Federated Learning-Based Insulator Fault Detection for Data Privacy Preserving.

As the failure of power line insulators leads to the failure of power transmission systems, an insulator inspection system based on an aerial platform is widely used. Insulator defect detection is performed against complex backgrounds in aerial images, presenting an interesting but challenging problem. Traditional methods, based on handcrafted features or shallow-learning techniques, can only localize insulators and detect faults under specific detection conditions, such as when sufficient prior knowledge is available, with low background interference, at certain object scales, or under specific illumination conditions. This paper discusses the automatic detection of insulator defects using aerial images, accurately localizing insulator defects appearing in input images captured from real inspection environments. We propose a novel deep convolutional neural network (CNN) cascading architecture for performing localization and detecting defects in insulators. The cascading network uses a CNN based on a region proposal network to transform defect inspection into a two-level object detection problem. To address the scarcity of defect images in a real inspection environment, a data augmentation method is also proposed that includes four operations: 1) affine transformation; 2) insulator segmentation and background fusion; 3) Gaussian blur; and 4) brightness transformation. Defect detection precision and recall of the proposed method are 0.91 and 0.96 using a standard insulator dataset, and insulator defects under various conditions can be successfully detected. Experimental results demonstrate that this method meets the robustness and accuracy requirements for insulator defect detection.

This paper proposes an innovative approach for detecting defects in insulators of overhead transmission lines. It employs a real-time object detector (RT-DETR) model named RESRTDETR to address the challenges faced by traditional methods in multi-object scenarios and complex backgrounds. The study addressed the issues of low accuracy and missed detections in traditional target detection algorithms for insulator defect detection. First, we propose the ResRepNet feature extraction network, which integrates the RepVGG reparameterized structure into existing backbone feature extraction networks to enhance the ability to extract features from defects of varying sizes. Secondly, since the information from neighboring channels surrounding insulator features plays a crucial role in small object detection, the ECA cross-channel attention mechanism is introduced. This leads to the proposal of the CA-CCFM module based on the CCFM module, enhancing the expressive capability of the head layer’s output features. Furthermore, to address the inherent limitations of the GIOU loss function in spatial localization, we introduce a SIoU loss function incorporating an angle penalty term to enhance the geometric awareness of bounding box regression. Finally, to enable the model to effectively learn features, a standard dataset comprising seven categories of samples was reconstructed to address the issues of imbalanced distribution and missing annotations in the CID insulator defect dataset. Data augmentation methods based on geometric transformations, color transformations, and mosaic stitching were employed to provide data support for subsequent experiments. Experiments validated the model’s effectiveness. Compared to existing object detection methods, RESRTDETR improves mAP@50 to 96.4% on the CID dataset and to 84.2% on the IDDD dataset. This approach not only enhances the accuracy of insulator defect detection but also plays a crucial role in maintaining the safety of power transmission systems, carrying far-reaching implications.

With the wider adoption of edge computing services, intelligent edge devices, and high-speed V2X communication, compute-intensive tasks for autonomous vehicles, such as object detection using camera, LiDAR, and/or radar data, can be partially offloaded to road-side edge servers. However, data privacy becomes a major concern for vehicular edge computing, as sensitive sensor data from vehicles can be observed and used by edge servers. We aim to address the privacy problem by protecting both vehicles’ sensor data and the detection results. In this paper, we present vehicle–edge cooperative deep-learning networks with privacy protection for object-detection tasks, named vePOD for short. In vePOD, we leverage the additive secret sharing theory to develop secure functions for every layer in an object-detection convolutional neural network (CNN). A vehicle’s sensor data is split and encrypted into multiple secret shares, each of which is processed on an edge server by going through the secure layers of a detection network. The detection results can only be obtained by combining the partial results from the participating edge servers. We have developed proof-of-concept detection networks with secure layers: vePOD Faster R-CNN (two-stage detection) and vePOD YOLO (single-stage detection). Experimental results on public datasets show that vePOD does not degrade the accuracy of object detection and, most importantly, it protects data privacy for vehicles. The execution of a vePOD object-detection network with secure layers is orders of magnitude faster than the existing approaches for data privacy. To the best of our knowledge, this is the first work that targets privacy protection in object-detection tasks with vehicle–edge cooperative computing.

High-tension (HT) power line insulators are critical components of electrical transmission systems, and their failure due to cracks can lead to power outages and safety hazards. Traditional inspection methods are time-consuming, costly, and pose significant risks to the workers. This paper proposes an artificial intelligence (AI) based surveillance system for detecting insulator cracks. The surveillance system uses drones to capture high-resolution images of insulators and incorporates a target detection algorithm based on YOLOv11 (You Only Look Once), which utilizes the powerful learning ability of deep convolutional neural network (CNN) to classify the insulators as defective or non-defective. This method is trained on a large dataset of annotated samples. The experimental results show that the YOLOv11-based insulator defect detection method can effectively identify defective insulators from the drone-captured aerial images. Compared with the previous insulator defect identification methods, the accuracy and detection time are significantly improved. The proposed solution offers a safer, faster, and more cost-effective alternative to manual inspections, with potential applications in large-scale power line monitoring.

Insulator defect detection is a critical task in distribution network inspections. To address issues such as low detection accuracy, high model complexity, and large parameter counts caused by the variety of insulator defect types, this study propose a lightweight multi-defect detection network, LMD-YOLO, based on YOLOv8. The network improves the backbone by introducing SCConv module to improve C2f module, which reduces spatial and channel redundancy, lowering both computational complexity and the number of parameters. The SimAM attention mechanism is integrated to suppress irrelevant features and enhance feature extraction capabilities without adding extra parameters. The SIoU loss function is used in place of CIoU to accelerate model convergence and improve detection accuracy. Additionally, this study creates a target detection dataset that encompasses four types of insulators: insulator, absent insulator, broken insulator, and shedding insulator. Experimental results show that LMD-YOLO achieves a 2% higher average accuracy on the insulator dataset compared to YOLOv8n, with a 24.6% reduction in model parameters, offering an effective solution for smart grid inspections.

Insulators are critical components of transmission lines, and defective insulators pose a serious threat to the safety of power supply systems. Timely detection of these defects is crucial to prevent catastrophic consequences for human lives and property. However, insulator defects are often small and easily affected by the noise of rain, fog, sunlight, dirt, and other pollutants, making detection challenging. We observe that diffusion models learn data distribution by progressively introducing noise and subsequently performing denoising. The progressive denoising mechanism can naturally simulate the randomness of environmental noise. Based on this observation, we treat the localization of insulator defects as a denoising-based recovery process, where the true defect bounding boxes are progressively reconstructed from noisy representations. To this end, we propose a novel diffusion-based Insulator Defect Detector (IDDet) that is specifically designed to handle complex environmental noise. IDDet introduces noise to the true bounding boxes to generate noisy target boxes with random distributions and is then trained to recover the true bounding boxes from these noisy representations through a residual denoising diffusion mechanism. For the inference stage, IDDet refines the defect location from a random noise bounding box by gradually removing the noise, ultimately achieving the task of precisely locating the defect in the image. Experimental results show that IDDet significantly improves detection capability in noisy environments, achieving the best mean average precision (mAP) of 92.3%, confirming the feasibility and effectiveness of our approach.

The timely detection of insulator defects in transmission lines is vital for ensuring social production and people’s livelihoods. Aiming to solve the problem of the low accuracy of insulator defect detection in current detection models, this study improves the YOLO11n model and proposes an insulator defect detection model, FPFS-YOLO, that integrates FasterNet and an attention mechanism. In this study, to mitigate parameter redundancy in the backbone of the YOLO11n model, the FasterNet lightweight network was introduced, and some convolution was embedded into the shallow network to enhance its feature extraction ability. To solve problems such as insufficient attention to important features and the low detection ability of small defects in the YOLO11n model network, the ParNet attention mechanism was added, along with a small-defect detection layer, which improved the detection accuracy of the model. Finally, in order to alleviate the computational redundancy caused by these additions, the C3k2_faster module and the PSP-Head detection head were introduced. These amendments further improved the accuracy of the model network in detecting insulator defects while simultaneously reducing its computational redundancy. The experimental results show that the improved FPFS-YOLO model achieved a 91.5% mAP@50 and a 56.6% mAP@0.5-0.95, increases of 3.1% and 1.2%, respectively, while the precision and recall reached 93.2% and 86.4%, increases of 1.5% and 4.2%, respectively. The FPFS-YOLO model achieved a higher detection accuracy than the YOLO11n model and thus could be widely applied in the detection of insulator defects.

As power grid structure becomes increasingly complex, the impact of the operation status of key substation equipment on the safe and stable operation of the power grid is gradually increasing. Aiming at the problems of dense targets and occlusion recognition difficulties in the complex background of substations, an improved you-only-look-once (YOLO) v4 insulator defect detection algorithm is proposed. A large number of insulator and defect datasets were collected from the Internet. We use MobileNet-v2 to replace the backbone network of YOLOv4, and in view of the problem that the accuracy of YOLOv4 target detection model is not high for small targets or dense targets, convolutional block attention module (CBAM) attention mechanism is added to the backbone network to enhance the feature extraction ability, and ultra-lightweight subspace attention module (ULSAM) is added to the detection head to learn the cross-channel information. Experiments based on InDataset show that the insulator defect detection algorithm based on deep learning proposed achieves a high detection accuracy and detection speed; the mean average precision of the improved YOLOv4 model is 87.48%, and the recall rate of insulator defects reaches 79.84%, which meets the requirements of robustness and accuracy of insulator defect detection in real scenarios.

Insulator defect detection is important in ensuring power systems’ safety and stable operation. To solve the problems of its low accuracy, high delay, and large model size in complex environments, following the principle of progressive extraction from high-entropy details to low-entropy semantics, an improved YOLOv8 target detection network for insulator defects based on bidirectional weighted feature fusion was proposed. A C2f_DSC feature extraction module was designed to identify more insulator tube features, an EMA (encoder–modulator–attention) mechanism and a BiFPN (bidirectional weighted feature pyramid network) fusion layer in the backbone network were introduced to extract different features in complex environments, and EIOU (efficient intersection over union) as the model’s loss function was used to accelerate model convergence. The CPLID (China Power Line Insulator Dataset) was tested to verify the effectiveness of the proposed algorithm. The results show its model size is only 6.40 M, and the mean accuracy on the CPLID dataset reaches 98.6%, 0.8% higher than that of the YOLOv8n. Compared with other lightweight models, such as YOLOv8s, YOLOv6, YOLOv5s, and YOLOv3Tiny, not only is the model size reduced, but also the accuracy is effectively improved with the proposed algorithm, demonstrating excellent practicality and feasibility for edge devices.

In computer vision, significant advances have been made in recent years on object recognition and detection with the rapid development of deep learning, especially deep convolutional neural networks (CNN). The majority of deep learning methods for object detection have been developed for large objects and their performances on small-object detection are not very good. This paper contributes to research in low-resolution small-object detection by evaluating the performances of leading deep learning methods for object detection using a common dataset, which is a new dataset for bird detection, called Little Birds in Aerial Imagery (LBAI), created from real-life aerial imagery data. LBAI contains birds with sizes ranging from 10px to 40px. In our experiments, some of the best deep learning architectures were implemented and applied to LBAI, which include object detection techniques such as YOLOv2, SSH, and Tiny Face, in addition to small instance segmentation techniques including U-Net and Mask R-CNN. Among the object detection methods, experimental results demonstrated that SSH performed the best for easy cases, whereas Tiny Face performed the best for hard cases, i.e. where a cluttered background makes detecting birds difficult. Among small instance segmentation methods, experimental results revealed U-Net achieved slightly better performance than Mask R-CNN.

As a special insulation device, insulators play an important role in aerial transmission lines. It can be easily influenced by the wind load, snow load and wire swing in severe weather. The fault of the insulator will seriously affect and destroy the safety and normal operation of the entire transmission line. Therefore, in the operation and inspection of the transmission line, the detection of insulator defects must be strengthened. Since the insulators are constructed in a complex environment and the background of the images collected by air is also extremely complicated, traditional defect detection methods rely on specific scenarios for specific analysis and the robustness is weak. Changes in scenes, changes in UAV’s shooting angles, and changes in lighting conditions will all make it difficult for the model to get good inspection results. This paper proposes an algorithm for locating and detecting insulator defects based on an enhanced YOLO model. Due to the electromagnetic interference during the power inspection of the UAV, there is a certain amount of noise in the image of the aerial insulator. At the same time, in order to solve the problem of few shots which leads to training difficulty, this paper uses a variety of data augmentation, including affine transformation, Gaussian blur processing, gray scale transformation, brightness and contrast transformation and random erasing of pixels, and then the augmentation data is used to train different YOLO models. The results show that the detection algorithm based on the YOLO model meets the robustness and accuracy of insulator defect detection, and augmented experiment results are better than those of the conventional YOLOs in power line insulator defect detection tasks.

Three-phase induction motors (TIMs) play a key role in industrial production lines. Due to their robustness and versatility, TIMs are commonly used to drive different devices like fans, conveyors, sieves, and compressors. However, these devices are often exposed to mechanical and electrical faults. Among them, failures in stator winding insulation lead to severe damage to the TIMs and can cause operational interruptions. Therefore, several approaches have been developed to monitor electrical faults in induction motors. The acoustic emission (AE) stands out as an efficient non-invasive technique (NIT) for TIM diagnosis. In this work, the AE analysis was applied to detect winding insulation faults and identify which electrical phase was affected. To achieve this proposal, a TIM was subjected to insulation faults in each of the three electrical phases, and the acoustic signals were acquired by four piezoelectric sensors attached to the motor. These signals were processed using a new technique, which calculates the energy of a specific range of the signal spectrum and assigns the energy values of each piezoelectric sensor to a coordinate axis (x, y). By ploting the values for each fault condition, this technique allows the detection of insulation faults and correctly identifies the affected phase by clustering the resulting values. Finally, the proposed methodology presented satisfactory results in winding insulation diagnosis.

Insulators are important components of transmission lines. Aiming at the problems of small detection targets and complex detection backgrounds in the images of insulators taken by drones in power inspections, this paper proposes an improved BM-YOLOv5 insulator defect detection method based on the YOLOv5 network. The multi-head self-attention structure is introduced to improve the performance of the model to capture long-distance dependencies, so that it can pay attention to global information; the original feature pyramid structure is replaced with a weighted bidirectional feature pyramid structure, and additional weights are added to features of different scales. Make full use of features between different scales. Based on the newly constructed insulator defect data set with complex background and small targets, the method is compared with the commonly used insulator defect detection models YOLOv5, YOLOv3, Faster-RCNN, and SSD. Compared with YOLOv5, the average accuracy has increased by 5.1%.

In maritime surveillance systems, object detection plays a crucial role in ensuring the security of nearby waters by tracking the movement of various objects, such as ships and aircrafts, that are found at sea, detecting illegal activities and preemptively countering or predicting potential risks. Using vision sensors such as cameras to monitor the sea can help to identify the shape, size, and color of objects, enabling the precise analysis of maritime situations. Additionally, vision sensors can monitor or track small ships that may escape radar detection. However, objects located at considerable distances from vision sensors have low resolution and are small in size, rendering their detection difficult. This paper proposes a multifocal object detection associative network (MODAN) to overcome these vulnerabilities and provide stable maritime surveillance. First, it searches for the horizon using color quantization based on K-means; then, it selects and partitions the region of interest (ROI) around the horizon using the ROI selector. The original image and ROI image, converted to high resolution through the Super-Resolution Convolutional Neural Network (SRCNN), are then passed to the near-field and far-field detectors, respectively, for object detection. The weighted box fusion removes duplicate detected objects and estimates the optimal object. The proposed network is more stable and efficient in detecting distant objects than existing single-object detection models. Through performance evaluations, the proposed network exhibited an average precision surpassing that of the existing single-object detection models by more than 7%, and the false detection rate was reduced by 59% compared to similar multifocal-based state-of-the-art detection methods.

This research proposes a novel hardware-optimized design to accelerate Convolutional Neural Networks (CNNs) using Verilog HDL. The design is specifically developed for the DARKNET-19 system model, which serves as the backbone of the YOLOv3-tiny algorithm, a widely used framework for real-time object detection in dynamic environments. The CNN architecture was implemented in Verilog HDL and synthesized using Synopsys Design Compiler, with a focus on improving both object detection accuracy and hardware resource efficiency. The proposed design efficiently performs key CNN operations, including convolution, pooling, and activation, enabling faster real-time object detection compared to many existing methods. To improve performance, the hardware design incorporates parallel processing techniques, allowing multiple computations to be executed simultaneously. This significantly reduces the system latency and power consumption. The convolutional layers of the DARKNET-19 architecture are efficiently mapped onto the hardware platform, ensuring optimized data storage and fast memory access, which further enhances processing speed and detection accuracy. An innovative feature of the design is a 2-dimensional image preprocessing module that prepares input images before they are fed into the CNN. This preprocessing stage includes image resizing, brightness normalization, and color adjustment, which helps the CNN process visual data more effectively. After preprocessing, the images pass through several CNN layers. The convolutional layers extract key features from the images, while the pooling and activation layers refine these features to improve detection performance. Finally, the processed data is analyzed by the YOLOv3-tiny algorithm, which identifies and locates objects in the images with high precision. Experimental results demonstrate that the proposed high-speed and resource-efficient hardware architecture is well-suited for real-time object detection applications, particularly in highly dynamic and unpredictable environments.