Fuel consumption correlation factor analysis method for vehicle condition signal data

Abstract

The invention discloses a fuel consumption correlation factor analysis method for vehicle condition signal data, and the method comprises the steps: determining a vehicle condition signal affecting fuel consumption, and screening fuel consumption signal data from a vehicle condition signal database of a big data platform; adopting a LightGBM algorithm in a gradient boosting decision tree to scoreeach numerical type vehicle condition signal and category type vehicle condition signal in a finally output numerical type vehicle condition signal and a finally output category type vehicle conditionsignal, wherein the higher the score is, the higher the correlation between the numerical type vehicle condition signal and an oil consumption signal is; and sorting the finally output numerical typevehicle condition signals and the finally output category type vehicle condition signals according to scores from high to low, and outputting a ranking result. According to the method, effective modeling can be carried out on complex vehicle condition signals, and oil consumption analysis is more accurate.

Description

technical field [0001] The invention relates to the technical field of automobile fuel consumption analysis, in particular to a method for analyzing fuel consumption correlation factors of vehicle condition signal data. Background technique [0002] With the vigorous development of communication technology, Internet of Vehicles technology and big data technology, more and more cars are equipped with intelligent network connection functions. At the same time, the collection, transmission, storage and processing technologies of vehicle condition signals are becoming more and more mature. Analyze vehicles in different dimensions through vehicle condition signals. Fuel consumption, as a factor that users attach great importance to when purchasing a car, how to analyze fuel consumption and find out the important factors that affect fuel consumption has practical significance for reducing fuel consumption. At present, the analysis and excavation of factors affecting fuel consumpt...

AI Technical Summary

Problems solved by technology

At present, the analysis and excavation of factors affecting fuel consumption by major vehicle manufacturers are mostly in the experimental stage. Due to the small amount and latitude of the experimental data, they are not complete; at the same time, traditional statistical analysis methods cannot analyze complex vehicle condition signals. Effective modeling, resulting in experimental results that are often not statistically significant, and are quite different from the actual results used by users

Images