Fault detection of highway flow monitoring sensors based on grey correlation degree and neural network

Highway traffic monitoring sensors require real-time collection of a large amount of data, including traffic flow, vehicle speed, lane occupancy rate, etc. These data are not only large in volume, but also highly complex and dynamic, and are affected by various factors such as weather, road conditions, and vehicle types, which increase the difficulty of fault detection. This paper proposes a research method for fault detection of highway flow monitoring sensors based on grey relational analysis and neural networks. By using grey relational analysis to evaluate the correlation between highway traffic data and its influencing factors, the close relationship between key influencing factors and traffic has been determined. Furthermore, the BP neural network model is introduced to model and predict the output data of the flow monitoring sensor, and identify whether the sensor has malfunctioned. The experimental results show that the detection method combining grey correlation degree and neural network can effectively improve the accuracy and timeliness of fault detection, providing strong guarantee for the stable operation of highway flow monitoring system.