Evolutionary Support Vector Machine And Its Application In Rock Body Slope

SVM(Support Vector Machine, in short for SVM)) is a kind of creative machine studying method, which is put forward by Vapnic and his cooperationer in ATî–š Bei Er laboratory based on VC(Vapnic?Chervonenkis) theory. Its basic thought is to change input space into high-dimensional one by non-linear variable defined by accumulating function and to look for a kind of non-linear relationship between input variable and output one in the high-dimensional space. SVM with better theoretical foundation possesses fairy popularizational value adopting structural risk minimization.The method for SVM is a Convex Quadratic Programing Problem, which guarantees that found keys are overall optimum ones and can solve some practical problems such as a little sample, non-linear, high-dimension and part minimized value. So SVM is a hot issue nowadays.Geomechanics is a subject with the deep theory and strong practice. Through a few decades , a lot of methods have been applied to solve the problems on geomechanics based on the traditional science such as material mechanics, elastic mechanics and elastic and plastic theory. But owing to rock and soil's features such as the complexity, non-linearity, randomty, uncertainty and obscurity, It is difficult to get satisfactory results by traditional ways. SVM, as a new general method of machine learning is fit for the problem that can't be solved with traditional mathematical model possesses an extensive applied prospect.The paper applies the SVM methods to the researches such as rock slope and anti-analysis of elastic displacement.. The main program is as follows:1 In view of the questions of safety appraisal on geotechnical engineering, the author applies SVM to the researches on geotechnical engineering and establishs the SVM model of reliability appraisal on slope engineering.2 In view of confirming the SVM parameter(including nucleus funtion and its parameter), the author puts forward evolutionary support vector machine method which combines the global optimization characteristic of genetic algorithms withchoice features which SVM solves the questions such as little sample, high-dimension and nonlinear.3 The author puts forward the ESVM method which forecasts the behavior of rock and land's distortion, applies the method to make research on the distortion of new beach's coast and verifies its feasibility.4 The author puts forward the time series on rock slope nonlinear displacement and a new method forecasting slippage, and expresses its feasibility and choice functions by simple examples.5 According to the ESVM method which forecasts the behavior of rock and land's distortion, the author puts forward the thoughts about ESVM displacement anti-presence and forecasts...