In order to solve the multifactor problem related to gas emission quantity prediction, a new dynamic prediction method of coupling Least Square Support Vector Machine (LS-SVM) with Kalman filter was proposed. The dynamically adaptive set of training samples were obtained to replace the fixed set of training samples based on the strategy for predicting variance ratio of residual errors. LS-SVM identification network was used to perform nonlinear mapping on relevant factors of gas emission quantity to extract the state vector with the best dimension number. The Kalman filter based gas emission quantity forecasting model was established by using the state vector. Experiments were carried out with the monitoring data of the mine. The experimental results show that the average relative error of results predicted by the model is 2.17% and the average relative variance is 0.008873. The proposed model is superior to other prediction models of neural network and support vector machine in terms of prediction accuracy and generalization ability.

To improve the accuracy and efficiency of absolute gas emission prediction, a new algorithm based on Chaos Immune Particle Swarm Optimization (CIPSO) and General Regression Neural Network (GRNN) was proposed. In this algorithm, CIPSO was employed to dynamically optimize the smooth factor of GRNN to reduce the impact of artificial factors in GRNN model construction, and then the optimized network was adopted to establish gas emission prediction model. The simulation experiment results on gas emission data of a coal mine show that the model is of faster convergence and higher prediction accuracy than other prediction models based on BP and Elman neural network. It is proved that the proposed method is feasible and effective.