Combined estimation method for road junction dynamic steering proportion based on Bayes weighting

Abstract

The invention discloses a combined estimation method for a road junction dynamic steering proportion based on Bayes weighting. According to the method, three sub algorithms of an improved Kalman filtering algorithm, an improved back-propagation neural network algorithm and a genetic algorithm are designed to solve the road junction dynamic steering proportion by utilizing road segment traffic detected by all inlet roads and outlet roads of road junctions, historical data are combined based on the road junction dynamic steering proportion, correction on historical and current estimation deviation is considered comprehensively, calibration is carried out by utilizing a Bayes formula and weight is updated dynamically, and obtained results through the three sub algorithms are weighted to obtain the dynamic steering proportion estimated by the combined method. Aiming at different traffic flow situations, the dynamic steering proportions estimated by existing methods all have advantages and disadvantages in the aspects of precision and efficiency, the combined estimation method can embody the advantages of all the methods on the whole, local oversize deviation is avoided, the combined estimation method has the advantages of being strong in adaptability, high in precision, good in stability and optimal in entirety, and can provide basic data supporting for signal control and other real-time traffic management and information service systems.

Description

technical field [0001] The invention relates to a Bayesian weighted-based intersection dynamic steering ratio combination estimation method applied to intersections, which is used for the development of intersection real-time self-adaptive signal control systems and provides basic data for other traffic management and information service systems. Background technique [0002] As an important node of the urban road network, intersections have the characteristics of non-linear and time-varying traffic in each flow direction. Scientific and reasonable intersection signal control and traffic organization schemes should be based on accurate and real-time traffic volumes, and dynamic steering flow is the basis of intersection signals. The basic data of the control. Under the existing traffic flow detection technology conditions, it is easy to obtain the traffic flow of each lane upstream of the entrance and exit road through detection, but it is difficult to obtain the dynamic ste...

AI Technical Summary

Problems solved by technology

[0004] The recursive estimation algorithm and the Bell fleet diffusion method both use a linear model to derive and estimate the steering ratio, which is suitable for the estimation of the steering ratio after a long period of traffic smoothing, but it is difficult to estimate the steering ratio of real-time nonlinear changes, so it is not suitable for online applications; the genetic algorithm It is an adaptive global optimization probability search algorithm formed by simulating the genetic and evolutionary process of organisms in the natural environment. It is used to solve the problem of minimizing the sum of the absolute value of errors between the observed value and the estimated value in the estimation of the dynamic steering ratio at the intersection. The optimization model, after several iterations, the result evolves to a state that contains or is close to the optimal solution of the dynamic steering ratio; the Kalman filter algorithm is a time-domain method developed on the basis of the recursive estimation algorithm to obtain the minimum variance meaning The change characteristics of the lower dynamic steering ratio belong to the optimal estimated value of the state variable. The nature of its recursive algorithm determines that the algorithm has high efficiency but relatively poor precision; The historical data of various traffic lanes is used for training and learning, and the estimated steering ratio is obtained, and the error is obtained by comparing with the actual data, and then the steepest descent method is used to continuously adjust the weight and threshold of the network through the backpropagation error, so that the network The sum of squared errors is the smallest, and the estimation of the current data is realized under stable weight and threshold conditions, but its learning rate is constant, which has the disadvantages of slow training speed and easy to fall into local optimum.

Images