|
| Models | Feature | Advantages | Disadvantages | Applied to |
|
| Grey | Use a small amount of incomplete information to establish a gray differential model; make a vague and long-term description of the development law of things | High accuracy: sample does not require regularity and large numbers; suitable for medium and long-term prediction | Ignore the internal mechanism of the system; unable to reflect system changes dynamically | Coal mine gas emission forecast [11]
Ground settlement forecast [12] |
|
| ARIMA | The regression dependent variable is only established for its lag value and the current value of the random error term | Mathematical models only need endogenous variables rather than exogenous variables | Timed data are required to be stable; nonlinear relationships cannot be reflected; the determination of model parameters is very complicated | Prediction of methane emissions [13]
Carbon emission reduction forecast for developing countries under the epidemic [14]
Inference of mine accident rate behavior [15] |
|
| Linear regression | Find the influencing factors; establish the regression equation between the characteristics and the target | Good at analyzing multifactor models; providing error checking of model estimation parameters; easy to calculate | The unfathomability of certain influencing factors is not considered; the results cannot reflect periodic waves | Coal seam gas pressure prediction [16]
Forecast of miners’ escape speed [17] |
|
| Nonlinear regression | Suitable for explaining the nonlinear relationship between one variable and multiple variables | The algorithm is easy to implement and deploy, and the execution efficiency and accuracy are high | Discrete independent variable data need to be used by generating virtual variables | Prediction of water inrush [18]
Maximum water inrush prediction [19] |
|
| Neural network | It abstracts the human brain neural network from the perspective of information processing; it is usually a logical expression of an algorithm | Provide self-learning functions and high-speed search optimal solutions; ultimately approach any complex nonlinear relationship; be able to learn and adapt to unknown or uncertain systems | Unable to explain the reasoning process and the basis of reasoning; unable to work when the data are insufficient; converting all inference into numerical calculations will lead to the loss of information | Risk status prediction of coal mine rock explosion [20]
Coal and gas outburst prediction [21]
Diagnosis of coal mining equipment [22] |
|
