Prediction Model of Exploitation Sink Using Ann and GIS

A new idea is put forward on researches of prediction method of coal mining subsidence supported by GIS, and a new method is given about quantitative prediction of mining subsidence by means of GIS and ANN(Artificial Neural Network).This paper has completed a lot of work concerning choosing factor,data processing, establishing and validating preliminary ANN prediction model. Further more,data processing is carried out by GIS software,and the BP training method is used for modeling the exploitation sink system. Subsequently,the error is qualitatively analyzed with considering the result of verification. Researches show that the ANN prediction model supported by GIS has theoretical feasibility and realistic significance in predicting complex exploitation sink system,and GIS and ANN possess wide application prospects in the prediction of exploitation sink.     

红旗煤矿开采沉陷土地生态服务价值影响

为研究因煤矿地下开采造成的地面沉陷程度及其土地生态服务功能价值影响,首先利用FLAC模型对地面沉陷进行定量预测,根据地面沉陷预测结果基于GIS技术对因地面沉陷造成的土地生态服务价值进行定量分析、估算。研究结果表明：全井田最大下沉值为3 590 mm,最大倾斜值为71.8 mm,最大曲率值为2.18×10-3/m,最大水平变形值为27.3 mm/m,最大水平移动为898 mm,地表沉陷面积为8.09 km2;将导致土地生态服务价值损失537.11万元。     

非稳沉采煤沉陷区生态修复探讨

以淮南市为例分析非稳沉采煤沉陷区的地表沉陷及其对生态环境影响,充分、科学、合理的利用沉陷区受损废弃的水土资源,将生态重构与环境治理修复及农业发展紧密结合,在调查分析淮南市土地沉陷与治理现状的基础上,提出非稳沉采煤沉陷区生态重构应遵循的基本原则,探索非稳沉采煤沉陷区生态修复、生态农业及生态景观的构建模式,力求实现生态环境修复与农业发展和生态景观的优化耦合,促进生态功能提升,为安徽省乃至全国同类地区的生态修复提供示范。     

采煤塌陷区水体生物多样性调查

通过对采煤塌陷区水体包括塌陷积水区、精养鱼塘、网箱养鱼区这3种水域的生物多样性进行调查分析,结果表明,煤炭开采引起的塌陷区水体具有如下特征：采煤塌陷区水体目前均处于富营养化水平,为严重污染状态,各水体的物种丰富度都比较低,个体分布不均匀,影响塌陷区水体浮游植物的主要因素是所处地域塌陷积水前的耕地养分情况。     

The Technology of Grouting into Separated Strata in Overburden and Computational Model

After coal mined, the balance of original stress state is to be broken. In the course of retribution, displacement and deformation in the overburden takes place with the working face advancing. The article points out that overburden can be divided into, in ascending, caving zone, fractured zone, bending zone and loose alluvium zone. The extracting space can be prevented from transferring to ground with injection material into bed-separation gap. Applying both mining subsidence theory and elastic thin plate theory, the computational model of subsidence control technology of grouting is worked out. The model can get rid of blindness of determining the position of separated strata, forecast the surface subsidence and provide the basis of theory for forecasting surface subsidence control technology of grouting.     

浅析淮南市潘集现代农业示范园区规划

浅析了淮南市潘集现代农业示范园区规划,对规划的背景、示范区现状、规划意义、规划目标、示范区的空间结构布局和功能分区以及规划的创新进行了充分的分析。淮南是全国重要的大型煤炭生产基地,面临着资源枯竭的危机和产业转型的机遇,综合示范区现有农业资源禀赋、产品定位、空间分布、市场区位和交通条件等因素,通过不同功能区的培育和交通系统的完善,因地制宜,针对性地提出了现代农业的规划,形成六区一带的总体格局,将蔬菜、粮食、循环养殖、加工物流、观光农业等产业及新农村建设有机结合,为采煤塌陷区产业转型提出了有效的现代农业的规划思路,促进潘集区现代农业的快速发展,给当地带来十分广阔的发展前景,给类似地区的发展提供参考。     

The Architecture Design Based on the Landscape Conditions: Taking the Architectural Design of Subsidence Area for Example

The relationship between architecture and people, architecture and city, architecture and nature has always been the soul of architectural design. In the architectural design, study on the relationship between architecture and nature needs "site analysis"(mapping), and "natural environment" tends to affect the design results[1]. In many special areas, the design needs analysis of geology, geomorphology, hydrology, vegetation and other landscape elements. Coal mining subsidence area is the product of the conf licts between human activities and natural environment in the process of industrialization. As the research object, coal mining subsidence area can be a good study object to demonstrate architectural design strategies and methods based on landscape, and fi eld defects of the site may be the origin of architectural space organization: architectural concept, structure, morphology, spatial organization are all from the landscape elements.     

Ecological Planning of Resource-based City——A Case Study of Huaibei City,Anhui Province

Ecological planning plays an important role in the construction of cities. Huaibei is a typical coal resource-based city, the abundant coal resources lay a solid foundation for its economic development. Coal mining has induced a series of social problems, and affected the regional social and economic development. Ecological planning of Huaibei City concentrates on ecological restoration of coal mining subsidence, and applies circular economy to develop eco-agriculture, eco-tourism and eco-industry, which will contribute considerably to the economic transformation of the city. Analytic Hierarchy Process and mathematical statistical model were applied to calculate sustainable development indexes of Huaibei from 2002 to 2010. By evaluating the indexes, it was found that Huaibei City has a low sustainable development level, and 3 imbalanced subsystems as the major obstacle. The authors proposed countermeasures according to specific conditions of the city.     

基于智能算法优化SVM的横向通风过程中温度场预测方法探究

将改进的智能预测技术应用于储粮横向通风过程中的粮堆温度预测,为粮食通风智能预测与决策提供了一种新思路。选取河北清苑国家粮食储备库冬季横向通风的实时监测数据,在分析主要影响因素的基础上,应用三种智能优化算法——网格寻优算法、GA遗传算法寻优、PSO粒子群算法,结合回归支持向量机理论,对粮堆的通风过程进行建模。结果表明,优化过的回归预测模型能较好地拟合粮食温度与其他变量之间的非线性关系,尤其是当样本数量较为有限时,该方法具有更高的拟合精度,更适合对储粮通风这一强非线性过程的预测研究,对于人工干预操作具有一定的现实指导意义。     

基于ARMA模型的地表水水质预测方法研究?

选用合适的模型提高预测的精度和可靠性,为区域水环境管理提供科学依据,是水质预测要解决的关键问题。为了解决这一问题,根据辽河流域的实际,运用自回归滑动平均(ARMA)模型对辽河流域东陵大桥监测断面CODMn的水质变化趋势进行预测。结果表明：综合自相关函数、偏相关函数以及BIC原则,ARMA(1,1)模型能够更好地用于东陵大桥断面水质预测。拟合结果显示,相对误差在2.60%~25.98%之间,平均相对误差为13.69%,说明该模型能够充分利用近期水质资料信息,以精确预测未来水质变化趋势。而对东陵大桥监测断面CODMn的预测显示,未来CODMn呈现出增长态势,辽宁水环境管理任务仍然很重。最后,就ARMA模型应用于水质预测的问题和发展方向进行了探讨。     

不同工程复垦措施对晋东南采煤沉陷区土壤质量演变特征的影响

为了揭示不同工程复垦措施下采煤沉陷区土壤质量的演变特征,基于10年的长期定位试验,研究了晋东南采煤沉陷区在表土剥离和混推复垦两种工程复垦方式下,10年间土壤的理化性质、微生物群落结构及土地生产力的变化特征。结果表明：复垦初期,表土剥离处理的复垦土壤理化性质、土地产出能力均显著高于混推复垦。复垦7年时,土壤的物理性质、微生物群落结构组成与多样性和土地产出能力基本一致,差异不显著。复垦10年间,0~20 cm土层土壤养分含量始终表现为表土剥离>混推复垦;10年间表土剥离较混推复垦收益累计增加6609元/hm²,因此,表土剥离复垦方式在保持耕层土壤肥力及综合收益上要优于混推复垦。但复垦10年后,2种复垦方式土地生产力和肥力水平均很低,说明复垦方式只是矿区复垦过程的一个前置环节,矿区土壤的生态恢复是必须要结合施肥措施进行。     

基于土地整治的采煤区生态服务价值评价

以采煤沉陷区为研究对象,分析采煤沉陷区土地利用和损毁情况,并通过生态系统服务价值(ESV)指标对土地整治效果进行评价。结果显示,通过土地整治工程,耕地面积由220.24 hm2增至311.08 hm2;采煤沉陷区总生态服务价值属于正向变化,由整治前的348.03×104元/年,增加至到整治后的356.67×104元/年;采煤沉陷区各单项生态服务价值有正向的,也有负向的。其中,属于正向影响的有气候调节、水源涵养、废物处理、食物生产和原材料;属于负向影响的有气温调节、土壤形成与保护、生物多样性保护和娱乐文化。土地整治改善农业基础设施条件和修复并重构生态环境,进而增加社会经济效益和生态效益。     

Prediction and Analyses of Residual Chlorine Based on Support Vector Regression in Urban Water Distribution System

Support vector regression(SVR) algorithm is an application of structural risk minimization principle in function regression.In this paper,a residual chlorine prediction model based on SVR is established by using the data of manual sampling residual chlorine of water distribution system in a certain city in the north of China.SVR model is compared with the artificial neural network and multivariate linear regression.The result shows that SVR model has better generalization ability for small samples,the predicted average relative error of all monitoring points is 1.80%~8.73%,and can achieve unique and globally optimal solutions.It is practical and can solve the problem for small samples of residual chlorine when the fit precision of model is good but the predicted effect is worse.     

基于人工蜂群算法优化支持向量机的 采场底板破坏深度预测

为确定合理的底板防水煤岩柱尺寸,减少底板突水安全事故的发生,利用支持向量机(SVM)与人工蜂群算法(ABCA)综合研究底板破坏深度问题。由于SVM训练参数惩罚因子 C 和核函数宽度 g 的选择对预测精度的影响显著,采用ABCA优化该训练参数的选择过程,建立基于SVM的底板破坏深度预测模型。选取采深、煤层倾角、采厚、工作面斜长、底板抗破坏能力和是否有切穿断层或破碎带作为影响底板破坏深度的主要影响指标,利用现场实测的30组数据作为样本对该模型进行训练和预测。结果表明：该预测模型的平均相对误差为12.5%,平均绝对误差为 0.986 m ,均方误差为0.005,平方相关系数为0.980,较其他预测模型具有更强的泛化能力和更高的预测精度。     

基于无迹卡尔曼滤波神经网络的光伏发电预测

针对光伏发电系统在不同天气状况下发电功率预测精度不高的问题,在分析传统方法的基础上,提出一种无迹卡尔曼滤波神经网络光伏发电预测方法。该方法利用无迹卡尔曼滤波实时更新神经网络模型的权重,以直流电压和电流作为系统的输入,以有功功率和无功功率作为系统的输出,分别建立两个独立的双输入单输出功率预测模型。实验结果表明：所提出的方法对有功功率和无功功率的预测精度分别为97.3%和94.2%,并且对天气具有良好的鲁棒性。     

局域法邻近点选取对供水量预测精度的影响

混沌局域法预测模型适用于非线性、非平稳的城市日供水量预测,而邻近相点个数的选取对该模型预测精度有直接影响。传统方法通常以嵌入维m作为参考值,凭经验选取m+1个邻近相点,且仅使用欧式距离法计算当前相点距离,无法反映相点的运动趋势,易引入伪邻近相点,导致预测精度的降低。鉴于此,将演化追踪法引入城市日供水量预测,通过挖掘邻近相点的历史演化规律对参考样本进行优选,以提高预测精度。最后,采用实际日供水量数据验证所提出方法,结果表明,运用演化追踪法优选邻近相点能显著提高日供水量预测精度,预测平均绝对误差由2.501%降低到1.683%。     

带锚FRP受剪加固梁非剥离破坏模式BP网络预测

对带可靠锚固FRP受剪加固混凝土梁的非剥离剪切破坏模式做了细化分类,即包括FRP断裂控制的破坏、受压区混凝土（达到极限应力状态）压碎控制的破坏、FRP断裂与混凝土压碎同步发生的界限破坏等3种模式;利用BP神经网络建立了带锚纤维受剪加固梁破坏模式的智能预测模型,与31根非剥离破坏加固梁试验的对比结果显示：模型总体精度达到90%,说明建立的破坏模式网络预测模型适用于带锚纤维受剪加固梁非剥离剪切破坏模式的判别。     

3D FEM Analysis of Subgrade Soil Movement and Deformation Caused by Extra Shallow Underground Pipe Jacking

Pavement structures will be damaged by subgrade soil movement around the pipes introduced by extra shallow underground pipe jacking. Soil layer deformation with shallow deposits on pipes during extra shallow underground pipe jacking is analyzed using 3D FEM. The effects on pavement deformation created by the friction between shield and soil, injection slurry, jacking forces and the vehicle loads are studied with a practical project. The analytical results show that the ground surface deformation is an uplift first followed by settling with the lower part of the cover moving faster than the upper layers. It is demonstrated by comparing computational results of FEM simulation and the observed data from the in situ test that these FEM models can be applied to real world engineering. Subgrade soil settling on extra shallow underground pipe jacking in a cross section will be stable when the shield has passed through a section with a length twice the diameter of the pipe. Horizontal surface subsidence along the lateral distribution is similar to a normal distribution curve, with the primary affected areas on both sides of the axis approximately 1.5 times the diameter of the pipe.     

Grey Prediction Method in Gas Emissing Quantity

Bastd on dealing with the initial data of the gas emissing quantity of mining coal face by natural logarithm,the improved grey model(1,1) is built.The improved Grey Markov prediction mode is built through uniting the improved grey model(1,1) and the Markov mode.Comparing the fitting precision of the improved grey model(1,1),the Grey Markov prediction mode and the improved Grey Markov prediction mode respectively through actual survey data in scene,it shows that the precision of the improved Grey Markov prediction mode is the best of the three and its result is correct and reliable,having certain general applicability.     

草面温度在霜预报中的应用

为了避免农作物遇霜后遭受冻害,本研究采用草面温度对霜进行预测。利用连云港气象观测站2014—2016年逐时气象要素,包括气温、0 cm地温、露点温度、水汽压、气压以及2 min平均风速等气象要素作为影响连云港地区草面温度的关键因子,并以这6个要素作为属性特征,以草温作为标志量构建训练样本集,结合KNN数据挖掘算法构建草温预测模型,并根据草温判别是否有霜出现。结果表明：基于该算法构建的草温预测模型效果较好,预报平均误差1.2℃;根据草温预测霜的准确率高达90.2%,尤其对初终霜的预报具有很好的指示意义。因此,引入草温作为霜的预报指标,对于避免农作物遭受霜害具有十分重要的意义。