Typical driving condition construction method and system using grey wolf algorithm to improve clustering

Abstract

The invention belongs to the field of automobile engineering, and provides a typical driving condition construction method and system using a grey wolf algorithm to improve clustering. The method comprises the following steps: acquiring automobile driving road spectrum data, and preprocessing the automobile driving road spectrum data to obtain sample data of an automobile driving working condition; constructing random number improved nonlinear convergence factors of different probability distribution functions, improving a grey wolf algorithm based on the nonlinear convergence factors, fusing the improved grey wolf algorithm with a K-means algorithm to obtain an improved K-means algorithm, and clustering the sample data of the automobile driving condition to obtain a clustering result; and according to a clustering result, predicting typical operation conditions of the automobile by using a Markov process and a Monte Carlo sampling method. The method can improve the classification precision of the typical working conditions of automobile driving.

Description

technical field [0001] The invention belongs to the field of automobile engineering, and in particular relates to a method and a system for constructing typical driving conditions with improved clustering by using the gray wolf algorithm. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] The driving condition of a vehicle is a speed-time curve. For the transportation industry, the characteristics of the road in a specific area can be described by the driving condition of the vehicle, and then the traffic network can be improved according to the characteristics; for the automobile industry, the driving condition of the vehicle can be used to simulate the vehicle. The performance indicators in the city provide guidance for the design and development of control strategies for automobiles, especially new energy vehicles. [0004] The traditiona...

AI Technical Summary

Problems solved by technology

[0004] The traditional technology directly uses the Markov process to construct the typical driving conditions of the car, because the data is not classified according to the actual situation, and the direct use of the Markov process is not effective

The clustering algorithm can be used to cluster the data, and then construct the typical driving conditions of the car. However, the traditional clustering algorithm has low convergence and poor precision, and it is difficult to obtain efficient classification results.

Images