Papers by Author: Kai Feng Ma

Abstract: Combining the advantages of basic genetic algorithm and neural network, analyze and set up GA & NN genetic neural network, explore and study the algorithm. The efficiency and effectiveness of this hybrid training has been significantly improved comparing with the single genetic evolution or BP training method, its versatility is better. The model is applied to predict the deformation of shield tunnel excavation. According to the effects of measured influence factors under construction, it can make the appropriate forecast to the surface settlement which is better than the conventional regression model. It shows that neural networks in the ground during tunneling shield analysis and prediction of settlement is practical and adaptable.

Abstract: The non-stationary time series data are dealt with the hybrid algorithm modal which combining the combined kalman and AR algorithm, and the modal was build, which the parameters stochastic variance of the AR modal was set in the state equations instead of extracting the tendency items from original data in conventional AR modals, and measure equations were constructed by observation data, then the AR modal can be solved by the Kalman algorithm. The deformation prediction results of the modal used in underground tunnel construction showed that this method was accuracy and feasible.