论文部分内容阅读
为科学准确预测煤自然发火期,运用灰色系统理论,基于灰色关联分析,选取煤样工业分析中的灰分、挥发分和元素分析中的C、H、O、S含量作为系统相关因素,建立了预测煤最短自然发火期的GM(0,7)模型,经后验差检验,模型精度为优;通过与多元线性回归模型预测结果对比,GM(0,7)模型预测煤自然发火期的平均相对误差为2%,多元线性回归模型预测的相对误差为10.35%.经外来数据回代检验,GM(0,7)模型预测结果的相对误差在2%左右,多元线性回归模型预测结果相对误差达26.27%,说明GM(0,7)模型预测结果优于多元线性回归模型.研究结果表明:利用灰色关联分析选取适当参数建立GM(0,N)模型能够较好预测煤最短自然发火期.
In order to predict the spontaneous combustion period of coal accurately and scientifically, the gray system theory and the gray relational analysis were used to select the contents of C, H, O and S in the ash, volatile and elemental analysis of the coal sample industrial analysis as the system related factors Prediction of the shortest spontaneous combustion period of coal GM (0,7) model, posterior difference test, the model accuracy is excellent; By comparing with the multivariate linear regression model predictions, GM (0,7) model predicts the average coal spontaneous combustion period The relative error is 2%, and the relative error of multivariate linear regression model prediction is 10.35% .Based on the regression of external data, the relative error of GM (0,7) model prediction results is about 2%, the relative error of multivariate linear regression model prediction results Up to 26.27%, which shows that GM (0,7) model is better than multivariate linear regression model.The results show that GM (0, N) model can be used to predict the shortest spontaneous combustion period of coal by using gray correlation analysis to select appropriate parameters.