Gaussian Process Model for Time Series Analysis of Mine Gas Emission
For the purpose of achieving effective analysis and full use of gas measuring data in mines, studied the method for time series analysis based on the Gaussian process regression model, and applied in modeling for gas emission time series analysis to achieve gas emission quantity prediction. Proposed two methods for gas emission time series analysis, the relationship between gas emission quantity and time (Q-T) model and autoregression model, considered gas emission time series as a function of time in Q-T model, while constructed the Gaussian process regression model from gas emission time series itself completely in autoregression model. The results of case study show that Gaussian process model can describe the objective laws and the developing trends of mine gas emission, its predictive results are accurate and reliable, therefore, the application of the Gaussian process regression in gas emission time series analysis is a feasible and effective method for gas emission quantity prediction, it has high practical application value.
gas emission Gaussian process time series andysis prediction
Dong Dingwen Zhang Taowei Li Shugang Chang Xintan
School of Energy Engineering Xian University of Science and Technology Xian, China
国际会议
成都
英文
145-148
2010-12-17（万方平台首次上网日期，不代表论文的发表时间）