基于GA-BP神经网络的新疆南疆核桃树生长模型研究

文章提出了一种利用遗传算法优化BP神经网络的核桃树生长模型来预测核桃树的树高、胸径的方法,通过优化BP神经网络的权值和阈值建立GA-BP模型,与多元线性回归模型的预测结果进行比较。结果表明:采用遗传算法优化后的模型具有更高的预测精度,对核桃树生长预测具有指导意义。

Prediction of Sedimentary Microfacies Distribution by Coupling Stochastic Modeling Method in Oil and Gas Energy Resource Exploitation

In view of the problem that a single modeling method cannot predict the distribution of microfacies, a new idea of coupling modeling method to comprehensively predict the distribution of sedimentary microfacies was proposed, breaking the tradition that different sedimentary microfacies used the same modeling method in the past. Because different sedimentary microfacies have different distribution characteristics and geometric shapes, it is more accurate to select different simulation methods for prediction. In this paper, the coupling modeling method was to establish the distribution of sedimentary microfacies with simple geometry through the point indicating process simulation, and then predict the microfacies with complex spatial distribution through the sequential indicator simulation method. Taking the DC block of Bohai basin as an example, a high-precision reservoir sedimentary microfacies model was established by the above coupling modeling method, and the model verification results showed that the sedimentary microfacies model had a high consistency with the underground. The coupling microfacies modeling method had higher accuracy and reliability than the traditional modeling method, which provided a new idea for the prediction of sedimentary microfacies.

基于GA-SA算法的机器人几何参数误差辨识

几何参数误差对机器人末端绝对定位精度影响最大,而几何误差参数辨识是一个高维非线性问题,求解困难,所以建立一种简单高效的辨识算法是有必要的,本文提出了遗传模拟退火算法(GA-SA)对机器人几何参数误差辨识。以机器人末端位姿误差最小为目标,采用遗传模拟退火算法辨识机器人几何参数误差,以ABB IRB120为算例迭代1100次,遗传算法在200代陷入局部最优,模拟退火参与后最终适应度为0.0914。误差补偿结果表明:机器人末端位置误差沿X,Y,Z轴方向分别降低了88.05%,81.73%,83.72%,姿态误差分别降低了93.92%,83.64%,83.44%,证明遗传模拟退火算法可以有效辨识机器人几何参数误差,提高误差补偿后的机器人末端位姿精度。

基于GA-BP神经网络长服役期内结构混凝土的强度演变预测

为研究长服役期内既有混凝土结构的强度演变规律及其预测模型,以唐包铁路、西户铁路等实际工程为研究背景,以服役时间为2、16、25、30、40、52、66、88、95和100 a的在役桥涵为研究对象,基于混凝土回弹法,开展役桥涵混凝土强度试验,分析长服役期内既有桥涵混凝土强度动态发展过程。同时,基于试验实测混凝土强度数据与收集的230组同类条件下在役桥涵(服役时间2~88 a)混凝土强度数据,构建GA-BP神经网络混凝土强度预测模型。此外,为提高模型可应用性,基于高精度GA-BP神经网络强度预测模型,建立一般矩阵公式和简化公式。基于本文构建的混凝土强度预测模型,分析该类地区(试验中已调研区域)长服役期内混凝土结构的强度演变规律。研究结果表明:相较于既有混凝土强度预测模型,本文构建的GA-BP神经网络混凝土强度预测模型可有效预测不同服役时间下的混凝土强度,预测数据的平均绝对百分比误差为8.76%,决定系数为0.83。本文简化公式(C25)精度较高,平均绝对百分比误差为6.6%,为便于简化计算,推荐简化公式(C25)作为长服役期内混凝土强度预测公式。百年服役期内混凝土强度经历2个时间阶段,即混凝土强度缓慢上升期(1~49 a)、混凝土强度快速下降期(49~100 a)。随混凝土结构服役时间增加,混凝土结构劣化速率增加,导致混凝土结构在长期服役过程中,混凝土强度不能满足混凝土结构服役要求。

The Cloud Model for Climate Change

In 1995, the Intergovernmental Panel on Climate Change (IPCC) released a thermodynamic model based on the Greenhouse Effect, aiming to forecast global temperatures. This study delves into the intricacies of that model. Some interesting observations are revealed. The IPCC model equated average temperatures with average energy fluxes, which can cause significant errors. The model assumed that all energy fluxes remained constant, and the Earth emitted infrared radiation as if it were a blackbody. Neither of those conditions exists. The IPCC’s definition of Climate Change only includes events caused by human actions, excluding most causes. Satellite data aimed at the tops of clouds may have inferred a high Greenhouse Gas absorption flux. The model showed more energy coming from the atmosphere than absorbed from the sun, which may have caused a violation of the First and Second Laws of Thermodynamics. There were unexpectedly large gaps in the satellite data that aligned with various absorption bands of Greenhouse Gases, possibly caused by photon scattering associated with re-emissions. Based on science, we developed a cloud-based climate model that complied with the Radiation Laws and the First and Second Laws of Thermodynamics. The Cloud Model showed that 81.3% of the outgoing reflected and infrared radiation was applicable to the clouds and water vapor. In comparison, the involvement of CO2 was only 0.04%, making it too minuscule to measure reliably.

基于GA-BP算法的充电站负效应评价

由于电动汽车出行需求存在随机性、充电信息不精准等问题,造成城市交通能源供应站承载力与补能需求车辆的时空错配,导致充电站产生了拥堵排队、能源消耗不合理等负效应。基于此,文中从负效应最小化的视角构建了充电站的负效应评价指标体系,综合考虑交通效率影响、站点服务影响、电网负荷影响等3个因素,采用GA-BP神经网络构建了充电站负效应评估模型。最后,以重庆市南岸区某充电站为例,验证了该方法的适用性与有效性。

基于GA-PSO算法的冻土本构模型参数识别

遗传算法(GA)与粒子群算法(PSO)分别具有缺乏目标导向性和易陷入局部最优的缺点,但同时分别具有全局搜索能力强与能有效传递优势信息的优点。本文以GA计算步结合精英保留策略作为PSO计算步的优势信息,避免PSO算法陷入局部最优,以PSO计算步结合非精英优化策略作为GA计算步的导向信息,克服GA算法缺乏目标导向的问题,建立了GA-PSO新算法。其具体过程为,通过采用GA计算步对解空间进行全局搜索并对精英个体进行保留,进一步,将适应度较差的个体利用PSO计算步进行优化。基于多峰函数的验证结果表明,GA-PSO算法在解空间中具有更强的全局搜索能力,同时具有更快的收敛速度。将GA-PSO算法应用到冻土非正交弹塑性本构模型的参数识别中,通过模型的参数识别以及模型预测结果对比与验证,结果表明GA-PSO算法能够有效识别冻土非正交弹塑性本构模型的参数,提升了模型的预测效果。

基于Bootstrap和GA-Elman的土质滑坡坡表变形区间预测

坡体变形是表征边坡稳定性最直观的指标。如何科学合理地解译其演化特征,对滑坡灾害预警防范具有重大的工程意义及科学价值。由于滑坡灾害的影响因素中,很多不确定因素都不可能完全准确地定量分析,只能从定性层面建立影响因素与坡体变形的关系,为了解决滑坡确定性预测方法中未考虑预测与数据误差的问题,量化滑坡点预测结果中的不确定因素的影响,依托滑坡坡表变形点预测方法,提出基于残差Bootstrap与GA-Elman神经网络的区间预测方法。相比于传统方法,通过变形伪数据集的建立、GA-Elman模型的迭代训练与总方差估计、ELM网络残差训练与随机误差方差估计等步骤创建的区间预测方法在预测可靠性、区间宽度、针对特殊变化坡体的预测灵活度等方面都有显著提升。利用Bootstrap重抽样模型、GA-Elman神经网络预测算法以及区间预测理论方法,建立基于Bootstrap和GA-Elman的滑坡变形区间预测模型。研究导致滑坡变形的不同影响因素、预测模型参数及置信区间等对于区间预测模型效果的影响,并运用到现场滑坡中。分析结果表明,所提出的方法可适用于现场滑坡,更好地将滑坡降雨等影响因素与坡体表观变形建立联系,为滑坡灾害的提前预警与防治提供可靠准确的信息支撑。

Creep behaviour and constitutive model of coal filled with gas

Coal exhibits different creep behaviours when filled with different amounts of gas. Creep tests of coal filled with 0 and 0.5 MPa gas were performed, and strain under different axial stress was compared.The three creep constitutive models which were analysed using the method fitting experimental data for determining which creep model can reflect the creep process of the test best. The results show that the deformation of coal filled with 0.5 MPa gas is more higher than that of coal filled with 0 MPa gas under the same axial stress. Gas plays a positive effect on the deformation of coal process and will accelerate creep process. And gas will reduce coal intensity and change coal creep properties.Compared with Nishihara Model and Extensional Nishihara Model, Burgers Model can reflect the three stages of creep process of coal filled with gas better. The research results can contribute to reveal coal and gas outburst mechanism.

Distribution Characteristics and Accumulation Model for the Coal-formed Gas Generated from Permo-Carboniferous Coal Measures in Bohai Bay Basin, China: A Review

Coal-formed gas generated from the Permo-Carboniferous coal measures has become one of the most important targets for deep hydrocarbon exploration in the Bohai Bay Basin,offshore eastern China.However,the proven gas reserves from this source rock remain low to date,and the distribution characteristics and accumulation model for the coal-formed gas are not clear.Here we review the coal-formed gas deposits formed from the Permo-Carboniferous coal measures in the Bohai Bay Basin.The accumulations are scattered,and dominated by middle-small sized gas fields,of which the proven reserves ranging from 0.002 to 149.4×108 m3 with an average of 44.30×108 m3 and a mid-point of 8.16×108 m3.The commercially valuable gas fields are mainly found in the central and southern parts of the basin.Vertically,the coal-formed gas is accumulated at multiple stratigraphic levels from Paleogene to Archaeozoic,among which the Paleogene and PermoCarboniferous are the main reservoir strata.According to the transporting pathway,filling mechanism and the relationship between source rocks and reservoir,the coal-formed gas accumulation model can be defined into three types:"Upward migrated,fault transported gas"accumulation model,"Laterally migrated,sandbody transported gas"accumulation model,and"Downward migrated,sub-source,fracture transported gas"accumulation model.Source rock distribution,thermal evolution and hydrocarbon generation capacity are the fundamental controlling factors for the macro distribution and enrichment of the coal-formed gas.The fault activity and the configuration of fault and caprock control the vertical enrichment pattern.

Analysis of gas transport behavior in organic and inorganic nanopores based on a unified apparent gas permeability model

Different from the conventional gas reservoirs,gas transport in nanoporous shales is complicated due to multiple transport mechanisms and reservoir characteristics.In this work,we presented a unified apparent gas permeability model for real gas transport in organic and inorganic nanopores,considering real gas effect,organic matter(OM)porosity,Knudsen diffusion,surface diffusion,and stress dependence.Meanwhile,the effects of monolayer and multilayer adsorption on gas transport are included.Then,we validated the model by experimental results.The influences of pore radius,pore pressure,OM porosity,temperature,and stress dependence on gas transport behavior and their contributions to the total apparent gas permeability(AGP)were analyzed.The results show that the adsorption effect causes Kn(OM)>Kn(IM)when the pore pressure is larger than 1 MPa and the pore radius is less than 100 nm.The ratio of the AGP over the intrinsic permeability decreases with an increase in pore radius or pore pressure.For nanopores with a radius of less than 10 nm,the effects of the OM porosity,surface diffusion coefficient,and temperature on gas transport cannot be negligible.Moreover,the surface diffusion almost dominates in nanopores with a radius less than 2 nm under high OM porosity conditions.For the small-radius and low-pressure conditions,gas transport is governed by the Knudsen diffusion in nanopores.This study focuses on revealing gas transport behavior in nanoporous shales.

基于RT-GAS Copula模型的经济金融行业非对称相依性及风险溢出研究

考虑到实体经济行业与金融行业间的相依关系存在杠杆效应,本文采用GJR门限结构将杠杆效应纳入包含高频信息的广义已实现自回归得分Copula(GRAS Copula)模型中,构建广义已实现门限自回归得分Copula(RT-GAS Copula)模型。利用RT-GAS Copula模型揭示实体经济行业与金融行业间时变相依关系对行业收益的非对称响应,并进一步分析经济金融行业间风险溢出的非对称性和时变特征。研究发现:各行业间的相依关系存在显著的杠杆效应,某一行业收益的上涨和下跌对该行业与其他行业间时变相依关系的影响是非对称的;行业间的相依关系会受到国家调控政策和各类市场风险事件的影响;行业间的系统性风险溢出存在非对称性,且会受到严重风险事件的影响。此外,有效性检验结果表明,当行业间相依关系存在显著杠杆效应时,RT-GAS Copula模型的拟合和预测能力优于现有时变Copula模型。

Water modeling of molten steel flow in a multi-strand tundish with gas blowing

Fluid flow characteristics in a four-strand tundish with gas blowing were studied by water modeling experiments.It is found that gas blowing can greatly improve the flow characteristics in the tundish with a turbulence inhibitor.It dramatically increases the peak concentration time,and greatly decreases the dead volume,and reduces the minimum residence time.The gas blowing location,gas flow rate,and porous plug area greatly influence the flow characteristics in the tundish; the gas blowing location near the baffle,smaller gas flow rate,and smaller porous plug area are better for improving the fluid flow characteristics.Using gas blowing can reduce the difference of flows at the middle outlets and side outlets for the multi-strand tundish.Bubbles produced by gas blowing can absorb small inclusions and provide the condition for inclusion collision and aggregation.Therefore,introducing gas blowing into a tundish and combining the turbulence inhibitor can improve inclusion floating and removal,and the cleanness of molten steel can be advanced.

Mathematical Model of Gas Permeation Through PTFE Porous Membrane and the Effect of Membrane Pore Structure

Membrane-based separation processes are new technology combined membrane separation with conventional separation. Hydrophobic porous membranes are often used in these processes. The structure of hydrophobic porous membrane has significant effect on mass transfer process. The permeabilities of five kinds of gas, He, N2,O2, CO2 and water vapor, across six polytetrafluoroethylene(PTFE) fiat membranes were tested experimentally.Results indicated that the greater the membrane mean pore size and the wider the pore size distribution are, the higher the gas permeability. A gas permeation model, including the effects of membrane structure parameter and gas properties, was established. A comprehensive characteristic parameter (including porosity, thickness and tortuosity) was found more effective to express the influence of membrane structure in gas permeation process. The predicted permeation coefficients were in good agreement with experimental data.

Forecasting China’s natural gas consumption based on a combination model

Ensuring a sufficient energy supply is essential to a country. Natural gas constitutes a vital part in energy supply and therefore forecasting natural gas consumption reliably and accurately is an essential part of a country＇s energy policy. Over the years, studies have shown that a combinative model gives better projected results compared to a single model. In this study, we used Polynomial Curve and Moving Average Combination Projection （PCMACP） model to estimate the future natural gas consumption in China from 2009 to 2015. The new proposed PCMACP model shows more reliable and accurate results： its Mean Absolute Percentage Error （MAPE） is less than those of any previous models within the investigated range. According to the PCMACP model, the average annual growth rate will increase for the next 7 years and the amount of natural gas consumption will reach 171600 million cubic meters in 2015 in China.

Mechanical Model of Domestic Gas Explosion Load

With the increase of domestic gas consumption in cities and towns in China,gas explo-sion accidents happened rather frequently,and many structures were damaged greatly.Rational physical design could protect structures from being destroyed,but the character of explosion load must be learned firstly by establishing a correct mechanical model to simulate vented gas explo-sions.The explosion process has been studied for many years towards the safety of chemical in-dustry equipments.The key problem of these studies was the equations usually involved some ad-justable parameters that must be evaluated by experimental data,and the procedure of calculation was extremely complicated,so the reliability of these studies was seriously limited.Based on these studies,a simple mathematical model was established in this paper by using energy conservation,mass conservation,gas state equation,adiabatic compression equation and gas venting equation.Explosion load must be estimated by considering the room layout; the rate of pressure rise was then corrected by using a turbulence factor,so the pressure-time curve could be obtained.By using this method,complicated calculation was avoided,while experimental and calculated results fitted fairly well.Some pressure-time curves in a typical rectangular room were calculated to inves-tigate the influences of different ignition locations,gas thickness,concentration,room size and venting area on the explosion pressure.The results indicated that: it was the most dangerous con-dition when being ignited in the geometry centre of the room; the greater the burning velocity,the worse the venting effect; the larger the venting pressure,the higher the peak pressure; the larger the venting area,the lower the peak pressure.

Kinetics and model of gas generation of source rocks in the deepwater area, Qiongdongnan Basin

In order to investigate the hydrocarbon generation process and gas potentials of source rocks in deepwater area of the Qiongdongnan Basin, kinetic parameters of gas generation （activation energy distribution and frequency factor） of the Yacheng Formation source rocks （coal and neritic mudstones） was determined by thermal simulation experiments in the closed system and the specific KINETICS Software. The results show that the activation energy （Ea） distribution of C1–C5 generation ranges from 50 to 74 kcal/mol with a frequency factor of 2.4×1015 s–1 for the neritic mudstone and the Ea distribution of C1–C5 generation ranges from 49 to 73 kcal/mol with a frequency factor of 8.92×1013 s–1 for the coal. On the basis of these kinetic parameters and combined with the data of sedimentary burial and paleothermal histories, the gas generation model of the Yacheng Formation source rocks closer to geological condition was worked out, indicating its main gas generation stage at Ro （vitrinite reflectance） of 1.25%–2.8%. Meanwhile, the gas generation process of the source rocks of different structural locations （central part, southern slope and south low uplift） in the Lingshui Sag was simulated. Among them, the gas generation of the Yacheng Formation source rocks in the central part and the southern slope of the sag entered the main gas window at 10 and 5 Ma respectively and the peak gas generation in the southern slope occurred at 3 Ma. The very late peak gas generation and the relatively large gas potential indices （GPI：20×10^8–60×10^8 m^3/km^2） would provide favorable conditions for the accumulation of large natural gas reserves in the deepwater area.

A Technical Review on Shale Gas Production and Unconventional Reservoirs Modeling

During the past several years, natural gas production from shale gas is increased and has adsorbed much attention worldwide. The reason behind this is because of advances gained in shale gas recovery techniques from this ultra-low permeability/porosity rock. These techniques are considered the horizontal drilling of the length of 3000 to 5000 ft long and conducting multi-stage hydraulic fracturing along the horizontal portion of the wells. The successful application of above has also driven down the gas prices worldwide and also culminated the security of gas supply for the upcoming decades. This paper is a technical literature review of shale gas production and modeling for future performance evaluation that identifies the current challenges in different stages. Several different and complex physics of gas flow in such a low permeability formation is also explained and the state of the art of the challenges encountered in the modeling process is also explained. As such, gas desorption phenomena, non-Darcy Flow, gas Klinkenberg effect are investigated for different shale formations in the US. This technical review also takes a look over the hydraulic fracturing effects on the economics of shale gas wells due to its straight tie to the production from shale and also the overall recovery from such reservoirs.