Fault Detection of Wind Turbine Blades Using Hopfield Network Combined with Image Recognition

Aiming at the safety hazard of fan blade fault, Hopfield neural network combined with sub-pixel image matching method is used to detect the fault of fan blade. Firstly, the UAV is used to collect the image of the wind turbine blade, and the manual annotation is used as the original sample. Then the Hopfield neural network is used for training to distinguish the faulty blade from the normal blade. For the faulty wind turbine blade, the sub-pixel image matching is carried out to identify the specific location of the fault on the blade. The results show that this method can quickly determine whether the fan blade has a fault, and accurately find the specific location of the fault. While achieving high accuracy, it also takes into account rapid detection.