Jie Li

Insulators are critical insulation components in power transmission lines; however long-term exposure to adverse environmental conditions may threaten the safety and stability of power delivery. Existing studies primarily emphasize detection accuracy, while deployment efficiency and inference speed have received insufficient attention, limiting their applicability to CPU-based edge computing devices. To address these limitations, this paper proposes PEBL-YOLO, a lightweight model for insulator defect detection. The proposed model retains the external C3k2 structure of YOLOv11 while simplifying its internal bottleneck module, in which PConv is embedded to improve spatial feature extraction and fusion efficiency. In the neck, the original Path Aggregation Feature Pyramid Network (PAFPN) is reconstructed by integrating a Bidirectional Feature Pyramid Network (BiFPN) with Efficient Channel Attention (ECA), enabling more effective aggregation of multi-scale features and stronger focus on defect-related regions with minimal parameter increase. Moreover, a lightweight shared decoupled detection head is designed to decouple classification and regression branches. By combining parameter sharing with Group Normalization (GN) the detection head further reduces model complexity while maintaining accurate localization capability. Experimental results show that PEBL-YOLO contains only 1.68 M parameters. It achieves Precision, Recall, mAP@0.5, and mAP@0.5:0.95 of 95.0%, 92.1%, 94.4%, and 53.6%, respectively. These results demonstrate that PEBL-YOLO achieves a favorable trade-off between detection accuracy and parameter efficiency, providing a practical solution for lightweight insulator defect detection in edge computing scenarios.

Due to centralized storage, centralization problems are common in machine learning model training and invocation, which makes train data and trained models extremely vulnerable to tampering and stealing. A safe framework for training and invoking models called ISC-MTI (IPFS (InterPlanetary File System) and Smart Contract-Based Method for Storage and Invocation of Machine Learning Mobel) is proposed in this paper. The framework uses IPFS as the storage solution, EOS (Enterprise Operation System) blockchain as the smart contract platform, RSA and AES as the implementation of encrypted communication. The Action responsible for invoking the training data and trained models in the smart contract and the model training, uploading, and invoking methods are designed. The experimental results demonstrate that ISC-MTI can improve the safety of model training and invocation with losing a little efficiency. Simultaneously, ISC-MTI can provide anti-theft model capabilities, traceability, tamper resistance, reliability, and privacy for the process.