基于灰关联分析法和多元线性回归模型的有轨电车能耗预测

Energy consumption prediction of trams based on grey relation analysis and multiple linear regression model

针对传统的有轨电车能耗预测模型缺少对能耗影响因素进行显著性量化分析的问题,提出灰关联分析法和多元线性回归模型相结合的有轨电车能耗预测方法。首先通过有轨电车动力学模型分析有轨电车能耗影响因素,然后利用灰关联分析法计算这些影响因素的关联度,最后选取关联度较大的因素作为模型输入变量,根据多元线性回归模型建立有轨电车能耗预测模型。经实验验证,新建模型的平均预测误差为2.29%,相比已有文献中提出的回归模型其预测误差更小。因此,该能耗预测模型能够更好地反映有轨电车能耗变化趋势。

Aiming at the problem that the traditional tram energy consumption prediction model lacks quantitative analysis on the significance of energy consumption influencing factors,a tram energy consumption prediction method based on grey relation analysis and multiple linear regression model is proposed.Firstly,the influencing factors of tram energy consumption are analyzed by tram dynamic model,and then the grey correlation analysis method is used to calculate the correlation degree of these influencing factors.Finally,the influencing factors with higher correlation degree are selected as the input variables of the model,and the tram energy consumption prediction model is established based on the multiple linear regression model.The experimental results show that the average prediction error of the new model is 2.29%,which is smaller than the regression model proposed in the literature.Therefore,the energy consumption prediction model proposed in this paper can better reflect the trend of tram energy consumption.