Although lots of ways can be used to estimate geo-stress state, estimation of geo-stress state without knowing geomechanical parameters such as pore pressure, tensile strength and Poisson’s ratio, etc., still remains one of the most challenging tasks in geotechnical engineering. The main contribution of this paper is to present a back-propagation neural network (BPNN) with genetic algorithm (GA) optimization to predict the geo-stresses based on wellbore pressures of hydraulic fracturing tests during drilling. In the suggested hybrid model, the BPNN is used establish a mapping between the recording pressures and the geo-stress state. Also the GA is used to carry out the optimization of the weights and thresholds of BPNN model for improving accuracy of prediction. Finally, based on the record pressures in hydraulic fracturing (HF) tests, the BPNN model with genetic algorithm optimization successfully predicts the geo-stresses at the corresponding formation in the event that these parameters such as pore pressure, tensile strength and Poisson’s ratio are unavailable. In the meantime, the geo-stress state has been calculated using the theoretical formula by assuming pore pressure and tensile strength of rock mass are known. Then results from theoretical equation, BPNN and BPNN with GA optimization are compared, which shows that the degree accuracy of geo-stresses predicted by using GA-BPNN model is more obviously improvement than the predicted results by the basic BPNN model.
A Hybrid Forecasting Model for the Velocity of Hybrid Robotic Fish Based on Back-Propagation Neural Network With Genetic Algorithm Optimization