,occur in the process of improving prediction accuracy.The combined prediction model proposed in this paper can abandon the transitional dependence on a single prediction.By combining the two prediction algorithms,the fusion of prediction performance is achieved,the limit of the single prediction performance is crossed,and the goal of improving vehicle speed prediction performance is achieved.In this paper,an extraction method suitable for fixed route vehicle speed is designed.The application of Markov and back propagation(BP)neural network in predictions is introduced.Three new combined prediction methods,all named Markov and BP Neural Network(MBNN)combined prediction algorithm,are proposed,which make full use of the advantages of Markov and BP neural network algorithms.Finally,the comparison among the prediction methods has been carried out.The results show that the three MBNN models have improved by about 19%,28%,and 29%compared with the Markov prediction model,which has better performance in the single prediction models.Overall,the MBNN combined prediction models can improve the prediction accuracy by 25.3%on average,which provides important support for the possible optimization of plug-in hybrid electric vehicle energy consumption.

Intelligent predictive model of ventilating capacity of imperial smelt furnace

In order to know the ventilating capacity of imperial smelt furnace(ISF), and increase the output of plumbum, an intelligent modeling method based on gray theory and artificial neural networks(ANN) is proposed, in which the weight values in the integrated model can be adjusted automatically. An intelligent predictive model of the ventilating capacity of the ISF is established and analyzed by the method. The simulation results and industrial applications demonstrate that the predictive model is close to the real plant, the relative predictive error is 0.72%, which is 50% less than the single model, leading to a notable increase of the output of plumbum.

Fast Calculation Method of Energy Flow for Combined Electro-Thermal System and Its Application

In recent years, Combined electro-thermal system has developed rapidly. In order to provide the initial data for the analysis of the combined electro-thermal system, a practical energy flow calculation method for the combined electro-thermal system is proposed in this paper. Based on the detailed analysis of the topology structure of the heating network and its hydraulic and thermodynamic model, the forward-backward sweep method for the heat flow of the heating network is established, which is more suitable for the actual radial heating network. The electric and thermal coupling model for heating source, such as thermoelectric unit and electric boiler is established, and the heat flow of heating network and the power flow of power grid are calculated orderly, thus a fast calculation method for the combined electro-thermal system is formed. What’s more, a combined electro-thermal system with two-stage peak-shaving electric boiler is used as the example system. This paper validates the effectiveness and rapidity of this method through the example system, and analyzes the influence for the energy flow of combined electro-thermal system caused by the operating parameters such as the installation location of electric boiler, the outlet water temperature of heat source and the outlet flow rate, etc.

白条猪价格预测模型构建

【目的】增强农产品价格预测准确度,为农产品价格的有效预测提供参考。【方法】以河南省白条猪每周平均批发价格为研究对象,提出一种基于序列分解、主成分分析和神经网络(CEEMDAN-PCA-CNN-LSTM)的白条猪价格预测方法。首先,使用自适应白噪声完全集合模态分解方法(CEEMDAN)对白条猪价格序列进行分解;其次,选用皮尔逊相关系数筛选影响价格波动的相关因素;再次,利用主成分分析(PCA)对影响因素及分解得到的子序列降维处理并作为原始价格序列的特征值,并行输入到作为编码器的卷积神经网络(CNN)中进行特征提取;最后,引入长短期记忆网络(LSTM)作为解码器输出得到预测结果。将该方法应用于河南省白条猪每周平均价格数据,与LSTM、门控循环单元(GRU)、CNN、基于卷积的长短期记忆网络(ConvLSTM)模型进行比较。【结果】CEEMDAN-PCA-CNN-LSTM组合模型预测方法得到的平均绝对误差分别降低了44.95%、27.30%、28.13%、43.17%。【结论】CEEMDAN-PCA-CNN-LSTM模型对于河南省白条猪市场价格的预测性能更优,有助于相关部门针对河南省白条猪价格波动做出科学决策。

某纯电驱动重载车辆能耗预测模型

高精度能耗预测模型是准确预测车辆续驶里程的重要前提。针对载荷大幅度变化且非结构化道路运行的纯电驱动重载车辆,建立其组合能耗模型,该模型由能耗计算基本模型与长短时记忆(Long Short-Term Memory,LSTM)神经网络差值修正两部分组成。基于能量流动过程驱动电机和变速器效率建模,结合汽车行驶动力学建立能耗计算基本模型;采用LSTM神经网络来修正基本模型能耗预测结果与车辆典型工况功率测试值的差值,有效提高了大幅变载荷且低信噪比坡度环境下的车辆能耗预测精度,因此组合能耗模型具有参数简单和模型拟合不需解释能耗规律的优点。经试验测试分析,与VT-Micro能耗模型和径向基(Radial Basis Function,RBF)神经网络能耗模型相比,所提组合能耗模型的功率预测平均误差率分别降低了17.76%和3.35%,能够实现纯电驱动重载车辆复杂工况下能耗的准确实时预测。

基于排序蒸馏的序列化推荐算法

为解决当前基于知识蒸馏的推荐算法排名有效性和效率低,以及现有知识蒸馏模型更强调的是静态和单一知识迁移的问题,提出一种基于排序蒸馏的序列化推荐算法。训练一个性能优越、规模大的教师模型,训练一个符合移动终端设备的小模型即学生模型,使学生模型在教师模型的指导下学习排序。学生模型实现了与教师模型相似的排名性能,且学生模型规模较小提高了在线推荐效率。通过在数据集MovieLens和Gowalla上的实验,验证了该模型增强了学生模型的学习效果,缓解了学生模型学习不充分导致排名不佳的问题。模型可以自然地运用于序列化推荐的模型中,具有很好的通用性。

ML组合的CYGNSS海面风速反演质量控制模型

卷积神经网络(CNN)可用于气旋全球导航卫星系统(CYGNSS)的海面风速反演。虽然在模型训练前设置了质量控制指标来检测和削弱CYGNSS的异常观测数据,但CYGNSS观测数据中仍存在异常值导致模型反演精度降低,甚至出现错误反演结果。因此,提出一种基于机器学习(ML)组合的海面风速反演模型。在基于CNN回归模型的CYGNSS反演海面风速基础上,ML分类模型生成CNN回归结果的质量标志位,该标志位可以检测并删除CNN回归结果的异常值,进一步提高风速反演结果的数据质量,ML分类模型能够更好地考虑各种数据误差之间的相互作用,而不是单独使用每个条件的阈值,以达到更优的海面风速反演精度的效果。实验对比了Logistic回归(LR)、决策树(DT)、朴素贝叶斯模型、K最邻近(KNN)算法、神经网络(NN)模型、支持向量机(SVM)算法等6个分类模型,其中,基于KNN算法的分类模型对风速反演质量控制的效果最优。所提风速反演组合模型显著提高了反演结果的精度,在0~20 m/s区间内,异常样本过滤率为81.27%,在所有被过滤的数据中,过滤正确率为86.03%;风速反演误差的均方根误差从无ML分类模型的1.7 m/s降低到有ML分类模型的1.44 m/s,其中,训练样本为0~10 m/s的反演结果精度提升效果较为明显,证明了所提风速反演组合模型对风速质量控制的有效性。

SARIMA-GRU组合模型的水位预测

相较于传统的单一模型,组合模型在一定条件下具有更优的预测精度。为验证组合模型是否有利于提高模型的预测精度,本文以长江中游支流澧水石龟山水电站的水位数据为基础,建立SARIMA模型和GRU神经网络模型,并将这两种模型基于方差倒数法和IOWA算子进行组合,最后比较单一模型和组合模型在该水位数据集上的预测精度差异。结果表明,适当的组合方式有利于提高模型预测精度,基于IOWA算子的组合模型具优良的预测性能。

基于城市复合网络的出行交通分配组合模型研究

文章提出了一种交通分配组合模型,解决传统四阶段方法缺乏联系导致误差逐渐放大的问题。文章基于构建的城市复合网络,将交通方式划分和交通分配整合在一起,综合考虑交通方式选择和交通分配的影响。通过基于A*算法的备选路径集查找方法,求解给定OD上的k短路径情况。采用广义费用公式对多方式出行效用进行计算,将费用、时间和换乘行为进行统一量化。最后,建立交通方式划分与交通分配组合模型,采用多层次迭代平衡求解,优化交通方式分担率。算例分析验证了组合模型在流量分配方面的优势,具有更好的路段流量均衡性和较低的阻抗时间。该模型可为城市交通规划和出行预测提供参考。

M-CM-GA-BP算法的地表移动变形参数预测模型

针对复杂的开采沉陷预测问题,研究22个工作面采动地表移动变形参数变化规律,提出了一种基于M-CM-GA-BP算法求取地表移动变形参数的预测模型。通过线性加权组合预测方法和遗传算法优化BP神经网络的权值和阈值,融合多元回归模型来提高地表移动变形参数的求取精度,以地表下沉系数q为例,将该模型与其他预测模型预测性能进行对比分析,验证模型的准确性。结果表明,该模型能够有效地提高地表移动变形参数的预测精度,模型的平均相对误差为1.294、均方根误差为0.013,为地表移动变形参数预测提供了一种可行方法。

西南某机场跑道沉降预测模型

机场道面沉降,严重影响机场安全运行。准确预测跑道工后沉降,对机场的建设与运行极为重要。以西南某机场跑道沉降变形的观测数据为依据,分别用双曲线模型、对数模型、指数模型以及灰色预测模型,对跑道沉降进行预测和对比分析,解决了小样本数下曲线预测精度较低及灰色模型对非线性预测准确度差等问题,提高了预测的精度;同时通过BP神经网络对组合预测模型的残差进行修正,最大限度地提高模型预测的精度和效果,为地基沉降预测提供借鉴。

配电网负荷预测中信号分解和预测模型组合的双层优化策略

负荷时间序列的波动性和非线性特征的加剧对负荷预测方法提出了更高的要求,而常规组合预测方法针对海量负荷数据存在应用局限性问题。为此,提出了配电网负荷预测中时序分解方法和预测模型组合的双层优化策略。首先针对某一负荷预测数据,在时序信号分解层配置权重,以负荷均方根误差最小寻优各分解方法的权重系数,进而获得各时序信号分解方法的最优组合;在此基础上,在预测模型层进行组合方案寻优,通过配置权重系数以获得各预测模型的最优组合,进一步提升负荷预测的精度。仿真结果表明,所提策略可根据预测对象的特征优化组合各信号分解方法和预测模型,降低了配电网负荷序列的非平稳性对预测精度的影响。

基于CNN-LSTM电力消耗预测模型及系统开发

有效预测电能负荷,对提高电力负荷时间序列测量准确度及合理制定用电能管理措施具有重要意义。针对传统预测模型在电能负荷预测中无法充分挖掘时间序列数据中隐藏特征的问题,基于电能数据时间序列的趋势,融合数值信息提出一种卷积神经网络(convolutional neuralnetwork,CNN)与长期短期记忆循环神经网络(long short-term memory network,LSTM)相结合的混合多隐层CNN-LSTM电力能耗预测模型。首先,通过设定最小目标函数作为优化目标,Adam优化算法更新神经网络的权重,并对网络层和批大小进行自适应调优以确定最佳层数和批大小。其次,构建混合多隐层模型并进行隐层组合优化与讨论,确定最佳时间维度的参数,进行时间维度的特征学习进而预测下一时间序列的耗电量。然后以某公司的电力负荷数据为例进行验证,并与LSTM、CNN、RNN等模型的预测结果分析比较。结果表明上述混合多隐层模型预测准确度达98.94%,平均绝对误差(MAE)达到0.0066,均优于其他相关模型,证明以上混合预测模型在电力负荷预测精度方面具有更好的性能。基于上述理论,开发了能耗监控决策系统,实现设备状态实时监控和能耗智能预测功能,为解决传统制造业能耗需求不精确和能源库存浪费问题提供参考和指导。

“分解-校正-集成”模式下基于深度信念网络模型的径流预测

精准的短期径流预测可为流域内水资源规划、防洪调度及抗旱减灾工作提供重要的科学依据。为减小模型的系统误差,提高径流预测精度,在“分解-集成”模式的基础上提出“分解-校正-集成”框架,构建EEMD-DBN-EnKF、VMD-DBN-EnKF模型。利用集合卡尔曼滤波数据同化算法对偏离实测径流过大的分量校正以降低分解子序列在预测中产生的系统误差,并与未修正的EEMD-DBN、VMD-DBN模型及单一DBN模型进行了对比分析。结果表明:基于模态分解的组合模型较单一模型RMSE减小了至少23%,NSE与R^(2)增加了21%以上;基于径流分量校正的组合模型相较于模态分解的组合模型各评价系数有所提升,其中VMD-DBN-EnKF预测模型误差最小,效果最优,NSE与R^(2)达到0.89以上,其次依次为EEMD-DBN-EnKF>VMD-DBN>EEMD-DBN。综上“分解-校正-集成”模式的预测框架在玛纳斯河流域具有良好的适用性,可为玛纳斯河径流短期预报提供技术支持。