可燃物含水率的变系数回归预测模型

The Variable Coefficient Regression Prediction Model of Fuel Moisture Content

根据变系数回归模型的理论,选取当前时刻含水率作为观测变量,相对湿度、气温和风速作为影响因子建立可燃物含水率变系数回归预测模型.并分析对比了无降水条件下,可燃物含水率的变系数回归预测模型和基于平衡含水率的可燃物含水率常系数线性预测模型的预测精度.结果表明:可燃物含水率的变系数回归预测模型的准确率为84.55%,高于可燃物含水率常系数线性预测模型的82.14%.说明可燃物含水率的变系数回归预测模型具有更好的预测能力,具有一定的实用价值.

Based on the theory of variable coefficient regression model, a variable coefficient model for moisture content of fuel prediction model is established by choosing the current moisture as the observed variables, and relative humidity, air temperature and wind speed as the influential factors . The accuracy of the variable coefficient fuel moisture content regression prediction model is analyzed and compared with fuel moisture content constant coefficient linear prediction model based on the equilibrium moisture content. The results show that the accuracy of the variable coefficient fuel moisture content regression prediction model rate is 84.55%, higher than 82.14% that of constant coefficient linear prediction model of fuel moisture content. A conclusion is drown that variable coefficient regression model provides a better prediction and is of certain practical value.