检索结果-内蒙古大学图书馆

Deep learning with regularized robust long- and short-term memory network for probabilistic short-term load forecasting

引用

JOURNAL OF FORECASTING 2022年第6期41卷 1201-1216页

作者： Jiang, He Zheng, Weihua Xi An Jiao Tong Univ Sch Econ & Finance Xian Peoples R China Yunnan Univ Sch Informat Sci & Engn Kunming 650500 Yunnan Peoples R China

Short-term electricity load forecasting plays an essential role in power system operation and energy trading. However, the strong volatility, seasonality, and uncertainly of the load series pose challenges to accurate short-term load forecasting using existing forecasting models. To tackle these challenges, in this paper, we investigate a novel deep learning-based probabilistic short-term load forecasting model to predict the hourly ahead electricity load accurately. The proposed deep learning forecasting model embeds nonconvex minimax concave penalty in the robust long- and short-term memory (LSTM) network to simplify its complex structure while extracting the important information. The model parameters in the proposed regularized and robust LSTM network are fine-tuned using whale optimization algorithm which is a meta-heuristic approach. For empirical applications, electricity load data collected from New York Independent System Operator and ISO New England are considered, and numerical results show that the proposed method outperforms other state-of-the-art competitors in terms of both point and interval forecasting accuracy.

关键词： minimax concave penalty quantile LSTM short-term load forecasting whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

An improved regularized particle filter for remaining useful life prediction in nuclear plant electric gate valves

引用

NUCLEAR ENGINEERING AND TECHNOLOGY 2022年第6期54卷 2107-2119页

作者： Xu, Ren-yi Wang, Hang Peng, Min -jun Liu, Yong-kuo Harbin Engn Univ Fundamental Sci Nucl Safety & Simulat Technol Lab 145 Nantong St Harbin 150001 Peoples R China

Accurate remaining useful life (RUL) prediction for critical components of nuclear power equipment is an important way to realize aging management of nuclear power equipment. The electric gate valve is one of the most safety-critical and widely distributed mechanical equipment in nuclear power installations. However, the electric gate valve's extended service in nuclear installations causes aging and degradation induced by crack propagation and leakages. Hence, it is necessary to develop a robust RUL prediction method to evaluate its operating state. Although the particle filter(PF) algorithm and its variants can deal with this nonlinear problem effectively, they suffer from severe particle degeneracy and depletion, which leads to its sub-optimal performance. In this study, we combined the whale algorithm with regularized particle filtering(RPF) to rationalize the particle distribution before resampling, so as to solve the problem of particle degradation, and for valve RUL prediction. The valve's crack propagation is studied using the RPF approach, which takes the Paris Law as a condition function. The crack growth is observed and updated using the root-mean-square (RMS) signal collected from the acoustic emission sensor. At the same time, the proposed method is compared with other optimization algorithms, such as particle swarm optimization algorithm, and verified by the realistic valve aging experimental data. The conclusion shows that the proposed method can effectively predict and analyze the typical valve degradation patterns. ?? 2021 Korean Nuclear Society, Published by Elsevier Korea LLC. This is an open access article under the

关键词： Regularized particle filter Remaining useful life prediction whale optimization algorithm Nuclear plant electric gate valves

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction Method of Underwater Acoustic Signals Using VMD and Reverse Weighted Permutation Entropy 6

Feature Extraction Method of Underwater Acoustic Signals Usi...

引用

6th International Conference on Information Communication and Signal Processing, ICICSP 2023

作者： Gao, Hanlin Wu, Chenglong Zhu, Dandan Li, Yaan Zhang, Yang School of Marine Science and Technology Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350339994

The underwater acoustic signals are rife with various non-linear and non-stationary elements. Denoising is vital in processing these signals. In this paper, we propose a denoising method for underwater acoustic signals based on an enhanced variational mode decomposition (VMD) and reverse weighted permutation entropy (RWPE). A significant challenge in the VMD algorithm is the incorrect selection of the mode component K and the penalty factor alpha. This can lead to partial decomposition and mode interference. To tackle this issue, we employed the whale optimization algorithm (WOA). This algorithm refines the penalty factor and adjusts the mode component count in the VMD. Consequently, the optimal parameter combination for K and alpha is identified. Using this optimal set, the VMD processes the acoustic signal to yield several intrinsic mode functions (IMFs). The RWPE then identifies the IMFs embodying significant signal features. These selected IMFs are utilized for reconstruction, culminating in the denoising of the underwater acoustic signal. Comparative analyses indicate that our refined VMD method outperforms other denoising techniques. © 2023 IEEE.

关键词： reverse weighted permutation entropy underwater acoustic signals variational mode decomposition whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Lithium-Ion battery remaining useful life prediction Using variational Mode Decomposition and Improved Extreme Learning Machine Model 5

Lithium-Ion battery remaining useful life prediction Using v...

引用

5th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2023

作者： Shen, Yang Li, Deyi College of Science Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9798350357950

The aging trajectories of lithium-ion batteries show nonlinear changes and the standard extreme learning machine (ELM) results show instability. To solve these problems, a battery RUL prediction model combining VMD approach and optimized extreme learning machine is proposed. To start with, VMD is used to process the original battery capacity, it is broken down into a quantity of relatively stable modal components. Then the constructed optimal parameter combination ELM approach is adopted to dope out each capacity subsequence separately, in which the ELM network's weights and thresholds are optimized using the whale optimization algorithm, and the ultimate conseq-uences are gained by superimposing the predictions of each subsequence. The consequences indicate that the accuracy of battery RUL prediction using VMD-WOA-ELM model is significantly improved, and the prediction results are stable for multiple times, and the model shows better prediction performance. © 2023 IEEE.

关键词： extreme learning machine remaining useful life variational mode decomposition whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Use of ML algorithms in Optimisation of Electrical Automatic Industries: Empirical Analysis

Use of ML Algorithms in Optimisation of Electrical Automatic...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Mishra, Rahul Chitkara University Institute of Engineering and Technology Chitkara University Centre for Interdisciplinary Research in Business and Technology Punjab India

ISBN: (纸本)9798350357769

The whale optimization algorithm (WOA) is a meta-heuristic algorithm that draws inspiration from the bubble-net hunting tactic employed by humpback whales. Widely embraced in engineering, WOA is renowned for its simplicity, minimal operator requirements, rapid convergence, and effective balance between exploration and exploitation. This research study examines the utilization, adaptations, and combinations of the whale optimization algorithm (WOA) within several engineering disciplines. Conducting a Systematic Literature Review of 80 articles from 2018 to 2022, the study uncovers WOA's prevalence in 5 fields and 17 subfields of engineering. The review identifies strengths, weaknesses, and opportunities, indicating a growing research trend in WOA. With an anticipation of continued exploration, the paper aims to provide insights into WOA-based algorithm development, inspiring both experienced researchers and novices in the field. © 2023 IEEE.

关键词： Bubble-net hunting Metaheuristic Swarm-based whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Transformer fault diagnosis based on TWOA-SVM 10

Transformer fault diagnosis based on TWOA-SVM

引用

10th International Forum on Electrical Engineering and Automation, IFEEA 2023

作者： Yin, Yongmiao Ma, Hongwei Yan, Feichao Shanghai Dianji University Shanghai China

ISBN: (纸本)9798350309379

An improved whale optimization (T-WOA) algorithm is proposed for the problems of low accuracy of transformer fault diagnosis methods used at the present stage, low accuracy of traditional support vector machine data identification and classification, difficulty in coordinating the exploration and development ability of whale optimization algorithm, and easy to be limited to the local optimum value. Firstly, the Tent chaotic mapping method is used to initialize the population to increase the uniformity and diversity of the distribution of individuals in the initial population;secondly, the nonlinear convergence factor and nonlinear weight are introduced and the improved parameters are used to update the position of the individuals, to achieve the purpose that the algorithm's searching ability for the global optimal solution is improved. After each iteration is completed, the individuals are ranked according to their fitness, and the elite individuals with higher fitness values are selected;finally, the elite individuals are perturbed by Gaussian perturbation. The experiment verifies the high accuracy and robustness of this method for transformer fault diagnosis. © 2023 IEEE.

关键词： chaotic mapping fault diagnosis Gaussian variation transformer whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

WOA-BiLSTM-Attention Model for Short-term Power Load Projection 6

WOA-BiLSTM-Attention Model for Short-term Power Load Project...

引用

2023 IEEE 6th International Conference on Information Systems and Computer Aided Education, ICISCAE 2023

作者： Gao, Linxin Beijing Institute of Technology Beijing China

ISBN: (纸本)9798350313444

Aiming at the periodicity, nonlinearity and certain volatility of power load, this study employs historical power load data and the defining characteristics of its influencing factors for the purpose of multivariate short-term power load prediction. Subsequently, an integrated model (WOA-BiLSTM-Attention) is introduced, utilizing the whale optimization algorithm to synergize the attention mechanism and the bi-directional long short-term memory (BiLSTM) network. This innovative approach serves as a novel methodology for short-term power load forecasting. Initially, the utilization of BiLSTM involves power load prediction, wherein both historical and prospective power load data, along with their respective influencing factors, are harnessed to comprehensively capture the inherent temporal intricacies of the dataset. Following this, the Attention mechanism comes into play, acquiring the ability to independently discern the significance attributed to diverse features and chronological segments. By prioritizing attributes intricately associated with the target, it adeptly manages the extended interdependence intrinsic to the data, thus culminating in an augmented predictive accuracy. Finally, whale optimization algorithm (WOA) is utilized to find the optimal neural network parameters to reduce the model stochasticity and time costs. The utilization of electricity load data from Panama serves as an illustrative case for the conducted experiments, revealing that the WOA-BiLSTM-Attention model attains an elevated level of prediction accuracy compared to single neural network methods such as BP, LSTM, BiLSTM, etc., corresponding to an R2 of 0.93 and an RMSE of 29.49. © 2023 IEEE.

关键词： attention mechanism bi-directional long and short-term memory networks power load forecasting whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Redesigning planet carrier for material conservation using whale optimization

引用

ENGINEERING RESEARCH EXPRESS 2023年第4期5卷 045027-045027页

作者： Shinde, Harshvardhan Barpande, Girish Mali, Arun Kuldharan, Amol MIT WPU Pune India Kirloskar Pneumat Co Ltd Pune India

Planet carriers are one of the important and heavy components in planetary gearboxes. Planet carriers of heavy gearboxes used for large applications are not produced in numbers. However, the increasing cost pressures has forced designers to apply weight reduction and optimization methods for components like these as a one-time obligatory exercise. In the presented case, a candidate planet carrier used in the gearbox of a sugar mill is considered for weight reduction exercise without compromising its strength. 3D CAD model of the given planet carrier is prepared and analyzed to understand the operating stresses. The knowledge of predictable stress values at various locations are used to guide the optimization. Numerical simulations are carried out with AI based whale optimization algorithm for optimization. Obtained dimensions of optimized planet carriers are verified by the stress analysis again. The results predicted that a weight reduction of 8% can be possible with the optimized design without compromising the design constraints. The work demonstrates that a relatively simple whale optimization algorithm can be used to optimize weight for many such heavy components.

关键词： planetary gearbox planet carrier finite element analysis structural optimization whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Seepage characteristics of core rockfill dam foundation with double cutoff walls in deep overburden: A case study

引用

CASE STUDIES IN CONSTRUCTION MATERIALS 2024年 21卷

作者： Huang, Zhangxin Shen, Zhenzhong Xu, Liqun Sun, Yiqing Li, Haoxuan Liu, Detan Hohai Univ Coll Water Conservancy & Hydropower Engn Nanjing 210024 Peoples R China Minist Transport Key Lab Transport Ind Comprehens Transportat Theor Nanjing Modern Multimodal Transportat Lab Nanjing 211100 Peoples R China Hohai Univ State Key Lab Hydrol Water Resources & Hydraul Eng Nanjing 210024 Peoples R China Datang Hydropower Sci & Technol Res Inst Co Ltd Chengdu 610074 Peoples R China

Some high rockfill dams, built on deep overburden, utilize double concrete cutoff walls for seepage control, thereby introducing increased complexity to seepage characteristics in the dam foundation. This study focuses on a core rockfill dam located on the Dadu River in China, investigating the impact of dam body and foundation permeability coefficients on the percentages of hydraulic head reduction by the double cutoff walls. A multifactor sensitivity analysis, based on finite element method, is conducted to analyze this influence. Subsequently, an inversion model, integrating support vector regression and whale optimization algorithm, is proposed to identify parameters that align with seepage monitoring data. Results indicate that the permeability coefficients of the surface bedrock and the main grouting curtain exert the most significant influence. Parameters derived from the inversion model yield finite element calculations consistent with monitoring data. Moreover, upstream water level minimally affects the distribution of hydraulic head reduction percentages by the double cutoff walls. And the seepage gradient (G) in the dam foundation overburden remains below the permissible limit, with its relationship to the upstream water level (L) fitted as G = -1.03318 + 6.96E - 4 x *** study may offer valuable insights for the construction and operational management of similar projects employing double cutoff walls.

关键词： High rockfill dam Deep overburden Double concrete cutoff walls Seepage characteristics Support vector regression whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Power System Harmonic Estimation Using whaleoptimization algorithm and Least Square Approach

Power System Harmonic Estimation Using WhaleOptimization Alg...

引用

2023 Innovations in Power and Advanced Computing Technologies, i-PACT 2023

作者： Bhoi, Ashok Mallick, Ranjan Kumar Nayak, Pravati Panda, Gayadhar Mishra, Sairam Swain, Ajay kumar Department Electrical Engineering NIT Meghalay Shillong India Department of EEE Siksha 'O' Anushandhan Deemed to be University Bhubaneswar India Department Electrical Engineering Siksha 'O' Anushandhan Deemed to be University Bhubaneswar India Department Electrical Engineering Synergy Institute of Technology Phulnakhara Bhubaneswar India

ISBN: (纸本)9798350325188

The accurate estimation of harmonic components is crucial for analyzing and mitigating power system distortions, ensuring the reliable operation of electrical networks. In this paper, we present a novel approach called Optimal Harmonic Estimation (OHE) that addresses the challenges of accurately estimating harmonic content in power systems. OHE leverages advanced optimization techniques to overcome the limitations of traditional methods and provides robust and precise harmonic estimation results. In this paper we combine whale optimization algorithm (WOA) and Recursive Least Square (RLS) approach for facilitating efficient power system harmonic analysis. The proposed approach shows promising potential for harmonic estimation. © 2023 IEEE.

关键词： Harmonic estimation Power System recursive least square whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：