Abstract: Disclosed is a vehicle fuel economy evaluation method based on data analysis. The method combines data processing and a fuel model with an enhanced learning mechanism to predict fuel consumption, analyze driving behavior and output an improvement suggestion. With continuous enhanced learning and long-term dynamic improvement, the model will be able to predict economic fuel consumption in an increasingly accurate way, along with specific and intuitive driving behavior suggestions to help drivers to drive economically.

Abstract: A method for detecting the load mass of a commercial vehicle includes the following steps. Step S1, data preprocessing: including data analysis, cleaning, noise processing and other operations for original terminal data of the vehicle. Step S2, identification and analysis of working conditions: further analyzing the working conditions according to the preprocessed data. Step S3, data screening: determining whether data with the working conditions analyzed belong to test data or training data; proceeding to step S5 if the data belong to test data, or proceeding to step S4 if the data belong to training data. Step S4, model construction and combination: constructing a plurality of different basic models through the training data in the step S2, and finally combining the models through training and screening.