A novel diagnosis methodology of gear oil for wind turbine combining stepwise multivariate regression and clustered federated learning framework DOI

Huihui Han,

Y. X. Zhao, Hao Jiang

et al.

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 23, 2025

Abstract Data-driven approaches demonstrate significant potential in accurately diagnosing faults wind turbines. To enhance diagnostic performance, we introduce a clustered federated learning framework (CFLF) to gear oil diagnosis. Initially, stepwise multivariate regression (SMR) model is introduced and optimized after data process, which integrates multiscale feature AIC diagnosis feature. Subsequently, tackle heterogeneity among different indicators, canonical correlation series of representations are extracted from the SMR models, combining CFLF method proposed assess performance oil. Actual analysis turbine showcase superior over single with higher prediction accuracy 35.73%. This study provides new technique for evaluating energy sector.

Language: Английский

Review of several key processes in wind power forecasting: Mathematical formulations, scientific problems, and logical relations DOI
Mao Yang, Y. Huang,

Chuanyu Xu

et al.

Applied Energy, Journal Year: 2024, Volume and Issue: 377, P. 124631 - 124631

Published: Oct. 10, 2024

Language: Английский

Citations

7
Plantas de fresa regeneradas in vitro mediante organogénesis directa en diferentes concentraciones de auxinas y citocininas DOI Open Access
Jesús Hernández-Ruíz, A. Eugenia Rangel-Castillo, María Isabel Laguna Estrada

et al.

Bioagro, Journal Year: 2025, Volume and Issue: 37(1), P. 123 - 134

Published: Jan. 1, 2025

La fresa (Fragaria x ananassa) es una especie vegetal de gran importancia económica y agroalimentaria, que se cultiva en regiones agroindustriales México, como el Bajío. El principal insumo la producción agrícola son las plantas, cuya primera etapa multiplicación empieza con formación clones por cultivo in vitro a partir plantas madre seleccionadas. Sin embargo, diversas características regeneradas pueden presentar variaciones reducen su valor agronómico comercial. Dicha variabilidad debida múltiples factores, aunque destaca efecto tienen combinaciones auxinas citocininas, así sus concentraciones. objetivo del presente estudio fue evaluar mediante organogénesis directa ante diferentes concentraciones citocininas. Los explantes obtuvieron meristemos apicales los estolones variedad Camino Real. Se utilizaron 21 tratamientos (AIB 2,4-D) citocininas (BAP cinetina) para organogénesis. mayor número vitroplantas obtuvo combinación AIB BAP 0,4 mg·L-1, tasa regeneración promedio 68,3 %. En dicho tratamiento presentaron mejor desarrollo alta respuesta antioxidante. concentración prolina 1,7 µg mL-1, control sin ni

Citations

0
New Energy Power Generation Prediction Based on CNN-LSTM-Attention Model and Risk Detection Analysis of Isolation Forest Algorithm DOI

殿刚 胡

Journal of Image and Signal Processing, Journal Year: 2025, Volume and Issue: 14(01), P. 45 - 61

Published: Jan. 1, 2025

Language: Английский

Citations

0
Modeling and Evaluation of Forecasting Models for Energy Production in Wind and Photovoltaic Systems DOI Creative Commons

Imene Benrabia,

Dirk Soeffker

Energies, Journal Year: 2025, Volume and Issue: 18(3), P. 625 - 625

Published: Jan. 29, 2025

The comprehensive change from known, classical energy production methods to the increased use of renewable requires new in field efficient application and energy. urban supply presents complex challenges improving efficiency; therefore, prediction dynamical availability is required. Several approaches have been explored, including statistical models machine learning using historical data numerical weather mathematical atmosphere conditions. Accurately forecasting involves analyzing factors such as related conditions, conversion systems, their locations, which influence both yield. This study focuses on short-term wind photovoltaic (PV) approaches, aiming for accurate 8 h predictions. goal develop capable producing forecasts resources (solar wind), suitable later a model predictive control scheme where generation demand, well storage, must be considered together. Methods include regression trees, support vector regression, neural networks. main idea this work past future information model. Inputs PV are solar irradiance, while uses speed data. performance evaluated over entire year. Two scenarios tested: one with perfect predictions another realistic situation not possible, uncertain accounted by incorporating noise models. results second scenario were further improved output filtering method. shows advantages disadvantages different methods, accuracy that can expected principle. show network has best predicting compared other an RMSE 0.1809 5.3154 wind, Pearson coefficient 0.9455 0.9632 wind.

Language: Английский

Citations

0
Forecasting rooftop photovoltaic solar power using machine learning techniques DOI
Upma Singh,

Shekhar Singh,

Saket Gupta

et al.

Energy Reports, Journal Year: 2025, Volume and Issue: 13, P. 3616 - 3630

Published: March 22, 2025

Language: Английский

Citations

0
Self-Adaptive Nonlinear Discrete Grey Model Based on Priority-Varying Weighted Accumulation for Forecasting Wind Power Generation Under New Information Uncertainty DOI
Nailu Li,

haonan ba,

Wenyu jiang

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
A novel diagnosis methodology of gear oil for wind turbine combining stepwise multivariate regression and clustered federated learning framework DOI

Huihui Han,

Y. X. Zhao, Hao Jiang

et al.

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 23, 2025

Abstract Data-driven approaches demonstrate significant potential in accurately diagnosing faults wind turbines. To enhance diagnostic performance, we introduce a clustered federated learning framework (CFLF) to gear oil diagnosis. Initially, stepwise multivariate regression (SMR) model is introduced and optimized after data process, which integrates multiscale feature AIC diagnosis feature. Subsequently, tackle heterogeneity among different indicators, canonical correlation series of representations are extracted from the SMR models, combining CFLF method proposed assess performance oil. Actual analysis turbine showcase superior over single with higher prediction accuracy 35.73%. This study provides new technique for evaluating energy sector.

Language: Английский

Citations

0