A vehicle driving cost evaluation method based on data-driven scenarios

Abstract

The invention relates to a vehicle running cost evaluation method based on a data-driven scene, belonging to the field of new energy vehicles. The method includes: obtaining the driving history data in a specific area, performing data preprocessing, and dividing the working condition segments; reducing the dimensionality of the multidimensional characteristic parameters of the working condition segments based on principal component analysis; using the IABC-Kmeans algorithm to build a typical working condition. According to the ratio of the number of samples in each cluster and the correlation between the samples in the cluster and the parameters of the cluster center, the synthetic working conditions that reflect the specific driving style and driving habits in a certain area are reconstructed, and the statistical characteristics are compared and verified with the original data set ; Design a unified quantification method for battery aging, fuel consumption and power maintenance, and build a DDPG multi-objective energy management optimization model that incorporates expert experience, so that the strategy has higher training efficiency under the premise of ensuring optimality. The invention can provide a reference for a more accurate vehicle running cost evaluation method.

Description

Technical field [0001] The present invention belongs to the new energy vehicle area, involving a method of traveling a vehicle driving cost based on data drive scenarios. Background technique [0002] The vehicle test cycle is a curve describing the vehicle's driving state, and the total time is about 1500s, which is a centralized reflection of the dynamic driving behavior of the vehicle. It can be analyzed for vehicle driving costs, energy consumption / emissions and limit standards and new models. The basis for technical development and evaluation. All countries in the world have attached importance to the development of the typical driving conditions suitable for the country. At present, Europe and the United States and other car developed countries have developed a test condition that reflects the driving characteristics of the country, my country's model testing conditions initially adopted the national five NEDC (new standard Europe Test cycle) Work conditions Since the tes...

AI Technical Summary

Problems solved by technology

In addition, most evaluations of energy management strategies are based on current standard operating conditions, and the differences in driving styles and habits in various regions make it difficult to conduct more accurate vehicle cost evaluations based on specific driving habits in a certain region. There are many parameters in the working condition segment, and the parameters are coupled and interacted with each other. How to combine the actual road scene and include as much original data set information as possible to perform dimensionality reduction and cluster analysis on the multi-parameters of the working condition segment, It is the key problem that needs to be solved in the construction of working conditions

Moreover, existing RL-based control strategies focus one-sidedly on improving fuel economy while ignoring the impact of battery aging during vehicle operation.

The lifespan of a battery is closely related to its working condition. An unreasonable control strategy will significantly increase the cost of battery replacement, even accelerate battery inconsistency, and risk triggering dangerous thermal runaway

Faced with higher maintenance or replacement costs due to battery aging, how to extend battery life is a problem that must be carefully considered in the design of energy management strategies

Images