Application of D-ELM in quantitative analysis of FTIR spectrum of mine gas

Three quantitative analysis models for mine gas were established, the support vector machine (SVM) model, the extreme learning machine (ELM) model and the dynamic extreme learning machine (D-ELM) model, to analysis and compare with the result of D-ELM. Since the results of each model were changed in a certain range, taking the average root mean square error (ARMSE), the average correlation coefficient (AR) and the average model running time (AT), all of them were the average values of 10 results of each model, as the standards to evaluate the performance of the model in the quantitative analysis of the mine gas. The results of particle swarm optimization(PSO)-SVM model, ELM model and D-ELM model were as follow: [0.054 2,0.998,200.38], [1.042 1,0.989 4,0.26], [0.043 8,1,2.01]. Considering the predicted accuracy and predicted speed, D-ELM is better than the other two models.