Federated knowledge distillation for enhanced insulator defect detection in resource-constrained environments

Insulator defect detection is crucial for the stable operation of power systems. It has become a mainstream research direction to realise insulator defect detection based on the combination of line images captured by UAVs and deep learning techniques. However, the existing high-quality insulator defect detection models still face problems such as relying on massive-labelled data and huge model parameters. Especially on resource-constrained devices, it becomes a challenge to strike a balance between model lightweighting and performance. Although the knowledge distillation technique provides a solution for model lightweighting, the loss of information in the distillation process leads to the performance degradation of small models, which in turn creates a paradox between lightweighting and performance. Hence, an insulator defect detection method based on federated knowledge distillation is proposed. The method not only realises the lightweighting of the model, but also effectively improves the model performance by collaboratively training the model through the federated learning approach. Moreover, the asynchronous aggregation approach and model freshness mechanism designed in the method further enhance the training efficiency and collaborative effect. The experimental results show that the detection accuracy and efficiency of this paper's method on public datasets are significantly better than the benchmark algorithm. A new framework for insulator defect detection methods in resource-constrained environments is proposed. With the help of the clever design of knowledge distillation and federated learning, that is, model freshness, this paper achieves the lightweighting of the traditional deep learning-based insulator defect detection model and ensures the guarantee of the model performance after the lightweighting. image