Automatic Detection and Classification of Surface Diseases on Roads and Bridges Using Fuzzy Neural Networks

Cracks, damages, roadbed subsidence, and potholes often occur during the use of road surfaces and bridges. These diseases not only cost huge maintenance costs and time, but also seriously affect the performance of road surfaces and driving safety, causing dual losses in economic and social benefits. In the current road detection methods, traditional detection methods mainly rely on manpower, which is time-consuming, labor-intensive, inefficient, and prone to causing traffic congestion, posing significant safety issues. This article proposes a method for automatic detection and classification of road and bridge surface diseases using fuzzy neural networks (FNN). Firstly, by collecting and preprocessing data, the characteristics of surface diseases on roads and bridges are extracted. Then, using fuzzification techniques, these determined values are transformed into fuzzy membership functions to better handle uncertainty and fuzziness, and an FNN is constructed to train the network using image data of known categories, enabling it to learn the features of diseases. The experimental results show that the method proposed in this paper can greatly improve the accuracy and efficiency of detection, timely detect surface diseases of roads and bridges, and provide important reference for the maintenance and upkeep of roads and bridges.