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。

Combined hybrid energy storage system and transmission grid model for peak shaving based on time series operation simulation

This study proposes a combined hybrid energy storage system(HESS) and transmission grid(TG) model, and a corresponding time series operation simulation(TSOS) model is established to relieve the peak-shaving pressure of power systems under the integration of renewable energy. First, a linear model for the optimal operation of the HESS is established, which considers the different power-efficiency characteristics of the pumped storage system, electrochemical storage system, and a new type of liquid compressed air energy storage. Second, a TSOS simulation model for peak shaving is built to maximize the power entering the grid from the wind farms and HESS. Based on the proposed model, this study considers the transmission capacity of a TG. By adding the power-flow constraints of the TG, a TSOS-based HESS and TG combination model for peak shaving is established. Finally, the improved IEEE-39 and IEEE-118 bus systems were considered as examples to verify the effectiveness and feasibility of the proposed model.

基于BP神经网络和二次指数平滑法组合预测模型的安徽省物流需求预测

为准确预测安徽省的物流需求,从经济发展、产量结构、地区贸易和消费水平4方面选取安徽省的地区生产总值,第一、二、三产业产值,社会消费品零售总额,固定资产投资,人均消费性支出7个影响因素作为安徽省物流需求评价指标,以安徽省货运量作为物流需求规模输出指标,采用灰色关联分析计算安徽省物流需求评价指标与物流需求规模间的关联度,判断评价指标的合理性。通过夏普利值法将BP神经网络预测模型和二次指数平滑法预测模型组合,预测2017—2021年安徽省物流需求。结果表明:BP神经网络预测模型、二次指数平滑法预测模型及二者的组合预测模型预测结果的平均相对误差分别为4.58%、6.70%、3.99%,组合预测模型的平均相对误差最小。通过组合预测模型预测2022—2024年安徽省物流需求分别为405 004.96万t、407 142.09万t、409 108.95万t,安徽省货运量呈持续增长趋势,但增幅降低。安徽省应加快传统物流向智慧物流的转移速度,扩大内需,加强物流枢纽城市间的联系,加速区域一体化发展步伐,确保物流高质量发展。

Pressure stimulated current in progressive failure process of combined coal-rock under uniaxial compression:Response and mechanism

Effective monitoring of the structural health of combined coal-rock under complex geological conditions by pressure stimulated currents(PSCs)has great potential for the understanding of dynamic disasters in underground engineering.To reveal the effect of this way,the uniaxial compression experiments with PSC monitoring were conducted on three types of coal-rock combination samples with different strength combinations.The mechanism explanation of PSCs are investigated by resistivity test,atomic force microscopy(AFM)and computed tomography(CT)methods,and a PSC flow model based on progressive failure process is proposed.The influence of strength combinations on PSCs in the progressive failure process are emphasized.The results show the PSC responses between rock part,coal part and the two components are different,which are affected by multi-scale fracture characteristics and electrical properties.As the rock strength decreases,the progressive failure process changes obviously with the influence range of interface constraint effect decreasing,resulting in the different responses of PSC strength and direction in different parts to fracture behaviors.The PSC flow model is initially validated by the relationship between the accumulated charges of different parts.The results are expected to provide a new reference and method for mining design and roadway quality assessment.

基于AR-LSTM-BP的CPI组合预测模型

针对居民消费价格指数(CPI)预测准确性的问题,提出一种AR-LSTM-BP组合预测模型.首先分别用回归(AR)、长短时记忆网络(LSTM)和BP神经网络这三种模型对CPI预测,并对预测结果进行比较分析;随后引入诱导有序加权调和平均算子(IOWHA)的概念,构建AR-LSTM-BP组合预测模型.结果表明,IOWHA组合预测模型的误差均小于单项预测模型,预测结果准确性较高,能够更好地反映CPI的波动走势.

小波降噪及改进遗传算法的BP神经网络在基坑变形中的组合应用

以某市人民医院基坑工程为例,针对实测数据建立实测数据结合BP神经网络预测模型,小波降噪结合BP神经网络模型和小波降噪结合改进遗传算法优化的BP神经网络模型,并利用误差分析理论对基坑变形数据预测效果评价。结果表明:对比3种模型实际处理、预测数据能力,实测数据结合BP神经网络模型预测精度在1%-4%之间,小波降噪结合BP神经网络模型预测精度1%-2%之间,小波降噪结合改进遗传算法优化的BP神经网络模型预测精度在1%以内,小波降噪结合改进遗传算法优化的BP神经网络模型的预测准确率最高。针对基坑变形监测,小波降噪结合改进遗传算法优化的BP神经网络模型具有更高预测精度,可为类似工程提供实际参考。

预测动车组牵引系统故障率的TSOBP-ARIMA-Prophet组合模型

针对单一模型预测故障率时的适用性差异问题,在考虑动车组牵引系统故障率数据特点的基础上,提出TSOBP-ARIMA-Prophet组合模型。首先,针对动车组牵引系统故障率的复杂非线性,引入金枪鱼群算法(TSO)优化BP模型,训练出TSOBP预测模型;其次,针对故障率的非平稳波动性,选取ARIMA预测模型;然后,针对故障率的季节周期性,选取Prophet预测模型;最后,运用方差倒数法对3个模型的预测结果赋权,得到TSOBP-ARIMA-Prophet组合模型的预测结果。以某动车组牵引系统为例,采用该组合模型预测故障率,并与3个单一模型及TSOBP-ARIMA组合模型对比验证其预测能力。结果表明:该组合模型预测时均方误差为0.0752,较TSOBP,ARIMA和Prophet模型单独预测时分别降低了45.83%,61.65%和53.42%,预测精度显著提高,且较TSOBP-ARIMA组合模型对数据趋势的感知力更优,可有效提升对动车组牵引系统故障率的预测能力。

基于GM(1,1)-BP组合模型在炮口初速预测的应用

炮口初速是影响火炮射击精度的重要因素,如何能够准确预测出炮口初速,把握短暂战机精确打击目标,成为研究的重要方向。以往对炮口初速的预测大多采用单一的预测模型进行预测,虽运算过程简单但是预测精度并不理想。为提高模型预测精度,提出在GM(1,1)、BP神经网络预测模型基础上,利用误差平方和最小原则建立组合预测模型,对炮口初速进行预测。预测结果表明组合模型预测结果精度高于其他两个单项模型。

基于BP神经网络组合模型的GPS高程拟合

为了提高BP(backpropagation)神经网络的高程拟合精度,本文在BP神经网络高程拟合方法的基础上引入了模拟退火算法(SimulatedAnnealing,SA),组成新的SA-BP高程拟合方法。该组合方法充分发挥了SA算法的全局寻优的优势,优化了BP神经网络拟合方法的初始值以及权值与阈值。将本文提出的组合高程拟合方法应用于平坦测区及复杂测区实测GPS水准点高程数据中,实验结果表明,本文提出的组合高程拟合方法可对实验高程数据进行有效拟合,拟合精度较传统的曲面拟合方法与BP神经网络方法更高,验证了本文提出方法的可靠性、优越性以及针对不同地势条件的良好适应性。

Combined model of trip mode and destination

This paper analyzes the characteristics of the destination distribution of trips and proposes a stratified sampling strategy for travel mode choice.The stratified sampling strategy can reduce the size of the alternative set;thus,the computation burden of simulation is decreased.Using the stratified sampling strategy,a combined choice model of the trip mode and destination is developed based on the Bayesian theory.Simulations are carried out to verify the proposed model.The results show that the combined choice model of the trip mode and destination can efficiently simulate travelers＇ choice behaviors.Furthermore,the forecasting accuracy of the combined choice model is higher than the one of the gravity model.Therefore,the proposed model is a powerful tool with which to analyze travelers＇ behaviors in selecting the trip mode.

Model Selection of Gas Turbine for Large Scale Gas-Fired Combined Cycle Power Plant

This paper briefs the configuration and performance of large size gas turbines and their composed combined cycle power plants designed and produced by four large renown gas turbine manufacturing firms in the world, providing reference for the relevant sectors and enterprises in importing advanced gas turbines and technologies.

基于GA-tBP模型的城市道路交通量预测

针对城市道路交通量时间差异性强的问题,提出了一种使用遗传算法(genetic algorithm,GA)优化BP(back propagation)神经网络并考虑时间特性的模型(GA-tBP)预测道路交通量。从月、周、日3个维度统计分析了历史交通量数据存在的差异,得出影响城市道路交通量的时间因素。以江西省南昌市赣江中大道交通量为例,对未来24 h内每5 min交通量进行预测,对比分析了不同模型在预测精度和学习能力等方面的表现。研究结果表明,同不考虑时间特性的模型及其他传统预测模型相比较,GA-tBP模型的预测效果最好,其均方误差(mean squared error, MSE)及平均绝对误差(mean absolute error, MAE)分别为14.87 veh/5 min和2.44 veh/5 min,故该模型具有可行性和有效性。

优化灰色BP神经网络组合模型在基坑沉降监测中的应用

基坑沉降监测是基坑工程施工中的一个重要环节.为准确预测基坑沉降,采用优化灰色GOM(1,1)模型与BP神经网络组合预测.GOM(1,1)模型是在GM(1,1)模型原理上对其参数进行优化,使拟合值接近观测值,BP神经网络具有较强的非线性数据处理能力,优化组合模型结合两者优点应用于基坑沉降监测,得出优化后的组合模型对基坑沉降数据预测优于普通组合模型.

Combined model based on optimized multi-variable grey model and multiple linear regression

The construction method of background value is improved in the original multi-variable grey model （MGM（1,m）） from its source of construction errors. The MGM（1,m） with optimized background value is used to eliminate the random fluctuations or errors of the observational data of all variables, and the combined prediction model together with the multiple linear regression is established in order to improve the simulation and prediction accuracy of the combined model. Finally, a combined model of the MGM（1,2） with optimized background value and the binary linear regression is constructed by an example. The results show that the model has good effects for simulation and prediction.

A Numerical Study on Effects of Land-Surface Heterogeneity from' Combined Approach' on Atmospheric ProcessPart II: Coupling-Model Simulations

Two land surface schemes, one the standard Biosphere / Atmosphere Transfer Scheme Version ie (BOZ) and the other B1Z based on B0Z and heterogeneously-treated by' combined approach' , were co 'pled to the meso-scale model MM4, respectively. Through the calculations of equations from the companion paper, parameters representing land surface heterogeneity and suitable for the coupling models were found out. Three cases were simulated for heavy rainfalls during 36 hours, and the sensitivity of short-term weather modeling to the land surface heterogeneity was tested. Through the analysis of the simulations of the three heavy rainfalls, it was demonstrated that BIZ, compared with BOZ, could more realistically reflect the features of the land surface heterogeneity, therefore could more realistically reproduce the circulation and precipitation amount in the heavy rainfall processes of the three cases. This shows that even short-term weather is sensitive to the land surface heterogeneity, which is more obvious with time passing, and whose influence is more pronounced in the lower layer and gradually extends to the middle and upper layer. Through the analysis of these simulations with BlZ, it is suggested that the bulk effect of smaller-scale fluxes (i.e., the momentum, water vapor and sensible heat fluxes) near the s ig nificantly-heterogeneous land surface is to change the larger-scale (i.e., meso-scale) circulation, and then to influence the development of the low-level jets and precipitation. And also, the complexity of the land-atmosphere interaction was shown in these simulations.

基于残差修正的ARIMA-BP组合模型在中国戊型肝炎发病预测中的应用

目的:探讨基于残差修正的ARIMA-BP组合模型在中国戊型肝炎传染病流行趋势预测中的作用。方法:对2004-2017年中国戊型肝炎统计数据采用SPSS软件分别建立ARIMA和ARIMA-BP模型,将2018年1-12月戊肝数据作为对比值,对模型的预测效果进行对比分析。结果:2种模型的预测结果评价指标中,ARIMA-BP组合模型的E、ER、MAE、MSE、MAPE指标整体上均小于ARIMA模型。结论:ARIMA-BP组合模型的预测效果优于ARIMA模型,可用于我国戊型肝炎发病趋势的早期预测。

A combined numerical tidal model for the Hangzhou Bay and Qiantang River

-In order to avoid prescribing open boundary condition on the upstream side of the Hangzhou Bay, in numerical simulation of the tides and residual currents of the Bay, a 1-D model for the Qiantang River is connected to the 2-D model for the Hangzhou Bay. The harmonic constants of diurnal constituent [ (K1+O1)/2],semidiurnal constituent (M2) and shallow water constituent (M4) are obtained. The results produced by the combined model are in better agreement with the observed ones than those produced solely by the original 2-D model. The combined model gives much more reliable results for tide-induced residual water level and current.

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.

Compression failure conditions of concrete-granite combined body with different roughness interface

Bedrock and concrete lining are typical composite structures in the engineering field and the stability of the geological body and engineering body is directly connected to the mechanical properties of the composite body.Under this background,the study provides the transverse isotropic equivalent model of concrete-granite double-layer composite based on the notion of strain energy equivalence.Assuming that the strength failure of concrete and granite meets the Mohr-Coulomb criterion,then the strength failure model of the combined body considering the joint roughness coefficient(JRC)is derived,and the influences of JRC,the height ratio of concrete to granite,and confining pressure on the strength failure characteristics of the combined body are emphatically analyzed.Finally,the model applicability is illustrated by the uniaxial and triaxial compression tests on concrete monomer,granite monomer and concretegranite composite samples(CGCSs)with different JRCs.The results revealed that the compressive strength of the composite is closer to the concrete with lower strength in the combined body under different confining pressures.Adding interface roughness causes to raise the compressive strength of the composite due to interfacial adhesion between concrete and granite,and a slowing growth trend is observed in compressive strength as roughness.The model can provide a certain reference for the stability design and evaluation of engineering rock mass.

Study of establishing disease-syndrome combined with animal model for immune thrombocytopenic purpura without additional conditions

Objective:To explore the feasibility of establishing the disease-syndrome combined animal model for immune thrombocytopenic purpura(ITP)without additional conditions.Methods:Three batches of data related to the ITP model mice obtained by replication at different time were analyzed,and whether the APS-injected model mice replicated through the passive immune modeling method could simulate the pathogenesis and clinical characteristics of human ITP was evaluated according to the differentiation criteria for diseasesyndrome combined model.Results:The APS-injected replicated ITP model mice possessed the following traits:(1)Compared with the normal group,the platelet count was significantly decreased,and coagulation time was significantly increased in the model group(P<.01).(2)Compared with the normal group,the medullary thrombocytogenous megakaryocytes were significantly decreased(P<.05,.01,.001).(3)The APS-injected sites and other parts of the model mice had spontaneous hemorrhage.(4)Behavioral changing signs were observed 1 week after the modeling(i.e.low activity,delayed activity,poor appetite,skin petechia/hemorrhage and spontaneous hemorrhage at the injected sites or other parts),and were getting more and more severe.Conclusion:According to the syndrome differentiation criteria for disease-syndrome combined model of ITP,the APS-injected animal model of ITP replicated through the passive immune modeling method without additional conditions possesses the characteristics of disease-syndrome combined model.It provides an ideal tool for the development of traditional Chinese medicine pharmacology experiment.