Search Results (197)

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

Recent advances in technologies such as blockchain, the Internet of Things (IoT), Cyber–Physical Systems (CPSs), and the Industrial Internet of Things (IIoT) have driven the digitalization and intelligent transformation of modern industries. However, embedded control devices within power system communication infrastructures have become increasingly susceptible to cyber threats due to escalating software complexity and extensive network exposure. We have seen that symmetric conventional patching techniques—both static and dynamic—often fail to satisfy the stringent requirements of real-time responsiveness and computational efficiency in resource-constrained environments of all kinds of power grids. To address this limitation, we have proposed a hardware-assisted runtime patching framework tailored for embedded systems in critical power system networks. Our method has integrated binary-level vulnerability modeling, execution-trace-driven fault localization, and lightweight patch synthesis, enabling dynamic, in-place code redirection without disrupting ongoing operations. By constructing a system-level instruction flow model, the framework has leveraged on-chip debug registers to deploy patches at runtime, ensuring minimal operational impact. Experimental evaluations within a simulated substation communication architecture have revealed that the proposed approach has reduced patch latency by 92% over static techniques, which are symmetrical in a working way, while incurring less than 3% CPU overhead. This work has offered a scalable and real-time model-driven defense strategy that has enhanced the cyber–physical resilience of embedded systems in modern power systems, contributing new insights into the intersection of runtime security and grid infrastructure reliability. Full article

This paper presents a novel method for assessing the technical condition of devices in the high-voltage (HV) switching bay of a substation, focusing on circuit breakers, disconnectors, and instrument transformers. These devices are typically maintained using a condition-based maintenance approach. The proposed method integrates data from individual maintenance tasks into a comprehensive assessment of each device’s technical condition. Traditionally, the technical condition and health index assessments rely solely on additive criteria. This study introduces an advanced assessment method that incorporates both additive and multiplicative criteria to enhance the prioritization of maintenance tasks. A data model is developed to extract the maintenance task data from device maintenance databases, enabling an automated assessment process. The proposed approach facilitates the generation of a c-curve throughout a device’s operational life. A comparison using real transmission system operator maintenance data demonstrates that the proposed method, which assesses device conditions using both additive and multiplicative criteria, outperforms the conventional approach that relies solely on additive criteria. Full article

This paper explores the optimal configuration strategies for building-integrated photovoltaic (BIPV) systems in response to the low-carbon transformation needs of semi-outdoor substations, aiming to reconcile the contradiction between photovoltaic (PV) power generation efficiency and indoor environmental control in industrial buildings. Taking a 220 kV semi-outdoor substation of the China Southern Power Grid as a case study, a building energy consumption–PV power generation coupling model was established using EnergyPlus software. The impacts of three PV wall constructions and different building orientations on a transformer room and an air-conditioned living space were analyzed. The results show the EPS-filled PV structure offers superior passive thermal performance and cooling energy savings, making it more suitable for substation applications with high thermal loads. Building orientation plays a decisive role in the net energy performance, with an east–west alignment significantly enhancing the PV module’s output and energy efficiency due to better solar exposure. Based on current component costs, electricity prices, and subsidies, the BIPV system demonstrates a moderate annual return, though the relatively long payback period presents a challenge for widespread adoption. East–west orientations offer better returns due to their higher solar exposure. It is recommended to adopt east–west layouts in EPS-filled PV construction to optimize both energy performance and economic performance, while further shortening the payback period through technical and policy support. This study provides an optimized design path for industrial BIPV module integration and aids power infrastructure’s low-carbon shift. Full article

The growing scale of offshore wind farms and increasing transmission distances has driven the demand for optimized offshore substation (OSS) configurations. This study proposes a comprehensive techno-economic framework to minimize the total lifecycle cost (LCC) of an OSS by determining the optimal number of OSSs and transformers considering wind farm capacity and transmission distance. The methodology incorporates three cost models: capital expenditure (CAPEX), operational expenditure (OPEX), and expected energy not supplied (EENS). CAPEX considers transformer costs, topside structural mass effects, and nonlinear installation costs. OPEX accounts for substation maintenance and vessel operating expenses, and EENS is calculated using transformer failure probability models and redundancy configurations. The optimization is performed through scenario-based simulations and a net present value (NPV)-based comparative analysis to determine the cost-effective configurations. The quantitative analysis demonstrates that for small- to medium-scale wind farms (500–1000 MW), configurations using 1–2 substations and 3–4 transformers achieve minimal LCC regardless of the transmission distance. In contrast, large-scale wind farms (≥1500 MW) require additional substations to mitigate transmission losses and disruption risks, particularly over long distances. These results demonstrate that OSS design should holistically balance initial investment costs, operational reliability, and supply security, providing practical insights for cost-effective planning of next-generation offshore wind projects. Full article

For modern power plants to be dependable, safe, sustainable, and provide the highest operational efficiency (i.e., enhance dynamic load distribution with a faster response time at reduced reactive losses), there must be an intelligent dynamic load management system based on modern computational techniques to prevent overloading of power devices (i.e., alternators, transformers, etc.) in grid systems. In this paper, a co-simulation framework (Panda-SDN Load Balancer) is designed to achieve maximum operational efficiency from the power grid with the prime objective of real-time intelligent load balancing of operational power devices (i.e., power transformers, etc.). This framework is based on the integration of two tools: (a) PandaPower (an open-source Python tool) used for real-time power data (voltage; current; real power, P_Real; apparent power, P_Apparent; reactive power, P_Reactive; power factor, PF; etc.) load flow analysis; (b) Mininet used for the designing of a Software-Defined Network (SDN) with a POX controller for managing the load patterns on power transformers after load flow analysis obtained through PandaPower via the synchronization tool Message Queuing Telemetry Transport (MQTT) and Intelligent Electrical Devices (IEDs). In this research article, the simulation is performed in three scenarios: (a) normal flow, (b) loaded flow without the proposed framework, and (c) loaded flow with the proposed framework. As per simulation results, the proposed framework offered intelligent substation automation with (a) balanced utilization of a transformer, (b) enhanced system power factor in extreme load conditions, and (c) significant gain in system operational efficiency as compared to legacy load management methods. Full article

In the context of global decarbonization goals and increasing urban electricity demand, the green transformation of power industry buildings to enhance the utilization of renewable energy represents a significant contribution to sustainable social development. Rooftop photovoltaic (PV) systems can reduce unnecessary radiative heat gain and generate clean electricity to support this transition; however, they also alter the rooftop wind environment. Deploying rooftop PV systems requires well-planned design strategies to optimize renewable energy production while ensuring adequate natural ventilation, particularly for semi-outdoor main transformer rooms where ventilation and heat dissipation are crucial for safe substation operations. This concept was tested at a 220 kV substation in Guangzhou, China, using Computational Fluid Dynamics (CFD) and PVSYST to assess the impact of different rooftop PV systems on natural ventilation and power generation. The analysis showed that while the horizontal PV system achieved the highest energy output, it also resulted in a wind speed reduction of 13.2% or 11.8%. In contrast, the 10° symmetrical PV system offers the most balanced solution, with only a 0.6% decrease in ventilation performance but at the cost of a 13.87% reduction in PV output. The unilateral pitched PV system results in ventilation losses of less than 4%, and the power generation loss is also kept below 4%. However, this configuration may lead to increased wind loads. This approach can be developed into a practical design tool to further support the integration of PV systems in substation green retrofitting projects. Full article

The identification of critical fault information plays a crucial role in ensuring the reliability and stability of power systems. However, existing fault-identification technologies heavily rely on high-dimensional sensor data, which often contain redundant and noisy information. Moreover, conventional data preprocessing approaches typically employ fixed time windows, neglecting variations in fault characteristics under different system states. This limitation may lead to incomplete feature selection and ineffective dimensionality reduction, ultimately affecting the accuracy of fault classification. To address these challenges, this study proposes a method of critical fault information identification that integrates a scalable time window with Principal Component Analysis (PCA). The proposed method dynamically adjusts the time window size based on real-time system conditions, ensuring more flexible data capture under diverse fault scenarios. Simultaneously, PCA is employed to reduce dimensionality, extract representative features, and remove redundant noise, thereby enhancing the quality of the extracted fault information. Furthermore, this approach lays a solid foundation for the subsequent application of deep learning-based fault-diagnosis techniques. By improving feature extraction and reducing computational complexity, the proposed method effectively alleviates the workload of operation and maintenance personnel while enhancing fault classification accuracy. Our experimental results demonstrate that the proposed method significantly improves the precision and robustness of fault identification in power systems. Full article

Rotational spectra for hexafluoroacetone imine, the singly substituted ¹³C isotopologues, and the ¹⁵N isotopologue, have been recorded using both cavity and chirped pulse Fourier transform microwave spectrometers. The spectra observed present as being doubled with separations between each pair of transitions being on the order of a few tens of kilohertz which is consistent with a large amplitude motion producing two torsional substates. The observed splitting is most likely due to the combined motions of the CF3 groups, for which the calculated barrier is small. However, no transitions between states could be observed and, similarly, no Coriolis coupling parameters were required to achieve a satisfactory fit for the transition frequencies. Hence, and somewhat curiously, the two states have been fit independently of each other such that the two states may simply be considered near-equivalent conformers. The structural properties of hexafluoroacetone imine are compared with two isoelectronic molecules hexafluoroisobutene and hexafluoroacetone. Rotational constants, quartic centrifugal distortion constants, and the ¹⁴N nuclear electric quadrupole coupling tensor have been determined and are presented together with supporting quantum chemical calculations. Full article

During substation inspection, operators are often exposed to hazardous working environments. It is necessary to use visual sensors to determine work status and perform action detection to distinguish between normal and dangerous actions in order to ensure the safety of operators. However, due to information security, privacy protection, and the rarity of dangerous scenarios, there is a scarcity of related visual action datasets. To address this issue, this study first introduces a virtual work platform, which includes a controller for the parameterized control of scenarios and human resources. It can simulate realistic substation inspection operations and generate synthetic action datasets using domain randomization and behavior tree logic. Subsequently, a spatiotemporal action detection algorithm is utilized for action detection, employing YOLOv8 as the human detector, Vision Transformer as the backbone network, and SlowFast as the action detection architecture. Model training is conducted using three datasets: a real dataset, a synthetic dataset generated via a VWP, and a mixed dataset comprising both real and synthetic data. Finally, using the model trained on the real dataset as a baseline, the evaluation results on the test set shows that the use of synthetic datasets in training improves the model’s average precision by up to 10.7%, with a maximum average precision of 73.61%. This demonstrates the feasibility, effectiveness, and robustness of synthetic data. Full article

Building-energy consumption constitutes a pivotal component of global energy systems, with the heating and cooling loads during the operational phase being particularly significant. Substation building, as nodes in the transmission and transformation network, deserve attention for their building-operating loads. This study investigates heating and cooling loads during substation operation in severe cold climates. By integrating energy consumption simulations with one-factor-at-a-time and orthogonal multivariate analyses, optimization strategies under key influencing factors are systematically explored. The impact analysis identifies the following order of influence magnitude on substation total loads: indoor equipment heat generation, ventilation rate, roof U-value, exterior wall U-value, and window U-value. The heating- and cooling-load characteristics exhibit distinct patterns depending on indoor equipment heat generation. The total building load can be reduced by 61.23 per cent under multifactor optimal de-sign conditions, highlighting the critical role of systemic design coordination. This study provides a case study reference for energy efficient design of heating and cooling loads in substations, especially where significant changes in equipment heat occur, and highlights the importance of controlling indoor heat sources to achieve optimal energy efficiency. Full article

The relevance is introducing fourth generation district heating (4GDH), which decreases operation and maintenance costs by utilizing the efficiency of low temperature district heating (LTDH). The aim is to develop a methodology allowing for a more flexible heat demand model and accurate function describing the relationship between outdoor temperature and heat demand. It is represented by a black-box model based on historical data collected from heating, ventilation, and air conditioning (HVAC) systems. Energy delivery/consumption is analyzed with the help of a set of statistical and regression formulas. The analysis of operational data is then transformed to methodology to regulate heat supply with combined heat-and-power (CHP) generation. The key features are that the model takes into account thermal capacity and type of substation; the district heating (DH) plant is not assumed to have a fixed return temperature and generation profile. The novelty is an emphasis on DH operation and introduction of statistics into a dynamic simulation model. With no abnormal buildings, higher accuracy of modeling is achieved. Most of the consumers are pretty similar in thermal response, even though specific energy demand and heated volume may differ. Heat demand of an old building is better simulated with discrete regression, while those with pump-equipped substations are modeled with linear regression. Full article

Existing substation equipment image data augmentation models face challenges such as high dataset size requirements, difficult training processes, and insufficient condition control. This paper proposes a transformer equipment image data augmentation method based on a Stable Diffusion model. The proposed method incorporates the Low-Rank Adaptation (LoRA) concept to fine-tune the pre-trained Stable Diffusion model weights, significantly reducing training requirements while effectively integrating the essential features of transformer equipment image data. To minimize interference from complex backgrounds, the Segment Anything Model (SAM) is employed for preprocessing, thereby enhancing the quality of generated image data. The experimental results demonstrate significant improvements in evaluation metrics using the proposed method. Specifically, when implemented with the YOLOv7 model, the accuracy metric shows a 16.4 percentage point improvement compared to “Standard image transformations” (e.g., rotation and scaling) and a 2.3 percentage point improvement over DA-Fusion. Comparable improvements are observed in the SSD and Faster-RCNN object detection models. Notably, the model demonstrates advantages in reducing false-negative rates (higher Recall). The proposed approach successfully addresses key data augmentation challenges in transformer fault detection applications. Full article

In electrical power systems, from generation power stations down to distribution substations, power transformers play a key role in ensuring reliable electricity transfer in the correct range from the generating source to the end-users. Over time, due to their operational demands and other various factors, transformers become susceptible to failures which threaten their reliability and life span. To address this issue, various transformer fault diagnosis methods are employed to detect and monitor the state of transformers, such as the dissolved gas analysis (DGA) method. In this paper, a systematic literature review (SLR) is conducted using the Preferred Reporting Items for Systematic Reviews (PRISMA) framework to record and screen current research work pertaining to the application of machine learning algorithms for DGA-based transformer fault classification. This study intends to assess and identify potential literature and methodology gaps that must be explored in this research field. In the assessment of the literature, a total of 124 screened papers published between 2014 and 2024 were surveyed using the developed PRISMA framework. The survey results show that the majority of the research conducted for transformer fault classification using DGA employs the support vector machine (32%), artificial neural network (17%), and k-Nearest Neighbor (12%) algorithms. The survey also reveals the countries at the forefront of transformer fault diagnosis and a classification based on DGA using machine learning algorithms. Furthermore, the survey shows that the majority of research conducted revolves around fault diagnosis with an emphasis on improving the accuracy of techniques such as SVM and ANN. At the same time, limited effort is put into other key metrics such as precision, Mean Squared Error, and R-Squared, and also, current works surveyed do not explore regularization techniques for preventing overfitting and underfitting of the proposed models. Full article