Font Size: a A A

The Control Algorithm Of Speed Based On ECO-driving Assistance System

Posted on:2019-08-19Degree:MasterType:Thesis
Country:ChinaCandidate:B LongFull Text:PDF
GTID:2382330566477802Subject:Vehicle Engineering
Abstract/Summary:PDF Full Text Request
The algorithm of vehicle speed optimization control is an important means to improve vehicle fuel economy.It provides a theoretical basis for prompting and evaluating functions in the eco-driving assistance system and it can effectively improve the driver's bad driving operation behavior.The main research work of this paper is as follows:A sub-model of the BP neural network vehicle speed forecasting model was established.Firstly,according to the box-plot of the characteristic parameters and statistical data of the car's historical speed data,the demarcation line of the BP neural network vehicle speed forecasting sub-model is determined.Combined with the theory of the BP neural network and the actual conditions of the BP neural network vehicle speed forecasting submodel,the activation function,training function and structural parameters of each network layer of the BP neural network vehicle speed forecasting submodel are determined.Through the analysis of the prediction results,the prediction accuracy of the sub-models of the vehicle speed forecasting is determined.Establishing a speed optimization model of the eco-driving assistance system with DP dynamic programming.Determining the optimization objective function which is based on the fuel economy of the vehicle and supplemented by dynamics,comfort and safety.The optimized analysis of the simulation was conducted on the process of starting acceleration,driving acceleration and climbing with the eco-driving assistance system's vehicle speed optimization model.Through the simulation,the five acceleration processes in the combined speed in the first chapter were selected and comparing the fuel consumption under the optimized vehicle speed model with the fuel comsuption of the original actual speed trajectory.The results showed that the average fuel consumption of the vehicle speed optimized by the eco-driving assistance system is promoted to 5.87%.The climbing conditions are divided into two types.The simulation results show that the fuel consumption of first type whose vehicle speed optimized by the eco-driving assistance system is promoted to 16.5%.The fuel consumption of the second type of condition is promoted to 24.85% by changing the target speed.Establishing a specific optimal objective function to calculate the fuel consumption through the traffic light intersection.combining with kinematics equations and dynamic programming algorithms,the optimization algorithm of the optimal vehicle speed trajectory was put forward.It shows that the optimization algorithm proposed in this paper increases 10.86% and 2.4% respectively in the red light deceleration mode compared to the optimization algorithm with the minimum acceleration and the smallest acceleration time.
Keywords/Search Tags:Speed Prediction, BP Neural Network, Eco-driving Assistance, Dynamic Programming
PDF Full Text Request
Related items