Search Results (350)

As large language models (LLMs) increasingly enter specialized domains, inference without external resources often leads to knowledge gaps, opaque reasoning, and hallucinations. To address these challenges in power equipment defect grading, we propose a zero-shot question-answering framework that requires no task-specific examples. Our system performs two-stage retrieval—first using a Sentence-BERT model fine-tuned on power equipment maintenance texts for coarse filtering, then combining TF-IDF and semantic re-ranking for fine-grained selection of the most relevant knowledge snippets. We embed both the user query and the retrieved evidence into a Chain-of-Thought (CoT) prompt, guiding the pre-trained LLM through multi-step reasoning with self-validation and without any model fine-tuning. Experimental results show that on a held-out test set of 218 inspection records, our method achieves a grading accuracy of 54.2%, which is 6.0 percentage points higher than the fine-tuned BERT baseline at 48.2%; an Explanation Coherence Score (ECS) of 4.2 compared to 3.1 for the baseline; a mean retrieval latency of 28.3 ms; and an average LLM inference time of 5.46 s. Ablation and sensitivity analyses demonstrate that a fine-stage retrieval pool size of k = 30 offers the optimal trade-off between accuracy and latency; human expert evaluation by six senior engineers yields average Usefulness and Trustworthiness scores of 4.1 and 4.3, respectively. Case studies across representative defect scenarios further highlight the system’s robust zero-shot performance. Full article

The improvement of environmental conditions has become a priority for governments and legislators. New electrified mobility systems are increasingly present in our environment, as they enable the reduction of polluting emissions. Electric vehicles (EVs) are one of the fastest-growing alternatives to date, with exponential growth expected over the next few years. In this article, the various charging modes for EVs are explored, and the risks associated with charging technologies are analysed, particularly for charging systems in high-power DC with Lithium battery energy storage, given their long market deployment and characteristic behaviour. In particular, the Arc Flash (AF) risk present in high-power DC chargers will be studied, involving numerous simulations of the charging process. Subsequently, the Incident Energy (IE) analysis is carried out at different specific points of a commercial high-power ‘Mode 4’ charger. For this purpose, different analysis methods of recognised prestige, such as Doan, Paukert, or Stokes and Oppenlander, are applied, using the latest version of the ETAP^® simulation tool version 22.5.0. This study focuses on quantifying the potential severity (consequences) of an AF event, assuming its occurrence, rather than performing a probabilistic risk assessment according to standard methodologies. The primary objective of this research is to comprehensively quantify the potential consequences for workers involved in the operation, maintenance, repair, and execution of tasks related to EV charging systems. This analysis makes it possible to provide safe working conditions and to choose the appropriate and necessary personal protective equipment (PPE) for each type of operation. It is essential to develop this novel process to quantify the consequences of AF and to protect the end users of EV charging systems. Full article

Maintenance techniques are fundamental in the context of the safe operation of continuous process installations, especially in electrical energy-transmission and/or -distribution substations. The operating conditions of power transformers are fundamental for the safe functioning of the electrical power system. Predictive maintenance consists of periodically monitoring the asset in use, in order to anticipate critical situations. This article proposes a methodology based on data science, machine learning and the Internet of Things (IoT), to track operational conditions over time and evaluate transformer aging. This characteristic is achieved with the development of a synchronization method for different databases and the construction of a model for estimating ambient temperatures using k-Nearest Neighbors. In this way, a history assessment is carried out with more consistency, given the environmental conditions faced by the equipment. The work evaluated data from three power transformers in different geographic locations, demonstrating the initial applicability of the method in identifying equipment aging. Transformer TR1 showed aging of $3.24\times {10}^{-3}\%$, followed by TR2 with $8.565\times {10}^{-3}\%$ and TR3 showing $294.17\times {10}^{-6}\%$ in the evaluated period of time. Full article

Substation equipment defect detection is a critical aspect of ensuring the reliability and stability of modern power grids. However, existing deep-learning-based detection methods often face significant challenges in real-world deployment, primarily due to low detection accuracy and inconsistent anomaly definitions across different substation environments. To address these limitations, this paper proposes the Language-Guided Enhanced Anomaly Power Equipment Detection Network (LEAD-Net), a novel framework that leverages text-guided learning during training to significantly improve defect detection performance. Unlike traditional methods, LEAD-Net integrates textual descriptions of defects, such as historical maintenance records or inspection reports, as auxiliary guidance during training. A key innovation is the Language-Guided Anomaly Feature Enhancement Module (LAFEM), which refines channel attention using these text features. Crucially, LEAD-Net operates solely on image data during inference, ensuring practical applicability. Experiments on a real-world substation dataset, comprising 8307 image–text pairs and encompassing a diverse range of defect categories encountered in operational substation environments, demonstrate that LEAD-Net significantly outperforms state-of-the-art object detection methods (Faster R-CNN, YOLOv9, DETR, and Deformable DETR), achieving a mean Average Precision (mAP) of 79.51%. Ablation studies confirm the contributions of both LAFEM and the training-time text guidance. The results highlight the effectiveness and novelty of using training-time defect descriptions to enhance visual anomaly detection without requiring text input at inference. Full article

Accurate measurement of high voltages is required to guarantee the safe and stable operation of power systems. Modern power systems, which are mainly based on new energy sources, require high-voltage measurement instruments and equipment with characteristics such as high accuracy, wide frequency bandwidth, broad operating ranges, and ease of operation and maintenance. However, it is difficult for traditional electromagnetic measurement transformers to meet these requirements. To address the limitations of conventional Rydberg atomic measurement methods in low-frequency applications, this paper proposes an enhanced Rydberg measurement approach featuring high sensitivity and strong traceability, thereby enabling the application of Rydberg-based measurement methodologies under power frequency conditions. In this paper, a 110 kV high-voltage measurement method based on Rydberg atoms is studied. A power-frequency electric field measurement device is designed using Rydberg atoms, and its internal electric field distribution is analyzed. Additionally, a decoupling method is proposed to facilitate voltage measurements under multi-phase overhead lines in field conditions. The feasibility of the proposed method is confirmed, providing support for the future development of practical measurement devices. Full article

This paper provides a reliability analysis of selected components in the electrical power supply systems used for railway traffic control equipment. It includes rectifiers, controllers, inverters, generators, batteries, sensors, and switching elements. The study used failure data from power supply system elements on selected railway lines. The analysis was performed using a mathematical model based on Markov processes. Based on the findings, recommendations were made to improve safety levels. The results presented in the paper could serve as a valuable source of information for operators of power supply systems in railway traffic control, helping them optimize maintenance processes and increase equipment reliability. Full article

Predictive maintenance (PdM) is a proactive strategy that enhances safety, minimizes unplanned downtime, and optimizes operational costs by forecasting equipment failures before they occur. This study presents a novel Field Programmable Gate Array (FPGA)-accelerated predictive maintenance framework for UAV engines using a Singular Value Decomposition (SVD)-optimized Long Short-Term Memory (LSTM) model. The model performs binary classification to predict the likelihood of imminent engine failure by processing normalized multi-sensor data, including temperature, pressure, and vibration measurements. To enable real-time deployment on resource-constrained UAV platforms, the LSTM’s weight matrices are compressed using Singular Value Decomposition (SVD), significantly reducing computational complexity while preserving predictive accuracy. The compressed model is executed on a Xilinx ZCU-104 FPGA and uses a pipelined, AXI-based hardware accelerator with efficient memory mapping and parallelized gate calculations tailored for low-power onboard systems. Unlike prior works, this study uniquely integrates a tailored SVD compression strategy with a custom hardware accelerator co-designed for real-time, flight-safe inference in UAV systems. Experimental results demonstrate a 98% classification accuracy, a 24% reduction in latency, and substantial FPGA resource savings—specifically, a 26% decrease in BRAM usage and a 37% reduction in DSP consumption—compared to the 32-bit floating-point SVD-compressed FPGA implementation, not CPU or GPU. These findings confirm the proposed system as an efficient and scalable solution for real-time UAV engine health monitoring, thereby enhancing in-flight safety through timely fault prediction and enabling autonomous engine monitoring without reliance on ground communication. Full article

Structural health monitoring (SHM) plays a pivotal role in ensuring the integrity and safety of critical infrastructure and mechanical components. While traditional non-destructive testing (NDT) methods offer high-resolution data, they typically require periodic access and disassembly of equipment to conduct inspections. In contrast, SHM employs permanently installed, cost-effective sensors to enable continuous monitoring, though often with reduced detail. This study presents an integrated hybrid SHM-NDT methodology enhanced by deep learning to enable the real-time monitoring and classification of mechanical stresses in structural components. As a case study, a 6-foot-long parallel flange I-beam, representing bridge truss elements, was subjected to variable bending loads to simulate operational conditions. The hybrid system utilized an ultrasonic transducer (NDT) for excitation and piezoelectric sensors (SHM) for signal acquisition. Signal data were analyzed using 1D and 2D convolutional neural networks (CNNs), long short-term memory (LSTM) models, and random forest classifiers to detect and classify load magnitudes. The AI-enhanced approach achieved 100% accuracy in 47 out of 48 tests and 94% in the remaining tests. These results demonstrate that the hybrid SHM-NDT framework, combined with machine learning, offers a powerful and adaptable solution for continuous monitoring and precise damage assessment of structural systems, significantly advancing maintenance practices and safety assurance. Full article

Dissolved gas analysis remains the most widely utilized non-intrusive diagnostic method for detecting incipient faults in insulating liquid-immersed transformers. Despite their prevalence, conventional ratio-based methods often suffer from ambiguity and limited potential for automation applicrations. To address these limitations, this study proposes a unified multiclass classification model that integrates traditional gas ratio features with supervised machine learning algorithms to enhance fault diagnosis accuracy. The performance of six machine learning classifiers was systematically evaluated using training and testing data generated through four widely recognized gas ratio schemes. Grid search optimization was employed to fine-tune the hyperparameters of each model, while model evaluation was conducted using 10-fold cross-validation and six performance metrics. Across all the diagnostic approaches, ensemble models, namely random forest, XGBoost, and LightGBM, consistently outperformed non-ensemble models. Notably, random forest and LightGBM classifiers demonstrated the most robust and superior performance across all schemes, achieving accuracy, precision, recall, and F1 scores between 0.99 and 1, along with Matthew correlation coefficient values exceeding 0.98 in all cases. This robustness suggests that ensemble models are effective at capturing complex decision boundaries and relationships among gas ratio features. Furthermore, beyond numerical classification, the integration of physicochemical and dielectric properties in this study revealed degradation signatures that strongly correlate with thermal fault indicators. Particularly, the CIGRÉ-based classification using a random forest classifier demonstrated high sensitivity in detecting thermally stressed units, corroborating trends observed in chemical deterioration parameters such as interfacial tension and CO₂/CO ratios. Access to over 80 years of operational data provides a rare and invaluable perspective on the long-term performance and degradation of power equipment. This extended dataset enables a more accurate assessment of ageing trends, enhances the reliability of predictive maintenance models, and supports informed decision-making for asset management in legacy power systems. Full article

With the digital transformation of power systems, higher demands are being placed on smart grids for the timely and precise acquisition of the status of transmission and transformation equipment during operational and maintenance processes. When a transformer is energized under no-load conditions, an excitation inrush phenomenon occurs in the windings, posing a hazard to the stable operation of the power system. A machine learning approach is proposed in this paper for predicting the internal magnetic field of transformers under excitation inrush condition, enabling the monitoring of transformer operation status. Experimental results indicate that the mean absolute percentage error (MAPE) for predicting the transformer’s magnetic field using the deep neural network (DNN) model is 4.02%. The average time to obtain a single magnetic field data prediction is 0.41 s, which is 46.68 times faster than traditional finite element analysis (FEA) method, validating the effectiveness of machine learning for magnetic field prediction. Full article

The safe and stable operation of hydropower units, as core equipment in clean energy systems, is crucial for power system security. However, anomaly detection under complex operating conditions remains a technical challenge in this field. This paper proposes a hydropower unit anomaly detection method based on K-means seeded quadratic discriminant clustering and an adaptive density-aware ensemble anomaly detection algorithm (KSQDC-ADEAD). The method first employs the KSQDC algorithm to identify different operating conditions of hydropower units. By combining K-means clustering’s initial partitioning capability with quadratic discriminant analysis’s nonlinear decision boundary construction ability, it achieves the high-precision identification of complex nonlinear condition boundaries. Then, an ADEAD algorithm is designed, which incorporates local density information and improves anomaly detection accuracy and stability through multi-model ensemble and density-adaptive strategies. Validation experiments using 14-month actual operational data from a 550 MW unit at a hydropower station in Southwest China show that the KSQDC algorithm achieves a silhouette coefficient of 0.64 in condition recognition, significantly outperforming traditional methods, and the KSQDC-ADEAD algorithm achieves comprehensive scores of 0.30, 0.34, and 0.23 for anomaly detection at three key monitoring points, effectively improving the accuracy and reliability of anomaly detection. This method provides a systematic technical solution for hydropower unit condition monitoring and predictive maintenance. Full article

This paper develops a model to calculate carbon emissions during the construction period of dredging projects. Carbon emission quotas for various types of dredgers and auxiliary vessels in different construction conditions and geotechnical soil types during the dredging project’s construction period are established, as well as the power consumption quota for management activities. Taking the construction of the main project of the cross-river channel from Shenzhen to Zhongshan (S09)’s foundation trench excavation and channel dredging, the Thilafushi Island reclamation project in Malé, and the second phase of the southern section of the Guangzhou Port Area channel maintenance project (2022–2023) as case studies, the validity of the quotas is verified. During the construction period, under the same dredging soil quality and the same working condition level, the carbon emissions of different types of dredgers are different. Conversely, under different dredging soil qualities and different working condition levels, the carbon emissions for the same dredger or auxiliary vessel are different. The carbon emissions of each dredger or auxiliary vessel increase with the increase in the ship’s specifications. The carbon emissions of dredging projects are huge, with direct carbon emissions accounting for 97%, and indirect carbon emissions from equipment deployment and management activities accounting for 3%, among which the carbon emissions from electricity consumption in management activities account for only 0.3%. Full article

This study aims to assess the carbon footprint for the organization of frozen processed seafood manufacturing plants and propose sustainable strategies for reducing greenhouse gas emissions. Organizational activity data from 2024 were utilized to evaluate the carbon footprint and develop targeted mitigation measures. The findings indicate that Scope 1 emissions amounted to 12,685 tons of CO₂eq, Scope 2 emissions amounted to 15,403 tons of CO₂eq, and Scope 3 emissions amounted to 31,564 tons of CO₂eq. The total greenhouse gas emissions across all three scopes were 59,652 tons of CO₂eq, with additional greenhouse gas emissions recorded at 34,027 tons of CO₂eq. Mitigation measures were considered for activities contributing to at least 10% of emissions in each scope. In Scope 1, the use of R507 refrigerant in the production cooling system accounted for 9907 tons of CO₂eq, representing 78.10% of emissions. In Scope 2, electricity consumption contributed 15,403 tons of CO₂eq, constituting 100% of emissions. In Scope 3, the procurement of surimi (processed fish meat) was responsible for 20,844 tons of CO₂eq, accounting for 66.04% of emissions. Based on these findings, key mitigation strategies were proposed. For Scope 1, reducing emissions involves preventive maintenance of cooling systems to prevent leaks, replacing corroded pipelines, installing shut-off valves, and switching to alternative refrigerants with no greenhouse gas emissions. For Scope 2, energy-saving initiatives include promoting electricity conservation within the organization, maintaining equipment for optimal efficiency, installing energy-saving devices such as variable speed drives (VSD), upgrading to high-efficiency motors, and utilizing renewable energy sources like solar power. For Scope 3, emissions can be minimized by sourcing raw materials from suppliers with certified carbon footprint labels, prioritizing purchases from producers committed to carbon reduction, and selecting suppliers closer to manufacturing sites to reduce transportation-related emissions. Implementing these strategies will contribute to sustainable greenhouse gas emission reductions. Full article

Carbon monoxide (CO) is a toxic pollutant emitted by municipal solid waste incineration (MSWI), which has a strong correlation with dioxins. In terms of the sustainable development of an ecological environment, CO emission concentration is strictly controlled by the environmental departments of various countries in the world. The construction of its prediction model is conducive to pollution reduction control. The MSWI process is affected by multi-factors such as MSW component fluctuation, equipment wear and maintenance, and seasonal change, and has complex nonlinear and time-varying characteristics, which makes it difficult for the CO prediction model based on offline historical data to adapt to the above changes. In addition, the continuous emission monitoring system (CEMS) used for conventional pollutant detection has unavoidable misalignment and failure problems. In this article, a novel prediction model of CO emission from the MSWI process based on semi-supervised concept drift (CD) detection in kernel feature space is proposed. Firstly, the CO emission deep prediction model and the kernel feature space detection model are constructed based on offline batched historical data, and the historical data set for the real-time construction of the pseudo-labeling model is obtained. Secondly, the drift detection for the CO emission prediction model is carried out based on real-time data by using unsupervised kernel principal component analysis (KPCA) in terms of feature space. If CD occurs, the pseudo-label model is constructed, the pseudo-truth value is obtained, and the drift sample is confirmed and selected based on the Page–Hinkley (PH) test. If no CD occurs, the CO emission concentration is predicted based on the historical prediction model. Then, the updated data set of the CO emission prediction model and kernel feature space detection is obtained by combining historical samples and drift samples. Finally, the offline history model is updated with a new data set when the preset conditions are met. Based on the real data set of an MSWI power plant in Beijing, the validity of the proposed method is verified. Full article

Fault diagnosis is one of the most important issues for a modular multilevel converter (MMC). However, conventional solutions are deficient in two aspects. Firstly, they lack the necessary feature information. Secondly, they are incapable of performing open-circuit fault diagnosis of the modular multilevel converter with the requisite degree of accuracy. To solve this problem, an intelligent diagnosis method is proposed to integrate the modal time–frequency diagram and FFT-CNN-BiGRU-Attention. By selecting the phase current and bridge arm voltage as the core fault parameters, the particle swarm algorithm is used to optimize the Variational Modal Decomposition parameters, and the fault signal is decomposed and reconstructed into sensitive feature components. The reconstructed signals are further transformed into modal time–frequency diagrams via continuous wavelet transform to fully retain the time–frequency domain features. In the model construction stage, the frequency–domain features are first extracted using the fast Fourier transform (FFT), and the local patterns are captured through a combination with a convolutional neural network; subsequently, the timing correlations are analyzed using bidirectional gated loop cells, and the Attention Mechanism is introduced to strengthen the key features. Simulations show that the proposed method achieves 98.63% accuracy in locating faulty insulated gate bipolar transistors (IGBTs) in the sub-module, with second-level real-time response capability. Compared with the recently published scheme, it maintains stable performance under complex working conditions such as noise interference and data imbalances, showing stronger robustness and practical value. This study provides a new idea for the intelligent operation and maintenance of power electronic devices, which can be extended to the fault diagnosis of other power equipment in the future. Full article