GAS DETECTING AND FORECASTING VIA TIME SERIES METHOD

The importance and urgency of gas detecting and forecasting in underground coal mining are self-evident. Unfortunately, this problem has not yet been solved thoroughly. In this paper, the author suggests that the time series analysis method be adopted for processing the gas stochastic data. The time series method is superior to the conventional Fourier analysis in some aspects, especially, the time series method possesses forecasting (or prediction ) function which is highly valuable for gas monitoring. An example of a set of gas data sampled from a certain foul coal mine is investigated and an AR (3) model is established. The fitting result and the forecasting error are accepted satisfactorily. At the end of this paper several remarks are presented for further discussion.