An algorithm for wind turbine icing de-rated capacity prediction

In this study diversities of temporal electricity production of all the wind farms were examined. On the first 10 days of January, on January 4 between 00:00 and 06:00 a.m., maximum power ramps have taken place, and output power has increased by about 400 MW. This increase corresponds to 30 % of the total installed wind power capacity. When all installed wind farms’ output power frequency distribution is examined in the first 10 days of January, total hourly output of 33 wind farms varied less than 1 % (rate of output power variation to the total installed wind farm capacity) with 20 % probability, and maximum hourly output power variation has been 6 % of the total installed capacity. When the same analysis was performed for the Gokcedag wind farm which has 135 MW installed power and also one of the biggest wind farms in Turkey, hourly output power variation has reached 20 % of total installed capacity. As can be seen from this study, installing all the wind farms in the same places causes serious problems such as the wind farms being out of service due to the fall and rise of the wind speeds. Therefore, while determining the locations of the wind farms, it is important to consider that wind farms back up the features of each other’s variable energy production for reaching stable grid operation conditions.

Effects of Large Scale Wind Power on Total System Variability and Operation: Case Study of Northern Ireland

Wind energy status in renewable electrical energy production in Turkey

Migrating to reverse Auction mechanisms in wind energy sector: Status and challenges

This study aims to address the challenge of balancing historical preservation and sustainable material selection in ancient building renovations, particularly in regions with unique climatic conditions like Hunan Province. The research proposes a hybrid model integrating Genetic Algorithm-optimized Extreme Gradient Boosting (GA-XGBoost) and Long Short-Term Memory (LSTM) networks. The GA-XGBoost component optimizes hyperparameters to predict material performance, while the LSTM network captures temporal dependencies in environmental and material degradation data. A multi-objective optimization framework is developed to simultaneously prioritize preservation integrity and green performance. The methodology is validated through a case study on an ancient architectural complex in Rucheng, Hunan Province. Key results demonstrate that the hybrid model achieves superior accuracy in material selection, with an 18–23% reduction in embodied energy (compared to conventional AHP-TOPSIS methods) and a 21.9% improvement in prediction accuracy (versus standalone XGBoost with default hyperparameters). A multi-objective optimization framework is developed to simultaneously prioritize preservation integrity and green performance, with Pareto-optimal solutions identifying material combinations that balance historical authenticity (achieving 92% substrate compatibility) with substantial sustainability gains (18–23% embodied energy reduction). The model also identifies optimal material combinations, such as lime-pozzolan mortars with rice husk ash additives, which enhance moisture buffering capacity by 28% (relative to traditional lime mortar benchmarks) while maintaining 92% compatibility with original substrates (based on ASTM C270 compatibility tests). The findings highlight the model’s effectiveness in bridging heritage conservation and modern sustainability requirements. The study contributes a scalable and interpretable framework for green material selection, offering practical implications for cultural heritage projects worldwide. Future research directions include expanding the model’s applicability to other climate zones and integrating circular economy principles for broader sustainability impact. Preliminary analysis indicates the framework’s adaptability to other climate zones through adjustment of key material property weightings.

A method to measure the superficial velocity of the water phase in gas–water flow using an electromagnetic flowmeter (EMF) and rotating electric field conductance sensors (REFCSs) is introduced in this paper. An electromagnetic flowmeter instrument factor model is built and the correlation between electromagnetic flowmeter output and gas holdup in different flow patterns are explored through vertical upward gas–water flow dynamic experiments in a pipe with an inner diameter (ID) of 20 mm. Water superficial velocity is predicted based on pattern identification among bubble, churn, and slug flows. The experimental results show that water superficial velocity can be predicted fairly accurately for bubble, churn, and slug flows with a water cut higher than 60% (absolute average percentage deviation and absolute average deviation are 4.1057% and 0.0281 m/s, respectively). The output of the electromagnetic flowmeter is unstable and invalid in slug flows with a water cut below 60% due to the non-conducting gas slug is almost filling the pipe. Therefore, the electromagnetic flowmeter is not preferred to be used in such conditions.

ObjectiveThe aim of this study was to compare flow rates over time and the deviations from the target flow rate of a magnetic resonance imaging contrast agent achieved by an automated injector versus manual injection.Materials and MethodsIn this laboratory study, the magnetic resonance contrast agent gadobutrol was repeatedly injected by an injector and by 10 experienced technologists. Six scenarios with 2 different target flow rates (1 and 5 mL/s), 2 different contrast volumes (10 and 20 mL), and 2 different intravenous (IV) catheters (22 gauge and 20 gauge) were tested. The flow rates over time were recorded. The target variable was the average absolute deviation and average absolute percentage deviation from the target flow rate.ResultsThe flow rates over time achieved by an injector were almost identical. Slight deviations from the target flow rate occurred during ramp-up and ramp-down only. Those of manual injection showed high variability over the whole course of the injection. In the 1 mL/s scenarios, the injector deviated from the target flow rate by 0.06 mL/s or less (≤6%) and in the 5 mL/s scenarios by 1.02 mL/s or less (<20%). For the manual injections at the same flow rates, these figures were 0.35 mL/s or less (≤35%) and 3.1 mL/s or less (≤62%).ConclusionsInjector administration of a magnetic resonance contrast agent minimally deviated from the target flow rate, whereas manual injection varied widely. Injector administration is more accurate and repeatable.

A Survey on Problems in Smart Grid with Large Capacity Wind Farm Interconnected

An attempt is made to simulate the Centennial wind farm consisting of 83 wind turbines. The farm is located in the Coulee municipality region near Swift Current, Southern Saskatchewan (Canada). The Wind Atlas Analysis and Application Program and other mapping programs were used for generating the annual energy production (AEP). Based on the generated wind atlas and using both the meteorological data for a period of 10 years (2000–2009), and a vector map with height contour and surface roughness lines, the total AEP for the wind farm was calculated. In addition, AEPs of the wind farm were individually calculated for 2007, 2008 and 2009. The results of the simulated model were compared to the actual values for 3 years. The average absolute deviation between the predicted and actual mean AEP values was found to be less than 7%.

Regarding the time‐series scenario generation of regional wind power, conventional methods face challenges in accurately characterizing the variation patterns of the wind power under installed capacity expansion. To address this issue, this paper presents a historical meteorological data‐driven regional wind power scenario generation approach, which can generate time‐series regional wind power scenarios under historical weather conditions and expected wind power capacity expansion. First, wind power aggregation points (WPAPs) in the study region are selected based on the consistency of the wind turbine models and wind speeds among wind farms. Then, the wind speed spatial distribution in the study region is classified into several patterns, and a dual‐layer convolutional neural network (DCNN) is designed to model the dependence of the regional wind power on wind speeds and installed capacities at WPAPs for each pattern. Finally, the expected installed capacities of wind power are aggregated to WPAPs to enable the trained DCNN models to generate regional wind power scenarios driven by the historical weather data. By means of the meteorological reanalysis data, the proposed approach can provide time‐series regional wind power scenarios with heterogeneity and a high degree of credibility for long‐term planning. Case studies in Shandong Province, China, are carried out to verify the effectiveness of the proposed approach.

Ensuring aircraft reliability and reducing downtime is essential in flight operations. This study applies and investigates the performances of several machine learning techniques namely regression learner, gradient boosting and artificial neural networks (ANNs) to predict unscheduled maintenance orders for a leading airline company in Saudi Arabia. In this study, we aim to develop a robust and accurate artificial intelligence (AI)-based model that predicts unscheduled aircraft maintenance orders that can help operational managers to construct a reliable maintenance plan. The models are trained using historical maintenance data and flight parameters to identify patterns leading to unscheduled maintenance orders. The findings revealed that ANNs yielded a substantial improvement in prediction accuracy compared to regression learner and gradient boosting, which could improve the operational effectiveness, increase safety, increase customer satisfaction, and reduce operational costs. All employed models are evaluated on four aircraft: A320, A333, A777, and A787. The models' errors are compared with their mean absolute deviation (MAD), mean square error (MSE), and mean absolute percentage error (MAPE). The results show that the ANN has the lowest MSE in all aircraft types, showing that the ANN is a more accurate technique in predicting unscheduled aircraft maintenance orders.

Measurements and correlations of isothermal (vapour + liquid) equilibrium for the {isobutane (R600a) + cis-1,3,3,3-tetrafluoropropene (R1234ze(Z))} system at temperatures from (303.150 to 353.150) K

The Vogel–Fulcher–Tamman (VFT) correlation is the known most accurate equation used to estimate and predict temperature-dependent viscosity of fluids. But its accuracy analysis for saturated liquids is still unknown. In this paper, we checked its ability for 49 saturated liquids by using the data in the National Institute of Standards and Technology (NIST) Webbook. Through detailed accuracy analysis, we found that the VFT correlation works qualitatively but does not work well quantitavely. We shown the temperature ranges in which the VFT correlation holds for absolute average deviations (AADs) of [Formula: see text][Formula: see text]1%, [Formula: see text][Formula: see text]2% and [Formula: see text][Formula: see text]5%. The corresponding coefficients are also obtained for engineers to use it directly. We also proposed a new four-parameter correlation to improve the predictive ability. We show that the new correlation holds for 5 fluids with AAD [Formula: see text] 1%, 37 fluids with AAD [Formula: see text] 2%, 43 fluids with AAD [Formula: see text] 3% and 48 fluids with AAD [Formula: see text] 4%.

Permeability is a critical parameter in subsurface fluid flow analysis, reservoir management, hydrocarbon recovery, and carbon dioxide sequestration. Traditional permeability measurement methods involve costly and time-consuming laboratory tests or well-related data. Machine learning (ML), specifically convolutional neural networks (CNN), is proposed as a cost-effective and rapid permeability prediction solution, harnessing interrelationships of input-output variables. In this study, empirical permeability correlation was developed using CNN. Forty nuclear magnetic resonance (NMR) T2 spectrums and 89 logarithmic mean NMR T2 distributions (T2lm) were preprocessed, screened and key spectra were identified using the principal component analysis (PCA). To develop the correlations, a custom-designed CNN architecture was employed to leverage the spatial patterns and intricate relationships embedded in the NMR data. The model was trained and validated rigorously using k-fold cross validation scheme to ensure robustness and generalization. Performance metrics like R-squared (R2), root mean squared error (RMSE), mean absolute error (MAE), standard deviation (SD), absolute deviation (AD), average absolute deviation (AAD), average absolute percentage relative error (AAPRE), and maximum error (Emax) were deployed to evaluate the model’s accuracy and ability to predict permeability values accurately. Among the folds considered, the fold 1 emerged as the best-performing model with the highest R2 value of 0.9544. This CNN-based correlation outperformed conventional and other AI-based models in terms of R2, Emax, AD, AAD, AAPRE, among other metrics. Overall, the study demonstrates the effectiveness of CNN in predicting permeability, offering a superior alternative to costly and limited traditional methods, with fold 1 showing the most promising results.

China's wind power capacity is increasing so rapidly that some areas are not able to consume all the produced wind power. Therefore, it has already become the inevitable trend in wind power integration to achieve the controlled operation of wind turbine. This paper first offers a method to predict the maximum generation capacity of every type of wind turbine, including both under-controlled wind turbine and uncontrolled wind turbine. And then a strategy for active power control of wind farm based on the predicting results is proposed. Considering thoroughly the active power fluctuation of wind turbine and the error of the prediction, the strategy adopts both long and short controlling periods to carry out coordinated optimization control. The simulation results show that the strategy can keep the active power output of wind farm in step with the control order, and consequently the generating efficiency is improved. In addition, the strategy is also applicable to the wind farm with some uncontrollable wind turbines, and the controlling precision can be satisfied.