Making use of the artificial neural network method,a rock burst forecast of artificial neural network model was established and according to some underground engineering measured parameters,it validated the reliability of the forecasting model.

In the light of the non-linear character of rock burst and master factors of rock burst,a non-linear grey model of classification for rock burst prediction is established.

There is a high tendency of rock burst in surrounding rock by analyzing the modified brittleness index and model test result,so it is essential to strengthen rock burst prediction and control.

The rockburst prediction method based on grey whitenization weight function cluster theory was proposed.

The rockburst of an underground cavern directly menaces the execution and securily of an underground engineering, so it is very important to undertake the reasonable rockburst prediction before execution.

Based on the neural network theory, a new rockburst prediction model is established.

Research on in-situ stress measurement and rockburst forecast in tunnels;

With some engineering projects at home and aboard taken as learning and training samples, rockburst forecast is performed for an underground hydropower plant by use of the samples that have been trained stably.

Mechanism of lithology prediction by double-critical DIVA method and its application;

The lithology prediction in the Ken-71 area of Shengli Oil Field is achieved by multiple seismic at- tributes and Backpropagation(BP)neural network.