Fuel Consumption Prediction Model using Machine Learning

Abstract

In the paper, we are enhancing the accuracy of the fuel consumption prediction model with Machine Learning to minimize Fuel Consumption. This will lead to an economic improvement for the business and satisfy the domain needs. We propose a machine learning model to predict vehicle fuel consumption. The proposed model is based on the Support Vector Machine algorithm. The Fuel Consumption estimation is given as a function of Mass Air Flow, Vehicle Speed, Revolutions Per Minute, and Throttle Position Sensor features. The proposed model is applied and tested on a vehicle's On-Board Diagnostics Dataset. The observations were conducted on 18 features. Results achieved a higher accuracy with an R-Squared metric value of 0.97 than other related work using the same Support Vector Machine regression algorithm. We concluded that the Support Vector Machine has a great effect when used for fuel consumption prediction purposes. Our model can compete with other Machine Learning algorithms for the same purpose which will help manufacturers find more choices for successful Fuel Consumption Prediction models.

Predicting the Costs of Forwarding Contracts: Analysis of Data Mining Competition Results

“…including sea and/or railway transport). In [5], [6] random forests and support vector machines are also used to predict fuel consumption in order to monitor and prevent fuel fraud. A recent review [7] summarizes the aspects of freight forwarding and transportation, whereby ML approaches have been utilized up to now.…”

“…Geo-location data related to key points on the routes was modified. Instead of original values, we used the Nominatim service 6 to generate coordinates of the central points in the corresponding post code areas. In the published data, the original geographical coordinates are changed into the generated ones.…”

“…The quality of submissions was evaluated online. We used RMSE as the 6 https://nominatim.org/ error measure. The preliminary score of each submission was computed on a small subset of the test records.…”

Application of algorithmic models of machine learning to the freight transportation process

“…In the paper [21], researchers improve the accuracy of the SVM model for forecasting fuel consumption by freight vehicles using a machine learning algorithm. Estimating fuel consumption is based on geographic coordinates, vehicle speed, engine rpm, and throttle position sensor values.…”

“…Although the main task of the models is the classification of objects, such as: choosing the type of transportation between road and rail [14], this algorithm shows quite good results in regression analysis, namely, forecasting the duration of cargo delivery [11] and predicting fuel consumption by vehicles [21].…”