Lifted truck axles detection by a combined method and their impact on road pavement

Abstract Overloaded transportation has been on the rise worldwide in recent years. However, overloaded vehicles negatively impact the lifespan of road pavements and bridges, and in some cases, can cause catastrophic accidents, such as bridge collapses. To mitigate these risks, accurately detecting, identifying, and classifying vehicles is crucial. This paper presents a conceptual framework that combines slim inductive loops with a camera‐based artificial intelligence (AI) solution for detecting lifted truck axles. By synthesizing existing literature, we identify current limitations and challenges in existing approaches and propose a novel method. This framework aims to enhance the ability of WIM stations to classify trucks with lifted axles more accurately, laying the foundation for future experimental and field validations. Moreover, the impact of lifted axles on pavement deterioration is evaluated using the Equivalent Standard Axle Load (ESAL) of standard C3 and T2S3 truck configurations. The results show that lifting a single axle increases pavement damage by a factor of about 1.3 for the C3 and 1.5 for the T2S3. Additionally, when the T2S3 is both overloaded and has one lifted axle, its pavement impact increases by a factor of about 2.