Advancement in transformer fault diagnosis technology

Frontiers in Energy Research, Год журнала: 2024, Номер 12

Опубликована: Июль 22, 2024

The transformer plays a critical role in maintaining the stability and smooth operation of entire power system, particularly transmission distribution. paper begins by providing an overview traditional fault diagnosis methods for transformers, including dissolved gas analysis vibration techniques, elucidating their developmental trajectory. Building upon these methods, numerous researchers have aimed to enhance optimize them through intelligent technologies such as neural networks, machine learning, support vector machines. These addressed common issues low correlation between characteristic parameters faults, ambiguous descriptions, complexity feature analysis. However, due structures uncertainties operating environments, collection becomes highly intricate. Researchers further refined algorithms values based on diagnostic transformers. goal is improve speed, mitigate impact measurement noise, advance adaptability artificial intelligence technology field On other hand, excellent multi-parameter capability more suitable techniques that involve fusion multiple information sources. Through powerful data acquisition, processing, decision-making capabilities provided algorithms, it can comprehensively analyze non-electrical oil characteristics, signals, temperature, along with electrical like short-circuit reactance load ratio. Moreover, automatically inherent relationship faults quantities provide suggestions. This technique pivotal ensuring safety network security, emerging prominent direction research.

Язык: Английский

---

Retired battery capacity screening based on deep learning with embedded feature smoothing under massive imbalanced data

Energy, Год журнала: 2025, Номер unknown, С. 134761 - 134761

Опубликована: Фев. 1, 2025

Язык: Английский

---

Transformer fault diagnosis method based on MTF and GhostNet

Measurement, Год журнала: 2025, Номер unknown, С. 117056 - 117056

Опубликована: Фев. 1, 2025

Язык: Английский

---

Prediction of retail commodity hot-spots: a machine learning approach

Data Science and Management, Год журнала: 2025, Номер unknown

Опубликована: Фев. 1, 2025

Язык: Английский

---

Integrating evolutionary algorithms and enhanced-YOLOv8 + for comprehensive apple ripeness prediction

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 1, 2025

The assessment of apple quality is pivotal in agricultural production management, and ripeness a key determinant quality. This paper proposes an approach for assessing from both structured unstructured observation data, i.e., text images. For support vector regression (SVR) models optimized using the Whale Optimization Algorithm (WOA), Grey Wolf Optimizer (GWO), Sparrow Search (SSA) were utilized to predict ripeness, with WOA-optimized SVR demonstrating exceptional generalization capabilities. image Enhanced-YOLOv8+, modified YOLOv8 architecture integrating Detect Efficient Head (DEH) Channel Attention (ECA) mechanism, was employed precise localization identification. synergistic application these methods resulted significant improvement prediction accuracy. These approaches provide robust framework deepen understanding relationship between maturity observed indicators, facilitating more informed decision-making postharvest management.

Язык: Английский

---

Incipient fault identification method for 10 kV power cables based on sheath current and DVAE-SAO-CatBoost

Electric Power Systems Research, Год журнала: 2025, Номер 245, С. 111583 - 111583

Опубликована: Март 11, 2025

Язык: Английский

---

Protein interactions, network pharmacology, and machine learning work together to predict genes linked to mitochondrial dysfunction in hypertrophic cardiomyopathy

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Март 24, 2025

Purpose This study looked at possible targets for hypertrophic cardiomyopathy (HCM), a condition marked by thickening of the ventricular wall, primarily in left ventricle.Methods We employed differential gene analysis and weighted co-expression network (WGCNA) on samples. then carried out an enrichment analysis. also investigated process immunological infiltration. six machine learning techniques two protein-protein interaction (PPI) selection approaches to search most characteristic (MCG). In validation ladder, we verified expression MCG. Furthermore, examined MCG levels HCM animal cell models. Finally, performed molecular docking predicted potential medications treatment.Results 7975 differentially expressed genes (DEGs) were found our study. identified 236 blue module using WGCNA. Screening transcriptome protein was used mine The final result screened CCAAT/Enhancer Binding Protein Delta (CEBPD) as confirmed that matched outcomes experimental ladder. level CEBPD mRNA lowered cellular Given Abt-751 had highest binding affinity CEBPD, it might be projected targeted medication.Conclusion new target called which is probably going function mitochondrial dysfunction. An innovative aim management or avoidance offered this may drug greatest with CEBPD.

Язык: Английский

---

Risk warning model for predicting sleep disorders in healthcare workers on long-term shifts

Sleep and Biological Rhythms, Год журнала: 2025, Номер unknown

Опубликована: Апрель 10, 2025

Язык: Английский

---

Transformer fault diagnosis using machine learning: a method combining SHAP feature selection and intelligent optimization of LGBM

Energy Informatics, Год журнала: 2025, Номер 8(1)

Опубликована: Апрель 22, 2025

Язык: Английский

---

Fault diagnosis of power transformers based on t-SNE and ECOC-TEWSO-SVM

AIP Advances, Год журнала: 2024, Номер 14(5)

Опубликована: Май 1, 2024

Support Vector Machines (SVMs) have achieved significant success in the field of power transformer fault diagnosis. However, challenges such as determining SVM hyperparameters and their suitability for binary classification still exist. This paper proposes a novel method diagnosis, called ECOC-WSO-SVM, which utilizes White Shark Optimizer (WSO) error correcting output codes to optimize SVMs. First, t-distributed Stochastic Neighbor Embedding (t-SNE) is employed reduce dimensionality Dissolved Gas Analysis (DGA) features constructed using correlation ratio method, from 26 dimensions. In addition, effectively solve SVMs, multi-strategy fusion proposed improve WSO, incorporating tent chaos initialization, elite opposite learning, selection strategies, forming TEWSO, its superior optimization performance validated IEEE CEC2021 test functions. Furthermore, address limitations SVMs classifier, an code introduced, thus constructing multi-class model. Finally, diagnostic ECOC-TEWSO-SVM model real-world data. Results demonstrate that exhibits best compared traditional models those literature, thereby proving significance effectiveness

Язык: Английский

---