IoT and Machine Learning for Efficient Truck Overload Detection and Prevention

Truck overloading occurs when a vehicle carries more weight than it is designed to handle. This practice is a significant safety hazard and can have detrimental consequences for both drivers and road infrastructure. This research aims to develop a robust and accurate model for predicting truck overloads, thereby enhancing road safety, reducing infrastructure damage, and improving transportation efficiency. By effectively identifying overloaded trucks, we can prevent accidents, minimize environmental impact, and ensure compliance with transportation regulations. It presents an integrated system for real-time truck overload detection and alarming. A NodeMCU- ESP8266 microcontroller acts as the system's central processing unit, processing load data and initiating appropriate actions. By integrating mobile devices and onboard technologies, fleet managers and truck operators can receive timely alerts and monitor truck loads, enhancing safety, efficiency, and sustainability in transportation operations. The proposed system involves strategically placed load cells at checkpoints before flyovers. As trucks pass over the load cells, their weight is calculated, and the microcontroller processes the data. If the truck is found to be overloaded, a gateway to the flyover is closed, forcing the truck to take an alternative route as indicated by the vehicle's navigation system. This innovative approach effectively prevents overloaded trucks from accessing flyovers, mitigating potential risks and ensuring compliance with weight regulations.