Future working condition prediction method based on front vehicle running information under intelligent network connection system

Abstract

The invention provides a future working condition prediction method based on front vehicle running information under an intelligent network connection system, which belongs to the technical field of intelligent traffic. The method comprises the steps of front vehicle running working condition data acquiring, front vehicle running working condition dividing, future working condition prediction model establishing and future vehicle working condition online predicting. The working condition prediction method can accurately acquire the front vehicle working condition information closest to the future working condition information of the vehicle, and accordingly establishes a future working condition prediction model which combines a least squares support vector machine and self-regressive sliding average error correction and is provided with prediction model precision judgement to carry out future working condition prediction of the vehicle. A prediction result has the advantages of good instantaneity, high accuracy and high reference performance. The prediction method is especially suitable for a hybrid vehicle running on a fixed line.

Description

technical field [0001] The invention provides a method for predicting the driving condition of a vehicle, in particular to a method for predicting the future working condition based on the running information of the preceding vehicle under an intelligent network connection system, and belongs to the technical field of intelligent transportation. Background technique [0002] Driving condition is one of the important factors considered in the design of hybrid electric vehicle energy management strategy, and plays a vital role in improving the fuel economy of the vehicle. It has become an effective method for the intelligent energy management strategy of hybrid vehicles to develop a method for reasonably and accurately predicting the working conditions in the future control time domain, and then combine the predictive energy management algorithm to realize the real-time optimal control of the hybrid power system. At present, the main research on the prediction of driving condi...

AI Technical Summary

Problems solved by technology

This method is based on the historical information of the vehicle's own operating conditions, and completes the multi-scale prediction of the vehicle's operating conditions by establishing a Markov chain prediction model. Due to the poor real-time performance of the historical information of the vehicle's own operating conditions for predicting future operating conditions, Moreover, the prediction results of the working condition prediction model lack in-depth analysis of errors, and the prediction accuracy of both the prediction model and the prediction results cannot be guaranteed. Therefore, there are problems such as lag, low accuracy, and poor reference in the prediction results of future working conditions.

Images