Aug 2026· Advanced Electromagnetics· Vol 15, pp. 5699-5706· 0 citations
TL;DR
The results demonstrate that the proposed approach effectively improves defect recognition performance and provides a practical solution for intelligent electromagnetic equipment inspection, condition monitoring, and reliability enhancement in advanced power systems.
Abstract
Addressing the limitations of traditional electrical equipment defect detection methods, including low efficiency, high missed detection rates, strong subjectivity, and insufficient real-time performance, this paper investigates the application of computer vision technology and corresponding strategies for improving recognition accuracy. Reliable defect identification is essential for ensuring the operational safety and electromagnetic reliability of modern power equipment and intelligent electromagnetic infrastructures. First, based on image processing, deep learning, and pattern recognition theories, a computer vision framework for electrical equipment defect detection is established, covering image acquisition, preprocessing, feature extraction, and defect classification. Second, through field investigations and experimental analysis, the visual characteristics of typical defects in transformers, circuit breakers, and insulators are systematically analyzed, while key challenges including complex environmental interference, limited small-sample recognition capability, and inadequate feature extraction are identified. Finally, an experimental platform is constructed using three representative categories of electrical engineering equipment, and comparative experiments are conducted to evaluate multiple optimization strategies. The results demonstrate that the proposed approach effectively improves defect recognition performance and provides a practical solution for intelligent electromagnetic equipment inspection, condition monitoring, and reliability enhancement in advanced power systems.
High voltage equipment, as a core component of power systems, plays an indispensable role in ensuring the reliability of power supply through its safe and stable operation. Traditional visual defect detection for high voltage equipment, however, often relies on manual inspection and experience‐based judgement, which struggles to meet the growing monitoring demands. Consequently, the introduction of more intelligent and precise large‐model technologies into the domain of high voltage equipment visual defect detection information processing is urgently required. The large‐scale foundational visual models, with their robust data processing capabilities, complex pattern recognition and reasoning abilities, are progressively penetrating various industries, serving as a key driver for industrial upgrades and transformation. In the field of high voltage equipment, the application prospects of foundational visual models are particularly promising. In this paper, we provide a comprehensive review of the research progress on visual large models in the specific context of high voltage equipment. It summarises a concise overview of the engineering challenges that foundational visual models need to tackle. Furthermore, based on research achievements from the era of smaller models, we thoroughly examine the application potential of large‐model technologies in the high voltage equipment domain. Additionally, we also identify and scrutinise the scientific issues associated with visual large models. At present, research on vision foundation models for high voltage equipment is still in its early stages both domestically and internationally. Significant gaps remain in areas such as dataset construction, pretraining and fine‐tuning, all of which present promising directions with immense application potential. The primary objective of this paper is to offer a comprehensive and systematic review of large pretrained models for high voltage equipment defect detection methods, providing valuable reference for researchers exploring this field.
Zhenbing Zhao, Shuo Feng, Teng Ma et al.· High Voltage· 0 citations
The manufacturing process of the industry requires very high quality standards to guarantee reliability and suitability of the product, level of customer satisfaction and economical efficiency of the product. The fact is that even small defects may cause some heavy loss of money, risks, and damaged reputation. Conventional defect inspection systems are often based on manual inspection and classical machine vision methods, which is time consuming, subjective and prone to errors and it is hard to scale into large scale production set ups today. The recent fast development of computer vision technology using the methods of deep learning and artificial intelligence has also changed the nature of automated defect detection systems dramatically. The current computer vision methods including convolutional neural networks (CNNs), transformer networks, and mixed learning systems have shown outstanding results when detecting surface defects, structural deformities and functional defects in many industrial settings. The paper is an in-depth research on the industrial defect detection with the help of the modern computer vision methodology, including the theoretical bases, the current approach methods, and the practical aspect of their implementation. The suggested framework incorporates the advanced image acquisition, preprocessing and deep features extraction, and intelligent classification algorithms to obtain a high level of detection and strong stability in adverse industrial environments. Extensive trials indicate the efficiency of the contemporary vision-based solutions to decrease false positives, accelerate the speed of inspection, and maintain the quality control. The outcomes verify that defect detection systems based on deep learning are far more effective than conventional inspection and can be utilized in practice in the industrial environment on a real-time basis. The paper ends with the determination of the current limitations and research areas to explore in the future in the field of scalable and explainable defect detectors in smart factories.
Idris Mohammed· International Journal of App...· 0 citations
Photovoltaic (PV) modules are increasingly deployed in large-scale renewable energy systems, making reliable defect detection and fault diagnosis essential for operational safety, energy yield, and maintenance efficiency. This review systematically examines computer vision-based approaches for PV module inspection from a decision-oriented perspective. First, it summarizes representative PV defects, including cracks, hot spots, soiling, shading, delamination, corrosion, broken cells, finger interruptions, burn marks, and bypass diode-related anomalies, and discusses their visual manifestations, physical origins, diagnostic implications, and maintenance relevance. Second, it reviews major imaging modalities, including electroluminescence imaging, infrared thermography, RGB imaging, and UAV-based inspection, highlighting their complementary roles in detecting internal, thermal, and surface-level defects. Third, it analyzes key computer vision tasks, such as image classification, object detection, semantic and instance segmentation, anomaly detection, and severity assessment. The review emphasizes that PV inspection should move beyond normal/defective recognition toward quantitative and trustworthy fault diagnosis. Finally, it discusses current challenges and future perspectives, including field robustness, data scarcity, small-defect detection, multimodal fusion, explainability, uncertainty estimation, edge deployment, and human-in-the-loop maintenance decision-making. This review provides a structured reference for developing intelligent and actionable PV inspection systems.
Yake Xue, Hao Ren· International Journal of Inf...· 0 citations
Recommendations are formulated for choosing an optimal machine vision architecture for different types of production, and promising directions for further development of the technology in the context of industrial digital transformation are identified.
Ya.A. Gaidukov, M. Naumov· Glavnyj mekhanik (Chief Mech...· 0 citations
Automated mechanical inspection is an important requirement in modern manufacturing industries for detecting dimensional errors, surface defects, cracks, missing components, and improper assembly. Conventional inspection methods often depend on manual operators or PC-based image-processing systems, which can introduce inspection delays and inconsistent results. This work proposes an FPGA-based machine vision system for automated mechanical inspection, combining image acquisition, preprocessing, feature extraction, defect detection, and decision-making on a reconfigurable FPGA platform. A camera captures images of mechanical components placed in a controlled inspection area. The acquired image is converted into a suitable digital format and processed using FPGA-based image-processing algorithms such as grayscale conversion, noise filtering, thresholding, edge detection, and morphological operations. Extracted features are compared with predefined dimensional and quality criteria to identify defective components. The FPGA provides parallel processing and low-latency operation, making the proposed system suitable for real-time industrial inspection. The system can generate a pass/fail decision and activate a sorting mechanism through suitable control interfaces. The proposed architecture offers improved processing speed, reduced dependence on external computers, and flexible hardware implementation. It can be applied to inspection of gears, shafts, bearings, castings, welds, electronic-mechanical assemblies, and other manufactured components.
Jeyasudha S, Radhakrishnan B, Sowmiya C et al.· International Research Journ...· 0 citations
With the rapid development of artificial intelligence, the Internet of Things, and computer vision technologies, bridge structural health monitoring is increasingly evolving toward intelligent and automated inspection. As one of the most common structural defects, bridge surface cracks require timely and accurate identification, which is of great significance for bridge safety assessment, maintenance decision-making, and long-term service performance evaluation. However, conventional crack detection approaches mainly rely on manual inspection and traditional image processing algorithms, which are often limited by low efficiency, insufficient detection accuracy, strong subjectivity, and poor adaptability to complex environmental conditions. To address these limitations, this paper proposes an intelligent bridge surface crack detection method based on an improved convolutional neural network and metric representation learning. Specifically, a crack detection model is constructed using the TensorFlow framework and the Keras deep learning library. The proposed model employs convolutional neural networks to automatically extract edge, texture, and morphological features from bridge crack images. Meanwhile, the loss function and model parameters are further optimized, and metric representation learning is introduced to transform crack detection into an anomaly detection problem in the pixel embedding space, which improves the ability to distinguish subtle cracks from complex backgrounds by constructing a discriminative feature manifold. Experimental results demonstrate that the proposed method can effectively identify cracks on bridge surfaces, achieves a detection accuracy of 98.23% on the self-built dataset, and provides a feasible technical paradigm for the application of deep learning in bridge structural health monitoring.
Yuyao Liu· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
