Jiang Annan

A Nonlinear Optimization Technique of Tunnel Construction Based on DE and LSSVM

Tunnel construction is a dynamic controlling system with observability and controllability; the feedback analysis requires identifying geophysics parameters and adjusting supporting parameters, and both of them are optimisation problems. The paper proposed a nonlinear optimization technique based on difference evolution arithmetic (DEA), least square support vector machine (LSSVM), and three dimensional numerical simulation. This method employs support vector machine with optimal architecture trained by the difference evolution arithmetic, instead of the time-consuming finite element analysis. Firstly, the three dimensional numerical simulation is used to create training and testing samples for LSSVM model construction. Then the nonlinear relationship between rock or anchoring parameters and displacement is constructed by support vector machine. Finally, the geophysics and supporting parameters are obtained by DE optimization arithmetic. The technique overcomes the conventional optimization method shortages of expending too much computing time and easily being limited in local optimal solution. This technique was verified by applying it to the feedback analysis of Dalian Metro in China, and the influence of the parameters of LSSVM and DE on the simulation ability of the algorithm was investigated.

Studying the lithology identification method from well logs based on DE-SVM

Identify the rock lithology has important meaning for estimating the reserve of petroleum, adopting proper drilling technology and improving recovery. The lithology identification from well log based on DE-SVM was proposed and studied. After digitization and collection the data of the well logs and cores observation results, the mapping model between well logs and strata lithology is established by Support vector machine(SVM), so the strata lithology of wells without rock cores can be automatically gotten by well logs. Because the penal factor c and kernel parameter σ affect the identification accuracy evidently, the global optimization arithmetic- difference evolutionary (DE) is coupled with SVM to optimize above parameters in order to improve the performance of SVM model. The model theory and algorithm are discussed as well as the true example is calculated, it is stated that the proposed method is feasible and can get satisfied results.

3D Numerical Simulation of Seawater Intrusion Seepage-Diffusion Coupling Based on GIS

The sea water intrusion has water-rock interactionprocess and spatial variability of geological parameters, which makes it difficult to calculate the intrusion process. The paper proposed a method combining GIS and 3D finite element method to simulate and analyze the sea water invasion process. The GIS is developed using database and component techniques, impeoving the data organization efficency. 3D finite element model adopts proper parameters from multi layers of GIS, decrease the error of the parameters selection. The dynamic seepage- diffusion coupling mechanism is also considered in the study. The seawater intrusion in NanGuanling region of Dalian City has been studied by the method. The calculation results of both flow and chlorine ion distribution field are all coincidence with actual observation well information. That stated the simulation method is feasible. The numerical simulation of next three years is also carried out and it showed that the seawater encroachment area will decrease. That means the amount of exploited groundwater in the past yeas is reasonable. The conclusion has active supervise meaning to prevention and cure of seawater encroachment in the area.

Studying the physical property of clay soil by erosion effect of pollution environment

Pollution environment has important influence to soil physical property, however, the method and theory of pollution soil research are not mature. The paper states chemical reaction with pollution solution, inducing dissolve and deposit effect, which is the immanent cause of physical mechanic property of soil. The soil samples of Dalian region have been soaked in sulphuric acid solution and sodium chloride solution with different concentration for 60 days. Then they are respectively studied by density test, limit moisture content test and compact test, obtained the regulation of how solution with different concentration affect the physical property index of the clay soil. The tests state that the environment of acid and salt water has non-negligible affection on soil physical property, the test results provide basic for reveal the mechanism of erosion solution acting on soil.

Computer Simulation and Recognition of Foundation Loading Based on Differential Evolution Algorithm and Finite Element Method

Research of foundation bearing capacity possesses significant value of theory and construction. As the calculation assumed conditions of ultimate bearing capacity of classic foundation are so many and the soil parameters are indeterminate, we exploit a foundation loading simulation program based on difference evolution(DE) algorithm and finite element method(FEM) in this paper, which we can simulate foundation loading test and identify actual soil parameters. Based on the discussion of algorithm and calculation course, we carried out research and demonstration of simple examples, the outcome of ultimate bearing capacity and analytical results comparatively accord. We identified the elastic modulus of stuff within two soil layers by using DE algorithm and got good recognition accuracy and favorable convergence performance. The work in this paper is with active meaning for the further research of complex foundation bearing capacity and mechanics behavior analysis.

Computer Simulation and Parameters Estimation for Slope Based on Finite Element Method and Difference Evolution Arithmetic

Slope stability is one of the classic geotechnical problems, however, because of the parameters uncertainty and complexity of stress-strain relation, the conventional calculation method such as slice method adopts too much hypotheses and can not express the actual mechanical behavior of slope. Aiming to these problems, this paper exploit a slope simulation program based on difference evolution algorithm and finite element method, which can simulate the displacement and stress distribution of slope and identify actual soil parameters based on monitoring data. The theory of algorithm and program procedure are introduced. A typical calculation sample is studied using the developed program, the calculated stress and strain distribution is reasonable and the identifying parameters of the elastic modulus and Poisson ration of the soil is accuracy. The convergence performances corresponding to different F and CR of DE algorithm are also compared. It states that the program is feasible and has good adaptability for complex slope calculation.