RESRTDETR: Cross-Scale Feature Enhancement Based on Reparameterized Convolution and Channel Modulation

In this paper, a method for detecting the self explosion defect of transmission line insulator based on Cascade RCNN is proposed. This method is proposed to improve the accuracy of insulator defect detection based on deep learning. The ResNeXt101 network is used as the feature extraction network of this method. This method improves the generalization ability of the network. It reduces the number of super parameters without increasing the network parameters, and reduces the difficulty of network design and computational overhead. It improves the detection accuracy of the self explosion defect of transmission line insulator. This paper selects three common methods for comparison: Cascade RCNN detection method with ResNet101 as feature extraction network, Faster RCNN detection method with ResNeXt101 as feature extraction network and RetineNet detection method with ResNeXt101 as feature extraction network. Through experimental analysis, the proposed method has higher reliability, average accuracy and stronger generalization ability. It significantly improves the detection accuracy of self explosion defects of transmission line insulators.

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.

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.

DeLiVoTr: Deep and light-weight voxel transformer for 3D object detection

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.

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.

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.

To tackle the issue of low detection accuracy in insulator images caused by intricate backgrounds and small defect sizes, as well as the requirement for real-time detection on embedded and mobile devices, this research introduces the YOLOv5s-KE model. Integrating multiple strategies, YOLOv5s-KE aims to boost detection accuracy significantly. Initially, an enhanced anchor generation method utilizing the K-means++ algorithm is proposed to generate more appropriate anchor boxes for insulator defects. Moreover, an attention mechanism is integrated into both the backbone and neck networks to enhance the model’s capacity to focus on defect features and resist interference. To improve the detection of small defects, the EIoU loss function is implemented in place of the original CIoU loss function. In order to meet the real-time detection needs on embedded and mobile devices, the model is further refined through the integration of Ghost convolution for lightweight feature extraction and a linear transformation to reduce the computational burden of standard convolution. A channel pruning strategy is deployed to optimize the sparsely trained network, diminishing redundancy, and improving model generalization. Additionally, the CARAFE operator replaces the original upsampling operator to minimize model parameters and elevate detection speed. Experimental outcomes demonstrate that YOLOv5s-KE achieves a detection accuracy of 92.3% on the Chinese transmission line insulator dataset, marking a 5.2% enhancement over the original YOLOv5s. The streamlined version of YOLOv5s-KE achieves a detection speed of 94.3 frames per second, indicating an improvement of 30.1 frames per second compared to the original model. Model parameters are condensed to 9.6 M, resulting in a detection accuracy of 91.1%. This study underscores the precision and efficiency of the proposed approach, suggesting that the advanced strategies explored introduce novel possibilities for insulator defect detection.

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%.

Insulators are widely used in distribution network transmission lines and serve as critical components of the distribution network. The detection of insulator faults is essential to ensure the safe and stable operation of the distribution network. Traditional insulator detection methods often rely on manual identification, which is time-consuming, labor-intensive, and inaccurate. The use of vision sensors for object detection is an efficient and accurate detection method that requires minimal human intervention. Currently, there is a considerable amount of research on the application of vision sensors for insulator fault recognition in object detection. However, centralized object detection requires uploading data collected from various substations through vision sensors to a computing center, which may raise data privacy concerns and increase uncertainty and operational risks in the distribution network. Therefore, this paper proposes a privacy-preserving insulator detection method based on federated learning. An insulator fault detection dataset is constructed, and Convolutional Neural Network (CNN) and Multi-Layer Perceptron (MLP) models are trained within the federated learning framework for insulator fault detection. Most of the existing insulator anomaly detection methods use a centralized model training method, which has the advantage of achieving a target detection accuracy of over 90%, but the disadvantage is that the training process is prone to privacy leakage and lacks privacy protection capability. Compared with the existing insulator target detection methods, the proposed method can also achieve an insulator anomaly detection accuracy of more than 90% and provide effective privacy protection. Through experiments, we demonstrate the applicability of the federated learning framework for insulator fault detection and its ability to protect data privacy while ensuring test accuracy.

Insulators play an important role in supporting and securing live conductors. In the task of insulator fault detection, existing models often miss small targets due to the interference of complex backgrounds. Furthermore, due to the very large aspect ratio of the insulators themselves, most models contain extraneous background in their results. To solve the above problems, this paper makes full use of the characteristics of the insulator itself and optimizes YOLOv5 from four aspects: feature extraction, feature fusion, candidate frame generation, and loss function. We divide the image feature extraction process into two procedures. The first procedure is mainly responsible for extracting insulator images from complex backgrounds, and the second stage is based on the extracted insulator images for fault analysis. At the same time, considering the trouble that the objective is too small due to the shooting distance, we design an attention mechanism that is more suitable for practical needs to enhance the ability to capture small objects. Furthermore, we design a rotated candidate box to improve the quality of the predicted box and reduce irrelevant background. The FAIN_detection dataset is compared with various advanced detection methods. The proposed method is more effective than the previous model by verifying the self-made data. Notably, the model achieved an average accuracy of 98% at 29 frames per second (FPS), laying the foundation for automatic insulator fault detection.

Small object detection is always a hot research direction in the field of computer vision, and widely used in traffic, production, industry, and other fields. A neural network for detecting small objects based on original Cascade RCNN is proposed. First, we modify the traditional feature pyramid network and introduce multi-branch dilated convolutions to enhance the feature information of the small target. Second, the feature extraction networks in original Cascade RCNN are replaced with multi-layer deformable convolution networks, which can better adapt to the geometric variations of detection target and huge size span of the objects in the same scene. Finally, Soft non-maximum suppression is also integrated into the network to avoid problems in dense object detection. To verify the practicability of our proposed network, we apply it to the garbage detection system. The experimental results show that compared with original Cascade RCNN and other commonly used target detection networks, our proposed method, with a recall rate >0.98 as well as mean average precision up to 0.964, performs better not only in small object detection but also in industrial applications.

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.

Transformer-based methodologies in object detection have recently piqued considerable interest and have produced impressive results. DETR, an end-to-end object detection framework, ingeniously integrates the Transformer architecture, traditionally used in NLP, into computer vision for sequence-to-sequence prediction. Its enhanced variant, DINO, featuring improved denoising anchor boxes, has showcased remarkable performance on the COCO val2017 dataset. However, it often encounters challenges when applied to scenarios involving small object detection. Thus, we propose an innovative method for feature enhancement tailored to recursive prediction tasks, with a particular emphasis on augmenting small object detection performance. It primarily involves three enhancements: refining the backbone to favor feature maps that are more sensitive to small targets, incrementally augmenting the number of queries for small objects, and advancing the loss function for better performance. Specifically, The study incorporated the Switchable Atrous Convolution (SAC) mechanism, which features adaptable dilated convolutions, to increment the receptive field and thus elevate the innate feature extraction capabilities of the primary network concerning diminutive objects. Subsequently, a Recursive Small Object Prediction (RSP) module was designed to enhance the feature extraction of the prediction head for more precise network operations. Finally, the loss function was augmented with the Normalized Wasserstein Distance (NWD) metric, tailoring the loss function to suit small object detection better. The efficacy of the proposed model is empirically confirmed via testing on the VISDRONE2019 dataset. The comprehensive array of experiments indicates that our proposed model outperforms the extant DINO model in terms of average precision (AP) small object detection.

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.