Neural Network Model for Predicting the Transformation Tendency of the Stress on the Surrounding Rocks of Tunnel

The stress on the surrounding rocks affects severely the stability of tunnel. To estimate the stability of tunnel needs the transformation tendency of the stress on the surrounding rocks. After the transformation tendency of the stress on the surrounding rocks and the factors affected it are analyzed, the neural network model for predicting the stress on the surrounding rocks is created. The model is applied successfully to predict the change of the stress of the Guanyingyan tunnel in the Qiwan expressway, which proves that it is feasible to predict the stress on the surrounding rocks with the neural network model. The method is convenient and correct.     

Elastic-Perfectly Plastic Solution of Tunnel Surrounding Rocks Using Mogi-Coulomb Strength Criterion

Reasonable choice of rock strength criteria is crucial for stress and displacement prediction and support design in tunnel engineering. Based on Mogi-Coulomb strength criterion and elastic-perfectly plastic model, analytical solutions of stress and displacement for surrounding rocks around a circular tunnel were derived The intermediate principal stress coefficient was used to present the intermediate principal stress effect. The results in this study were compared with the current solutions in the literatures and the influence of intermediate principal stress and shear strength parameters of surrounding rocks was discussed. The results showed extensive applicability and the Mohr-Coulomb strength criterion and Matsuoka-Nakai criterion are two special cases; when the intermediate principal stress coefficient b was equals to 0.5, the results indicated that the intermediate principal stress effect and its range for rock strength; the influence of cohesion and internal friction angle on the plastic radius and tunnel wall displacement was significant; Care should be taken to the effects of intermediate principal stress and shear strength parameter variations of surrounding rocks on tunnel design and construction.     

Application of Intelligent Neural Network on Prediction of Time Series Signal

The research of neural network has been maturated both in theory and practical application since 1980's, and also been employed into the prediction and analysis of nonlinear time series signal in the field of signal process system. Concerning with the problem of time series signal prediction based on traditional neural network, such as black box, poor accuracy, and facing the shortage of post knowledge, this paper presents a different neural network prediction model from the traditional ones, based on intelligent neural cell model and employing the iterative prediction method. Through the example on stock price prediction, the prediction accuracy and practical value are proved.     

Analysis and Simulation of the Highway Tunnel Fire Contamination

A one-dimensional contamination diffusion model for tunnel fire is presented. Based on this model, a highway tunnel fire within a short time course was simulated and analyzed. Compared to the test results, the simulation result demonstrates that the model is feasible. In the end, it suggests a formula for highway tunnel fire contamination. The author hopes that this analysis will be available as the foundation of highway tunnel fire control.     

Analysis and Calculation of Ventilation System of Xuefengshan Highway Tunnel

Some problems about ventilation in extra long highway tunnels have been discussed in this paper. The ventilation modes and geometry parameters of longitudinal blow-suction ventilation of Xuefengshan Tunnel in Hunan Province (7 000 m) have been studied and calculated. Based on this, the general design, principle design, technical design and relative structural design of ventilation for the tunnel have been successfully done.     

Rock Deformation, Stability Monitor Active Control About Excavation of Super-span Tunnel

According to the measurement during excavation of Jinzhou tunnel with four lanes in one cave which lies on the rebuilt highway from Shenyang to Dalian, this paper analyzes the rock deformation rule, discusses the reason of instability after a highway tunnel was excavated, emphasizes the necessity of the construction stability monitor and active control. The importance of support is Fresented with bolts and shotcrete to improve and enhance the carrying capability of the rock. It is necessary to insist on the rule of measurement and active control to ensure the safety and quality of tunnel construction.     

Service Life Prediction of Lining Concrete for Jiaozhou Bay Subsea Tunnel

Jiaozhou Bay subsea tunnel is the second self built tunnel in China with the designed service life over 100 years. On the basis of service environment of subsea tunnel concrete and the durability experiments of concretes, the service life prediction model considering chloride diffusion, carbonation and bending loading was proposed. The key durability coefficient of lining concrete in subsea tunnel was investigated. And the function of chloride diffusion coefficient and rebound strength of concrete was proposed. Moreover, the chloride content in concrete varied with service time and the service life of lining concrete for subsea tunnel was predicted with the proposed service life prediction model. It was found that the value of varied cover thickness was from -4(6) to 15 mm. The chloride diffusion coefficient mean value of lining concrete in standard curing was 2.1(2.7)×10-12m2/s. And the initial chloride content in concrete was less than 0.35kg/m3. The relationship between chloride diffusion coefficient and rebound strength could be regressed to linear relationship, and the calculated chloride diffusion coefficient of lining concrete was varied from 1.5×10-12m2/s to 3.5×10-12m2/s. The predicted service life of lining concrete for Jiaozhou bay subsea tunnel was more than 100 years according to proposed model.     

基于气候适宜度指数的山东省冬小麦产量动态预报

利用山东省主产区冬小麦产量资料、生育期内的温度、降水量、日照时数资料,结合冬小麦生理特性,分别构建了冬小麦温度、降水及日照适宜度模型,利用气候适宜度与冬小麦产量的关系,建立基于气候适宜度的冬小麦产量动态预报模型。通过对2008～2010年冬小麦产量进行动态预报, 结果表明, 3月31日、4月30日和5月31日预报的小麦产量丰歉趋势的预报平均正确率均为100%,单产预报平均准确率分别为95.1%、95.1%和95.4%,预报准确率较高,能够满足业务服务的需要。     

毛竹导热系数的神经网络预测模型

为了准确测算一定范围内的毛竹导热系数,同时改进现有的竹材导热系数研究方法,笔者采用激光闪光法精确测量毛竹导热系数值,并以此为基础,建立毛竹导热系数随不同温度和密度变化的神经网络预测模型。由于原始BP算法收敛速度慢,笔者使用Trainlm函数训练神经网络模型,确定了最佳隐层神经元个数,并对该模型的输出预测值进行线性分析及误差分析。实验结果如下：毛竹导热系数神经网络模型具有很高的预测精度,能准确预测一定条件范围内毛竹的导热系数,从而节省了以往常规试验所花费的大量时间和资源。本研究初步揭示了毛竹导热系数随温度、密度等因素的变化关系,为进一步研究毛竹热物理特性提供了理论依据。     

Prediction Model of Soil Erosion Amount in Highway Engineering during Construction Period in Mountainous Area

The highway project in mountainous area will lead to serious soil erosion,due to its long road line and large volume of the work.While the program of water and soil conservation is drawn up,the prediction of the amount of soil erosion is needed. The whole amount of soil erosion comprises primary and new soil erosion amount. The primary soil erosion amount may be predicted by the method of average erosion modulus or universal soil loss equation.The new soil erosion amount is made up of erosion amount due to disturbed earth surface and discarded soil.Finally, the prediction model of soil erosion amount about a specific highway project during its construction period in mountainous area is analyzed.     

Numerical Analysis on Stability of Rock in Sijiaotian Tunnel

The Sijiaotian Tunnel in Yunnan Dabao Highway lies in the narrow defile landscape,and the engineering geology condition is complex,with plenty of cienega.According to the actual situation of the Sijiaotian Tunnel Project in Yunnan Dabao Highway,the stability of the surrounding rock mass is studied by using a 3-D non-linear FEM.The Drucker-Prager criterion is chosen as the failure criterion of the rock.The relatively dangerous zone and the monitoring points in the tunnel are determined.The numerical results show that the Sijiaotian Tunnel is relatively stable.The conclusion has some significance for guiding the construction of similar projects.     

基于RBF神经网络的蔬菜价格预报研究

准确预测农产品市场价格对于农户生产决策与政府调控等具有重要意义。针对蔬菜市场价格预报的复杂性,利用RBF神经网络的特性,应用2003-2007年的香菇市场价格数据建立蔬菜价格预报模型,并对RBF神经网络模型的参数选择进行分析。最后应用模型对2008-2009年的香菇市场价格数据进行预报,通过与BP神经网络模型预报结果进行比较,表明RBF神经网络模型具有更高的预报准确度。     

Application of BP Neural Networks in Inventory Dynamic Modeling

The authors establish an original inventory model based on BP neural networks in dynamic environment using the inventory history data, and overcome the net overfitting problem occurred with insufficient samples by using early stopping method. After a simple-relation inventory model training is attained, they get inventory model and analyze it dynamically by reconstructing the model after getting new sample data. An example is provided to illustrate the model. The theoretical evidence is provided for the inventory system to make management decision.     

基于幼果期气象数据苹果产量早期预测研究——以运城市为例

本文通过对运城市2005—2018年气象数据和苹果年产量数据进行分析,构建运城市苹果产量早期预测模型。首先,采用HP滤波法将运城市苹果年产量分为趋势产量和气象产量。其次,分别对苹果物候期：发芽期、花期、幼果期、膨果期、成熟期建立多元线性回归模型,研究每个物候期对苹果气象产量影响的强弱。最后,选取对苹果气象产量影响最强的幼果期建立BP神经网络早期预测模型,并对其进行验证。结果表明：选取幼果期建立的BP神经网络苹果产量早期预测模型其预测结果相对平均误差为7.08%,使用2019年相关数据验证BP神经网络产量早期预测模型的精度为89.6%,表明该模型能够较为准确的预测苹果产量,可为农作物产量早期预测提供理论支持。     

Research on Load Prediction Model of Air Condition System Based on Elman Neural Network

The load of air condition system is influenced by many factors, and they are variable and nonlinear, The relation between them is dynamic,It is impossible to forecaste the load of air condition syestem accurately by traditional method. But Recurrent Neural Network is able to reflect the dynamic lively and directly. Elman is one of the typical RNN. Based on the analysis as above, prediction model of air-condition system based on Elman neural network is established, and some prediction is done. The prediction accuracy of Elman neural network and BP neural network is compared, and the experiments show that the Elman neural network is efficiency and accuracy , so Elman neural network is a new and reliable method for predicting the load of air-condition system.     

基于多模型离散覆盖的宿州初霜期动态灰预测

初霜冻害是影响宿州市秋收作物收成的重要因素。根据季节事件灰预测和多模型离散覆盖机理,创建不同零起点的灾变子序列并建立多个GM(1,1)模型,按照灰关联度择优选模,利用新息或灰数依次递补,对初霜期10月23日出现年份进行预测。提出按照频次对多模型离散覆盖进行白化以确定最有可能出现的年份,经预报检验效果较好,对初霜期的长期预测有一定的参考价值。     

The Prediction of Dynamic Phenomenon of Stope and Drift Faces in Yan Shi Tai Coal Mine

According to the characteristics of dynamic phenomenon of stope and drift facesin Yan Shi Tai Coal mine,the prediction system is set up on the basis of fuzzy method.With thismethod ,the forecasts of dynamic phenomen on are carried out.The preliminary application showsthat it is feasible to predict the dynamic phenomenon of stope and drift faces using this method.     

Parametric Analysis of the Cable''s Vortex-Induced Vibration of Submerged Floating Tunnel

The cable's motion was modeled by a spring-mass-damper system. The flow field was calculated by RSM combined with the enhanced wall function model and the vibration equation of the cable was solved by the Four Step Runge-Kutta Algorithm, which was written into FLUENT software to be analyzed. It was adopted to analyse the factors influencing vortex-induced vibration of submerged floating tunnel cable, such as mass ratio, damping ratio of the cable and whether to consider streamline movement. The main conclusion included: mass ratio has little influence on the transverse vortex induced vibration amplitude of the cable, but has a big influence on the region of the reduced velocity; damping ratio almost has little influence on the region of the reduced velocity of cable's viv, but has an influence on the cable's vibration amplitude significantly; In the case of low-mass ratio, considered the impact of the cable streamline movement, the transverse vortex-induced vibration amplitude is bigger than not considered the case.