Application of neural networks for predicting the structural behavior of the pavement due to load impact

Knowledge of the structural and functional condition of pavement structure is extremely important for the success of the entire pavement management system. Given that today’s tendency is to collect pavement condition data using non-destructive methods, deflection measurement using a falling weight deflectometer device is becoming an increasingly popular method of pavement condition assessment. As the prediction of the behavior of the pavement structure in the exploitation period is a module of exceptional importance, with the development of technology, there is a growing interest in the application of artificial intelligence, especially neural networks. By knowing the pavement behavior prediction model, it becomes possible to predict the moment when it will be necessary to perform a certain level and form of intervention, in order to maintain a certain degree of safety and comfort of traffic over a long period of time.