LA_YOLOv8s: A lightweight-attention YOLOv8s for oil leakage detection in power transformers

Abstract

To detect the oil leakage problem of the power transformer in time and guarantee the normal operation of the power system, this paper proposes a lightweight-attention YOLOv8s, called LA_YOLOv8s, for oil leakage detection in the power transformer. First, the idea of lightweight structure + attention is used to redesign the backbone and neck of the original network respectively, which greatly reduces the number of parameters and calculation amount, but also retains strong feature extraction ability. Second, the dynamic head frame Dyhead is used to improve the representation ability of the detection head. Finally, the Wise-IoU bounding box loss function with a dynamic non-monotonic focusing mechanism is used to further improve the overall performance of the model by balancing the learning of high and low-quality samples. Using a self-constructed outdoor power transformer oil leakage dataset for training and testing, the results show that compared with the original model, the attention of LA_YOLOv8s becomes focused, enabling the network to detect oil leaks in power transformers better. LA_YOLOv8s greatly reduces the number of parameters and computation, while maintaining the same detection performance as the original network, which is conducive to engineering deployment.

Keywords

• Power transformer oil leakage detection
• YOLOv8
• DBB
• BIFPN
• Dyhead
• WIoU