| The thought of information-based design and construction in tunnel engineering have been accepted by people and adopted more and more. But how to get the right rock parameter, have been a tougher problem for a long time. .That using back analysis method to get the rock parameter is provided a more valid path. According to the characteristics in tunnel engineering and the development trend of tunnel supervision measurement items, some researches have been done in the text by using the inner stress of initial stages shoring concrete back analysis rock parameter .Because direct method, one of many kinds of back analysis metnods, has broad applicability direct method is adopted in this text. Calculation efficiency will be improved greatly if we substitute Artificial NeuralNet works for the FLAC computation model. Orthogonal experimental design is adopted to constitute study examples. Accuracy of forecast of net is ensured and time of test is reduced. Genetic Algorithm is used to search most appropriate neural network structure . Uniform design method is used to constitute test examples. Back test is used to test the result. The result proves that forecast capability of Neural Networks is good enoughAfter the mapping of rock parameter and displacement is constituted by neural network , Genetic Algorithm is used to search optimum rock parameter . Back analysis program is compiled based on NN and Genetic Algorithm. Only constitute general and correct study examples with correct forward analysis program, all kinds of mapping of relationship of input and output can be got by NN, so the program in this text is all-purpose in some areaThe back analysis program YLF_GN is used to calculate rock parameters of an engineering example. The result is good. The error of displacement based on the parameter gained by the back analysis program is little.Through the examination, the error margin of computable result is acceptble and the computable result have certain actual applied value. |
PDF Full Text Request