Study on Driver Model Parameters Distribution for Fatigue Driving LevelsBased on Quantum Genetic Algorithm

摘要

According to the characteristics that fatigue study cannot reveal fatigue mechanism and nonlinear influencefactors of vehicle driving closed-loop system defects, this paper proposes a driver model inversion method for studyingthe driver's fatigue diagnosis. Furthermore, the new methods is divided into two steps: 1. using the forecast looks neuralnetwork model to build the driver - vehicle - road closed loop model which is adapted to the complex road conditions. Besides,and the model was used to study the car system parameter changes of the closed-loop system in which the driver isin a state of fatigue. 2. By defining specific movement track in the degree of approximation of theoretical data and takingtest data as the objective function, we take the driver parameter inverse problem into multiple target optimization problems.Using a method of real-coded chaotic mutation of quantum genetic algorithm (GA) optimization to obtain the globaloptimal solution. The driving simulation test results show that under the condition of complex road conditions, theproposed algorithm in actual driving parameter inversion of the alignment is superior to the traditional genetic algorithm(GA) and the traditional quantum genetic algorithm (QGA), Finally the pilot model parameters the relationship betweenfatigue factors are made.