Short-term wind speed prediction based on temporal convolutional networks DOI

Sicheng Fan

2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), Год журнала: 2023, Номер unknown, С. 165 - 169

Опубликована: Дек. 8, 2023

To improve the utilization efficiency of wind energy, this research proposes a hybrid model based on Temporal Convolutional Network (TCN) and two-level speed decomposition. Firstly, original data is decomposed into main residual signals through Singular Spectrum Analysis (SSA). Then, usage Variational mode decomposition (VMD) decomposes several sub-sequences. The next step involves predicting signal all sub-sequences using TCN. Eventually, Grey Wolf Optimizer (GWO) employed to perform optimization stack prediction results, resulting in outcomes. results demonstrate that proposed SSA-VMD-TCN-GWO outperforms reference models. Thus, provides new solution

Язык: Английский

A machine learning method of accelerating multiscale analysis for spatially varying microstructures DOI
Shengya Li, Shujuan Hou

International Journal of Mechanical Sciences, Год журнала: 2023, Номер 266, С. 108952 - 108952

Опубликована: Дек. 24, 2023

Язык: Английский

Процитировано

9

Enhanced Streamflow Forecasting for Crisis Management Based on Hybrid Extreme Gradient Boosting Model DOI
Hamed Khajavi, Amir Rastgoo, Fariborz Masoumi

и другие.

Iranian Journal of Science and Technology Transactions of Civil Engineering, Год журнала: 2025, Номер unknown

Опубликована: Янв. 13, 2025

Язык: Английский

Процитировано

0

Short‐Term Wind Power Prediction Based on MVMD‐AVOA‐CNN‐LSTM‐AM DOI Creative Commons
Xiqing Zang,

Zehua Wang,

S. W. Zhang

и другие.

International Transactions on Electrical Energy Systems, Год журнала: 2025, Номер 2025(1)

Опубликована: Янв. 1, 2025

Due to the intermittent and fluctuating nature of wind power generation, it is difficult achieve desired prediction accuracy for prediction. For this reason, paper proposes a combined model based on Pearson correlation coefficient method, multivariate variational mode decomposition (MVMD), African vultures optimization algorithm (AVOA) leader–follower patterns, convolutional neural network (CNN), long short‐term memory (LSTM), attention mechanism (AM). Firstly, method used filter out meteorological data with strong relationship establish dataset; subsequently, MVMD decompose original into multiple subsequences in order handle better. Thereafter, optimize hyperparameters CNN‐LSTM algorithm, AM added increase effect, decomposed are predicted separately, values each subsequence superimposed obtain final value. Finally, effectiveness verified using from farm Shenyang. The results show that MAE established MVMD‐AVA‐CNN‐LSTM‐AM 2.0467, MSE 2.8329. Compared other models, significantly improved, had better generalization ability robustness, robustness.

Язык: Английский

Процитировано

0

A framework for spatial correlations between industrial pollution sources and groundwater vulnerabilities based on machine learning and spatial cluster analysis: implications for risk control DOI
Rui Zhou, Jian Chen,

H. Bian

и другие.

Journal of Hazardous Materials, Год журнала: 2025, Номер 494, С. 138492 - 138492

Опубликована: Май 7, 2025

Язык: Английский

Процитировано

0

Artificial intelligence-based predictive models for shear wave velocity of soils: A comprehensive review DOI Creative Commons
Meghdad Payan, Parviz Asadi,

Amirhossein Jamaldar

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 155, С. 111095 - 111095

Опубликована: Май 22, 2025

Язык: Английский

Процитировано

0

Digital Channel Equalizer Using Functional Link Artificial Neural Network Trained with Quantum Aquila Optimizer DOI
Arnapurna Panda

SN Computer Science, Год журнала: 2024, Номер 5(4)

Опубликована: Март 15, 2024

Язык: Английский

Процитировано

3

Hybridised Network of Fuzzy Logic and a Genetic Algorithm in Solving 3-Satisfiability Hopfield Neural Networks DOI Creative Commons
Farah Liyana Azizan, Saratha Sathasivam, Majid Khan Majahar Ali

и другие.

Axioms, Год журнала: 2023, Номер 12(3), С. 250 - 250

Опубликована: Март 1, 2023

This work proposed a new hybridised network of 3-Satisfiability structures that widens the search space and improves effectiveness Hopfield by utilising fuzzy logic metaheuristic algorithm. The method effectively overcomes downside current structure, which uses Boolean creating diversity in space. First, we included into system to make bipolar structure change continuous while keeping its structure. Then, Genetic Algorithm is employed optimise solution. Finally, return answer initial form casting it framework hybrid function between two procedures. suggested network’s performance was trained validated using Matlab 2020b. techniques significantly obtain better results terms error analysis, efficiency evaluation, energy similarity index, computational time. outcomes validate significance results, this comes from fact model has positive impact. information concepts will be used develop an efficient gathering for subsequent investigation. development with presents viable strategy mining applications future.

Язык: Английский

Процитировано

7

Adaptive Aquila Optimizer Combining Niche Thought with Dispersed Chaotic Swarm DOI Creative Commons
Yue Zhang, XU Xi-ping, Ning Zhang

и другие.

Sensors, Год журнала: 2023, Номер 23(2), С. 755 - 755

Опубликована: Янв. 9, 2023

The Aquila Optimizer (AO) is a new bio-inspired meta-heuristic algorithm inspired by Aquila’s hunting behavior. Adaptive Combining Niche Thought with Dispersed Chaotic Swarm (NCAAO) proposed to address the problem that although has strong global exploration capability, it an insufficient local exploitation capability and slow convergence rate. First, improve diversity of populations in uniformity distribution search space, DLCS chaotic mapping used generate initial so better state. Then, accuracy algorithm, adaptive adjustment strategy de-searching preferences proposed. development phases NCAAO are effectively balanced changing threshold introducing position weight parameter adaptively adjust process. Finally, idea small habitats promote exchange information between groups accelerate rapid optimal solution. To verify optimization performance improved was tested on 15 standard benchmark functions, Wilcoxon rank sum test, engineering problems test optimization-seeking ability algorithm. experimental results show faster speed compared other intelligent algorithms.

Язык: Английский

Процитировано

6

A novel deep learning architecture for distribution system topology identification with missing PMU measurements DOI
Y. Raghuvamsi, Kiran Teeparthi,

Vishalteja Kosana

и другие.

Results in Engineering, Год журнала: 2022, Номер 15, С. 100543 - 100543

Опубликована: Июль 20, 2022

Язык: Английский

Процитировано

9

Some Modified Activation Functions of Hyperbolic Tangent (TanH) Activation Function for Artificial Neural Networks DOI

Arvind Kumar,

Sartaj Singh Sodhi

Advances in intelligent systems and computing, Год журнала: 2023, Номер unknown, С. 369 - 392

Опубликована: Янв. 1, 2023

Язык: Английский

Процитировано

3