本研究利用數位式行車記錄器擷取車輛之資訊,經由研究中的方法將這些基礎資訊分離出與油耗相關之油耗因子,並探討油耗因子在車輛特徵與駕駛習慣下之影響,將這些油耗因子分為車輛油耗因子與駕駛油耗因子。 本研究油耗預估方法I為將各行車指標與油耗相關高的行車指標,透過ANOVA分析找出車輛因子與駕駛因子,將這些因子加入複迴歸分析模型預測其單位油耗。 研究另一個油耗預估方法II為偵測速度區間下不同的行車舉動次數,利用指標與油耗的迴歸分析相關度解決速度區間下油耗離散的問題,透過速度區間舉動次數乘以對應的油耗資料庫預測其油耗。 研究結果顯示,將油耗估計機制區分為訓練階段(training phase)與油耗預估測試階段(testing phase),將不同方法透過訓練階段之油耗預估公式實用於預估測試上,不同的方法對於不同道路的比較,利用行車指標之車輛因子與駕駛因子對於山路與高速公路是比較佳的。而對於一般平面道路及包含些許窄路的路線,利用速度區間舉動辨識是比較穩定的。
In this study, digital recorders capture vehicle and traffic information, through the study of methods to isolate these basic information associated with the fuel consumption factors, and to explore the fuel factors in characteristics of vehicle and driving habits under their influence and to classify them into the vehicle fuel consumption factor and driving fuel consumption factor. In this study, fuel consumption estimate Methods I, using each index and which index is high correlation with fuel consumption through ANOVA analysis to identify the vehicle factor and the driving factor, these variable factors and types of vehicles in the multiple regression analysis model to predict the fuel consumption (km/l). Another fuel consumption prediction method II for the detection speed range under different number of traffic interregional, useing regression analysis correlation with index and fuel consumption to solve the fuel consumption is discrete problem. Through the number of speed range multiply by the corresponding fuel consumption database to predict the fuel consumption. The results showed that fuel consumption estimates mechanism is divided into a training phase and fuel consumption to estimate the test phase. Different methods of fuel consumption estimated through the training phase of the formula.Estimate methods for different comparison of the road, the use of Index of the vehicle and driving factors for the mountain road and highway is excellent. For generally road and contains a little narrow routes, the advantage of the speed interregionnal recognition is relatively stable.