检索结果-内蒙古大学图书馆

Detection and Classification of Incipient Faults in Three-Phase Power Transformer Using DGA Information and Rule-based Machine learning Method

引用

JOURNAL OF CONTROL AUTOMATION AND ELECTRICAL SYSTEMS 2020年第5期31卷 1251-1266页

作者： Katooli, Mohsen Savari Koochaki, Amangaldi Islamic Azad Univ Dept Elect Engn Aliabad Katoul Branch Aliabad Katoul Iran

Three-phase transformers (TPT) play a significant and crucial function in the power networks in order to connect the sub-systems and deliver the electrical energy to final customers. The TPT are one of the most high-priced equipment in modern power networks, and therefore their working condition should be constantly monitored to prevent their breakdown, power outages and huge financial damage. Accordingly, this paper presents a hybrid method for detection and classification of incipient faults in TPT using dissolved gas analysis techniques (DGAT) information and rule-based machine learning method. In the developed method, the most informative and important items of DGAT data out of 14 items selected by association rules mining technique (ARMT) are employed as the input of adaptive neuro-fuzzy inference system (ANFIS). The ARMT is implemented to select the items, which have maximum information and can train the ANFIS more accurately. Furthermore, in order to enhance the accuracy of ANFIS and improve its robustness in different implementations, black widow optimization algorithm is applied for ANFIS training. In order to evaluate the performance of developed method on real issues, two industrial data collections obtained from Iran-Transfo Company chemical laboratory and Damavand power substations are used. The obtained results through MATLAB simulations proved that the developed method has high fault detection and classification accuracy, robust function in different implementations, short run time and simple structure.

关键词： BWO Fuzzy rules Item selection learning algorithm Transformer

来源：评论

学校读者我要写书评

暂无评论

An application of artificial neural networks for solving fractional higher-order linear integro-differential equations

引用

BOUNDARY VALUE PROBLEMS 2023年第1期2023卷 74-74页

作者： Allahviranloo, T. Jafarian, A. Saneifard, R. Ghalami, N. Nia, S. Measoomy Kiani, F. Fernandez-Gamiz, U. Noeiaghdam, S. Istinye Univ Fac Engn & Nat Sci Istanbul Turkiye Islamic Azad Univ Dept Math Urmia Branch Orumiyeh Iran Fatih Sultan Mehmet Vakif Univ Engn Fac Comp Engn Dept Istanbul Turkiye Univ Basque Country UPV Nucl Engn & Fluid Mech Dept EHU Nieves Cano 12 Vitoria 01006 Spain Irkutsk Natl Res Tech Univ Baikal Sch BRICS Ind Math Lab Irkutsk 664074 Russia South Ural State Univ Dept Appl Math & Programming Lenin Prospect 76 Chelyabinsk 454080 Russia

This ongoing work is vehemently dedicated to the investigation of a class of ordinary linear Volterra type integro-differential equations with fractional order in numerical mode. By replacing the unknown function by an appropriate multilayered feed-forward type neural structure, the fractional problem of such initial value is changed into a course of non-linear minimization equations, to some extent. Put differently, interest was sparked in structuring an optimized iterative first-order algorithm to estimate solutions for the origin fractional problem. On top of that, some computer simulation models exemplify the preciseness and well-functioning of the indicated iterative technique. The outstanding accomplished numerical outcomes conveniently reflect the productivity and competency of artificial neural network methods compared to customary approaches.

关键词： Higher-order linear integro-differential equation Artificial neural network approach Caputo fractional derivative learning algorithm Cost function

来源：评论

学校读者我要写书评

暂无评论

Evolving Dendritic Neuron Model by Equilibrium Optimizer algorithm 8

Evolving Dendritic Neuron Model by Equilibrium Optimizer Alg...

引用

IEEE International Conference on Progress in Informatics and Computing (IEEE PIC)

作者： Hou, Chunzhi Shi, Jiarui Zhang, Baohang Univ Toyama Fac Engn Toyama 9308555 Japan

ISBN: (纸本)9781665426558

In recent years, the role of a single dendritic neural structures with non-linear localisation in computing has attracted a lot of attention from the industry. The dendritic neuron model (DNM) is an approximate logical neuron model based on dendrites, with branches of dendrites corresponding to three distributions in *** model is trained to assort data as needed by mimicking the mechanisms of transmitting information and biological nerves. Traditionally DNM models use error back propagation (BP) to optimise local minimum problems, but also degrade their performance. We now train it using an equilibrium optimizer based on physical phenomena inspired by control volume mass balance. Experimental results due to some real-world classification problems show that the mentioned algorithm can improve the accuracy of the DNM solution.

关键词： artificial neural network classification equilibrium optimizer learning algorithm computational intelligence deep learning

来源：评论

学校读者我要写书评

暂无评论

A type-3 fuzzy control for current sharing and voltage balancing in microgrids

引用

APPLIED SOFT COMPUTING 2022年第0期129卷

作者： Taghieh, Amin Mohammadzadeh, Ardashir Zhang, Chunwei Kausar, Nasreen Castillo, Oscar Shenyang Univ Technol Multidisciplinary Ctr Infrastruct Engn Shenyang 110870 Peoples R China Yildiz Tech Univ Fac Arts & Sci Dept Math TR-34210 Istanbul Turkey Tijuana Inst Technol Div Grad Studies & Res Tijuana Mexico

This paper studies the current sharing and voltage balancing problems of direct current microgrids (DC-MGs) consisting of distributed generation units (DGUs) connected by a communication network. The main challenge is that the DC-MG model is prone to unknown dynamic models and external disturbances. Moreover, the voltage at each DGU's point of coupling (PC) has to converge to its desired value while the information of the DGU filter current is exchanged with the nearest neighbors. To this end, the suggested distributed control algorithm benefits from an interval type-3 fuzzy logic system (IT3FLS). To enhance the accuracy of the approximation, a learning strategy is designed based on a correntropy unscented Kalman filter (CUKF) with a fuzzy kernel size. Utilizing the approximation technique and merging the consensus-based secondary control policy with the proposed type-3 fuzzy (T3F) controller result in the balanced voltages of the closed-loop DC-MG. The convergence of the trajectories of the DC-MG is ensured and the effects of approximation error signals are investigated via the proposed method. Furthermore, the robustness of the voltages and currents against unknown uncertainties admits the efficiency of the suggested learning-based control policy. The simulation results also confirm the appropriate transient response and the robustness of trajectories, thus the suggested controller can be implemented for practical cases. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Microgrid Current sharing Voltage balancing Type-3 fuzzy logic learning algorithm Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Prediction of actual evapotranspiration by artificial neural network models using data from a Bowen ratio energy balance station

引用

NEURAL COMPUTING & APPLICATIONS 2020年第17期32卷 14001-14018页

作者： Walls, Spencer Binns, Andrew D. Levison, Jana MacRitchie, Scott Univ Guelph Sch Engn Coll Engn & Phys Sci 50 Stone Rd E Guelph ON N1G 2W1 Canada Minist Environm Conservat & Pk Environm Monitoring & Reporting Branch 125 Resources Rd Toronto ON M9P 3V6 Canada

Seven artificial neural network (ANN) models were developed to predict daytime actual evapotranspiration (ET) for Nissouri Creek in Oxford County, Canada, from April to July 2018, using the Bowen ratio energy balance method as target output for the first time. In total, 12 variations of each model were deployed using different combinations of model parameters, including the sigmoid and rectified linear unit (ReLU) activation functions, stochastic gradient descent (SGD), and root-mean-square-propagation (RMSprop) learning algorithms, three different network architectures, and 100 and 500 training epochs. This is the first time that ReLU has been used in ANNs that predict ET and it outperformed sigmoid in six of the seven models. This is particularly significant because until now the sigmoid activation function (or variations therein) had been exclusively employed in the ET literature. RMSprop was also used for the first time and typically demonstrated equivalent performance to that of SGD. The optimal model employs the ReLU activation function, consists of a 4-4-1 network architecture, includes the input parameters of net radiation, air temperature, soil heat flux, and wind speed, and is trained by the SGD learning algorithm for 500 training epochs. This model boasts a coefficient of determination (R-2) of 0.997, root-mean-square error (RMSE) of 0.39 mm/day, and mean absolute error (MAE) of 0.18 mm/day. Furthermore, all seven models developed adequately model the ET process, with R-2 ranging from 0.988 to 0.997, RMSE from 0.39 to 0.78 mm/day, and MAE from 0.18 to 0.58 mm/day.

关键词： Evapotranspiration Bowen ratio energy balance method Artificial neural networks Activation function learning algorithm ReLU

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Gradient Operator and Hyperbolic Back-Propagation learning algorithms

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2018年第5期29卷 1689-1702页

作者： Nitta, Tohru Kuroe, Yasuaki Natl Inst Adv Ind Sci & Technol Human Informat Res Inst Tsukuba Ibaraki Japan Kyoto Inst Technol Kyoto Japan

In this paper, we first extend the Wirtinger derivative which is defined for complex functions to hyperbolic functions, and derive the hyperbolic gradient operator yielding the steepest descent direction by using it. Next, we derive the hyperbolic backpropagation learning algorithms for some multilayered hyperbolic neural networks (NNs) using the hyperbolic gradient operator. It is shown that the use of the Wirtinger derivative reduces the effort necessary for the derivation of the learning algorithms by half, simplifies the representation of the learning algorithms, and makes their computer programs easier to code. In addition, we discuss the differences between the derived Hyperbolic-BP rules and the complex-valued backpropagation learning rule (Complex-BP). Finally, we make some experiments with the derived learning algorithms. As a result, we find that the convergence rates of the Hyperbolic-BP learning algorithms are high even if the fully activation functions are used, and discover that the Hyperbolic-BP learning algorithm for the hyperbolic NN with the split-type hyperbolic activation function has an ability to learn hyperbolic rotation as its inherent property.

关键词： Backpropagation hyperbolic number learning algorithm neural network (NN) Wirtinger calculus

来源：评论

学校读者我要写书评

暂无评论

A Fuzzy Restricted Boltzmann Machine: Novel learning algorithms Based on the Crisp Possibilistic Mean Value of Fuzzy Numbers

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2018年第1期26卷 117-130页

作者： Feng, Shuang Chen, C. L. Philip Beijing Normal Univ Sch Appl Math Zhuhai 519085 Peoples R China Univ Macau Fac Sci & Technol Macau 99999 Peoples R China UMacau Res Inst Zhuhai 519080 Peoples R China Dalian Maritime Univ Dalian 116026 Peoples R China

A fuzzy restricted Boltzmann machine (FRBM) is extended from a restricted Boltzmann machine (RBM) by replacing all the real-valued parameters with fuzzy numbers. A new FRBM that employs the crisp possibilistic mean value of a fuzzy number to defuzzify the fuzzy free energy function is presented. This approach is much clearer and easier to obtain the expression of the defuzzified free energy function and its approximation than the centroid method. Several theorems that discuss the error bounds of the approximation to ensure the rationality and validity are also investigated. learning algorithms are given for the designed FRBM with symmetric triangular fuzzy numbers (STFNs), asymmetric triangular fuzzy numbers, and Gaussian fuzzy numbers. By appropriately choosing the parameters, a theorem is concluded that all FRBMs with symmetric fuzzy numbers will have identical learning algorithm to that of FRBMs with STFNs. This is illustrated by a case of FRBM with Gaussian fuzzy numbers. Two experiments including the MNIST handwriting recognition and the Bars-and-Stripes benchmark are carried out. The results show that the proposed FRBMs significantly outperform RBMs in learning accuracy and generalization ability, especially when encountering unlearned samples and recovering incomplete images.

关键词： Crisp possibilistic mean value fuzzy number fuzzy restricted Boltzmann machine (FRBM) learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Coordinated control scheme for provision of frequency regulation service by virtual power plants

引用

APPLIED ENERGY 2022年 325卷

作者： Oshnoei, Arman Kheradmandi, Morteza Blaabjerg, Frede Hatziargyriou, Nikos D. Muyeen, S. M. Anvari-Moghaddam, Amjad Shahid Beheshti Univ Fac Elect Engn Tehran Iran Aalborg Univ Dept Energy DK-9220 Aalborg Denmark Natl Tech Univ Athens Sch Elect & Comp Engn Athens Greece Qatar Univ Dept Elect Engn Doha Qatar

This paper proposes a coordinated control strategy for a Virtual Power Plant (VPP) contribution to load frequency control. The considered VPP comprises distributed Battery Energy Storage Systems (BESSs) and Heat Pump Water Heaters (HPWHs). The frequency regulation signal is distributed between thermal generator and the VPP based on distribution coefficients which are calculated through conducting a multi-objective optimization problem. The optimization framework incorporates the dynamic regulation performance as well as the total regulation cost. A fuzzy strategy is adopted to obtain the final solution according to user-defined conditions. The regulation signal of VPP is dispatched based on the speed and the available power capacity of VPP components. The performance of the proposed coordination scheme is compared to the scheme without coordination and that with no involvement of VPP in frequency regulation. The regulation performance is also evaluated for varying time delays expected in the communication channels. An approach based on brain emotional learning is developed to coordinate the VPP and conventional generation unit to avoid large frequency deviations caused by the communication delays. Case studies are conducted on a multi-area power system in MATLAB/Simulink environment, and the results are verified by the OPAL-RT real-time simulator.

关键词： Battery Energy Storage System (BESS) learning algorithm Load frequency control (LFC) Heat pump water heater (HPWH) Virtual power plant (VPP)

来源：评论

学校读者我要写书评

暂无评论

Model Free Adaptive Control algorithm based on GRU network 33

Model Free Adaptive Control Algorithm based on GRU network

引用

33rd Chinese Control and Decision Conference (CCDC)

作者： Sun, Jinggao Chen, Xianfeng Su, Guanghao Pan, Hongguang East China Univ Sci & Technol Key Lab Adv Control & Optimizat Chem Proc Minist Educ Shanghai 200237 Peoples R China Xian Univ Sci & Technol Sch Elect & Control Engn Xian 710049 Peoples R China

ISBN: (纸本)9781665440899

The application of traditional adaptive control algorithm usually depends on the precise mathematical model of process, but it is difficult to establish a mathematical model for a dynamic process. The existing Model Free Adaptive (MFA) control algorithm structure is based on Back Propagation(BP) Neural Network, which does not fully take into account the continuous characteristic relationship between the input timing error sequences. According to this actual problem, an improved MFA control algorithm based on Gated Recurrent Unit (GRU) network is proposed in this paper, compared with BP network, GRU network has more advantages in processing timing series. It fully considers the information of error sequence, and more appropriate manipulated variable could be generated automatically to satisfy the demand of an open-loop stable and controllable single-variable, multivariable or large delay process system without the need for complicated manual adjustments, quantitative knowledge of the process or the identifier of the controlled system and learning process. Simulation results demonstrate that the GRU-MFA learning algorithm performs better in terms of stability, response speed and adaptability than the BP-MFA algorithm without human intervention.

关键词： Model free adaptive control Timing error sequences Gated recurrent unit learning algorithm

来源：评论

学校读者我要写书评

暂无评论

An artificial neural network for predicting air traffic demand based on socio-economic parameters

引用

Decision Analytics Journal 2024年 10卷

作者： Alam, Md Shafiqul Deb, Jayanta Bhusan Amin, Abdullah Al Chowdhury, Shilpa Faculty of Graduate Studies & Research University of Regina SK Canada Department of Engineering & Technology Western Carolina University NC United States Department of Aeronautical Engineering Bangladesh University of Professionals Bangladesh Department of Information Systems and Analysis Lamar University TX United States

Over the past five years, emerging economies have consistently progressed toward achieving greater economic independence. The aviation industry has played a significant role in driving this progress. Accurately forecasting the future demand for air travel is crucial for making long-term commitments to these economies. The findings of this study provide valuable insights into the provision of low-cost passenger carrier demand. They can assist low-cost carriers, airports, airport consultants, and government agencies in their strategic planning and development processes. The primary objective of this study is to identify and evaluate artificial intelligence-based solutions, specifically, Artificial Neural Networks (ANN), to determine the most effective model for projecting domestic demand for low-cost carriers. The study analyzes nine variables that impact the accuracy of predicting domestic air passenger demand in emerging countries using a Multilayer Feed-Forward Backpropagation Neural (MFFBPN) network. The performance of the developed ANN model for predicting air passenger demand is assessed through training, validation, and testing using 240 data sets. The evaluation metrics employed, including mean square error (MSE), root mean square error (RMSE), accuracy, precision, sensitivity, and specificity, indicate the effectiveness of the developed ANN model, with results of 0.0019 for MSE, 0.0440 for RMSE, 0.92 for accuracy, 0.92 for precision, 0.93 for sensitivity, and 0.95 for specificity. We show that modeling based on artificial intelligence approaches and ANN is more effective than conventional linear regression models. © 2023 The Author(s)

关键词： Activation function Artificial neural network Aviation industry Data normalization learning algorithm Multilayer feed-forward backpropagation neural network

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：