The main objective of the project is to develop self-calibration methods and algorithms that will reduce the relative error in total vehicle weight and axle loads measurement, while maintaining high accuracy over time.
The research focuses on the axle load sensor–road surface system to improve weighing accuracy without expensive interventions at the weighing stations. The project includes the development of self-calibration algorithms, improvement of the methodology for verifying the operation quality of HS-WIM stations (through the development of methods for automatic verification of data accuracy and correctness, along with the determination of threshold values for deflections and longitudinal pavement smoothness that ensure a certain accuracy class), and the use of machine learning and artificial intelligence techniques to verify measurement errors.
Additionally, a model of the road surface–axle load sensor system is being developed, as well as the identification of the relationship between pavement smoothness and random error in axle load measurements.
