The weight adjustment of the statistical method of highway freight transport volume under the major and intermediate road maintenance conditions

In order to better implement the statistical method of road freight volume developed by the Ministry of Transport, which is "comprehensive survey of enterprises above scale + calculation of fluctuations in households below scale", this article considers the impact of major and intermediate road maintenance conditions on the freight volume of road sections in the maintenance affected area, and studies the real-time weight adjustment problem in the statistical method. Firstly, an improved ant colony algorithm is used to simulate the missing data in the affected area. Secondly, BP neural network is used to fit the road data, and the adaptive artificial fish swarm algorithm improved by using chaotic mapping is proposed to solve the problem that the BP neural network algorithm has a high dependence on the initial value and is easy to fall into the local optimum. Finally, the trained internal connection weights of the model are used as the calculation indexes, and the entropy weight method is applied to calculate to get the adjusted weights. The improved algorithm increases the traversal and randomness by using chaotic mapping, and enhances the algorithm's global optimality seeking ability by making adaptive improvements to the field of view and step size. The example analysis shows that this model is superior to the traditional models such as BP, GA-BP and AFSA-BP, and the adjusted new weight is more in line with the demand of freight traffic statistics after major and middle road repair.