Improving the accuracy of weighing systems in motion using dynamic neural networks

The paper is devoted to solving the problem of weighing vehicles in motion as part of modern information technologies and automated intelligent systems for managing urban resources and infrastructure. The aim of the work is to improve the accuracy of measurements in systems for weighing vehicles in motion in heavy traffic as part of intelligent urban infrastructure management systems, thereby contributing to the efficiency and sustainability of urban processes. The scientific novelty is the use of models in the form of neural networks with time delays to process data from weighing sensors. The application of this approach makes it possible to improve the accuracy of mass measurement in weighing systems in motion under conditions of intense traffic by taking into account the dynamic and nonlinear properties of the weighing process. The practical usefulness of the developed method lies in the development of new innovative weighing systems as part of modern information technologies and automated intelligent systems for managing urban resources and infrastructure. Testing the method on a simulation model of the WIM process demonstrated advantages in weighing accuracy compared to traditional methods using static and linear models. Experimental data showed a reduction in the root mean square error compared to the traditional method based on Kalman filters, which confirms the effectiveness of the proposed approach.