检索结果-内蒙古大学图书馆

Multilayer perceptron for reference evapotranspiration estimation in a semiarid region

NEURAL COMPUTING & APPLICATIONS 2013年第2期23卷 341-348页

作者： Tabari, Hossein Talaee, P. Hosseinzadeh Islamic Azad Univ Dept Water Engn Ayatollah Amoli Branch Amol Iran Islamic Azad Univ Hamedan Branch Hamadan Iran

Calculation of reference evapotranspiration (ETo) is essential in hydrology and agriculture. ETo plays an important role in planning and management of water resources and irrigation scheduling. The results of many studies strongly support the use of the Penman-Monteith FAO 56 (PMF-56) method as the standard method of estimating ETo. The basic obstacle to using this method widely is the numerous meteorological variables required. Multilayer perceptron (MLP) networks optimized with different learning algorithms and activation functions were applied for estimating ETo in a semiarid region in Iran. Four MLP models comprising various combinations of meteorological variables are developed. The MLP model which needs all of the meteorological parameters performed best for ETo estimation amongst the other MLP models. It was also found that the ConjugateGradient, DeltaBarDelta, DeltaBarDelta and Levenberg-Marquardt were the best algorithms for training the MLP1, MLP2, MLP3 and MLP4 models, respectively.

关键词： Reference evapotranspiration Artificial neural network learning algorithm Meteorological parameters Iran

来源：评论

学校读者我要写书评

暂无评论

Model-based update in task-level feedforward control using on-line approximation

引用

AUTOMATICA 2001年第3期37卷 391-400页

作者： Gorinevsky, D Vukovich, G Honeywell Technol Ctr Cupertino CA 95014 USA Canadian Space Agcy St Hubert PQ J3Y 8Y9 Canada

This paper proposes and studies an algorithm for task-level control based on a radial. basis function network approximation of the optimal task input vector on parameters of the task. A learning update scheme is proposed for on-line compensation for the inaccuracy of the model used in the controller design. The update approximates the Jacobian of the task input-output mapping using an off-line design model. Deadzone convergence of this learning scheme in the presence of modeling errors is proved and constructive estimates of the convergence robustness parameters are obtained. An application of the proposed algorithm to Feedforward vibration compensation for flexible spacecraft slewing complements the theoretical analysis. Simulations demonstrate practically acceptable performance of the algorithms in this difficult problem. (C) 2001 Elsevier Science Ltd. All rights reserved.

关键词： feedforward control learning algorithm convergence neural network approximation flexible spacecraft

来源：评论

学校读者我要写书评

暂无评论

Training feedforward neural network via multiobjective optimization model using non-smooth L1/2 regularization

引用

NEUROCOMPUTING 2020年 410卷 1-11页

作者： Senhaji, Kaoutar Ramchoun, Hassan Ettaouil, Mohamed Sidi Mohamed Ben Abdellah Univ Lab Modeling & Sci Comp FST Fez Fes Morocco Moulay Ismail Univ Natl Sch Business & Management Lab Math Modeling Simulat & Smart Syst Meknes Morocco BCAM Basque Ctr Appl Math Bilbao Spain

The paper presents a new approach to optimize the Multilayer Perceptron Neural Network (MLPNN), to deal with the generalization problem. As known, most supervised learning algorithms aim to minimize the training error. However, the mentioned methods, based only on error minimizing, may generate a solution with an insufficient generalization performance. This present work proposes a multiobjective modelling problem involving two objectives: accuracy and complexity since the learning problem is multiobjective by nature. The learning task is carried on by minimizing both objectives simultaneously, according to Pareto domination concept, using NSGAII (Non-dominated Sorting Genetic algorithm II) as a solver. This method leads us to a set of solutions called Pareto front, being the optimal solutions set, the adequate MLPNN need to be extracted. We show empirically that the proposed method is capable of reducing the neural networks topology and improved generalization performance, in addition to a good classification rate compared to different methods. (C) 2020 Published by Elsevier B.V.

关键词： Multiobjective optimization NSGAII learning algorithm L-1/2 regularization Neural network

来源：评论

学校读者我要写书评

暂无评论

An intelligent method for online voltage stability margin assessment using optimized ANFIS and associated rules technique

引用

ISA TRANSACTIONS 2020年 102卷 91-104页

作者： Ghaghishpour, Amin Koochaki, Amangaldi Islamic Azad Univ Aliabad Katoul Branch Dept Elect Engn Aliabad Katoul Iran

This paper puts forward an intelligent method for online voltage stability margin (VSM) assessment based on optimal fuzzy system and feature selection technique, which has excellent performance for large power systems. The proposed VSM estimation method includes three key parts: feature extraction and selection part, estimator part and training part. In this method, power system's loading parameters are used as the main input of adaptive neuro-fuzzy inference system (ANFIS) and association rules (AR) technique is used to select the most effective loading parameters. In the training part, we used Harris hawks optimization algorithm (HHOA) to train the ANFIS efficiently. Using the proposed method, the VSM can be monitored online with high precision for both small and large systems and appropriate control measures can be applied if necessary. Knowing the exact amount of VSM and applying precautionary measures can prevent from voltage collapse, heavy financial losses and power supply interruption. The proposed method tested on 39-bus, 118-bus and 300-bus IEEE test system and the MATLAB simulation results demonstrated that the propounded method has much better performance than other recently introduced VSM assessment approaches. Providing a VSM estimation method, which is effective for large power systems, selecting the most informative loading parameters and improving the ANFIS's performance using HHOA are the main contributions of this paper. (C) 2020 ISA. Published by Elsevier Ltd. All rights reserved.

关键词： ANFIS Estimation Feature selection learning algorithm Voltage stability

来源：评论

学校读者我要写书评

暂无评论

A new fractional-order developed type-2 fuzzy control for a class of nonlinear systems

引用

INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE 2023年第15期54卷 2840-2858页

作者： Sedaghati, Akram Pariz, Naser Siahi, Mehdi Barzamini, Roohollah Islamic Azad Univ Dept Elect Engn Cent Tehran Branch Tehran Iran Ferdowsi Univ Mashhad Dept Elect Engn Mashhad Razavi Khorasan Iran Islamic Azad Univ Fac Mech Elect Power & Comp Sci & Res Branch Tehran Iran

In this paper, a novel fractional-order adaptive controller is presented for a class of nonlinear systems with unknown dynamics. The dynamics of the system is considered to be fully unknown. The multi-layer perceptron (MLP) neural network using restricted Boltzmann machine (RBMs) is employed for online dynamic identification. A deep learning method on the basis of contrastive divergence (CD) algorithm combined with the extended Kalman filter (EKF) is proposed for online optimisation. The proposed controller has two parts. The first part is a simple error feedback controller and the second one is the suggested DT2-FLS. The parameters of DT2-FLS are tuned such that a cost function of tracking error to be minimised and the closed-loop system to be stable. For the best knowledge of the authors, for the first time the tuning rules for the membership function and rule parameters of DT2-FLS are derived by error feedback learning method. The closed-loop stability is demonstrated with Lyapunov method and the well performance of the schemed controller is shown by applying on the induction motor and brushless DC motors. In addition to unknown dynamics, some disturbances are also considered such as abruptly changes in load torque and time-varying rotor resistance. Furthermore, the performance of the suggested scheme is compared with some popular controllers and FLSs.

关键词： Control systems neural networks fuzzy systems learning algorithm robust control stability analysis

来源：评论

学校读者我要写书评

暂无评论

Intelligent tracking control of a PMLSM using self-evolving probabilistic fuzzy neural network

引用

IET ELECTRIC POWER APPLICATIONS 2017年第6期11卷 1043-1054页

作者： Chen, Syuan-Yi Liu, Tung-Sheng Natl Taiwan Normal Univ Dept Elect Engn Taipei 106 Taiwan

This study presents a self-evolving probabilistic fuzzy (PF) neural network with asymmetric membership function (SPFNN-AMF) controller for the position servo control of a permanent magnet linear synchronous motor (PMLSM) servo drive system. In the beginning, the dynamic model for the PMLSM is analysed on the basis of field-oriented control. Subsequently, an SPFNN-AMF control system, which integrates the advantages of self-evolving NN, PF logic system, and AMF, is proposed to handle vagueness, randomness, and time-varying uncertainties of the PMLSM servo drive system during the control process. For the SPFNN-AMF, the proposed learning algorithm consists of the structure learning and parameter learning in which the former is used to grow and prune the fuzzy rules automatically, whereas the latter is utilised to train the network parameters dynamically. Finally, detailed experimental results of two position commands tracking at different operation conditions demonstrate the validity and robustness of the proposed SPFNN-AMF for controlling the PMLSM servo drive system.

关键词： intelligent control permanent magnet motors linear motors synchronous motors machine control position control machine vector control intelligent tracking control SPFNN self-evolving probabilistic fuzzy neural network asymmetric membership function controller permanent magnet linear synchronous motor servo drive system field-oriented control SPFNN-AMF control system PMLSM servo drive system control process learning algorithm structure learning parameter learning

来源：评论

学校读者我要写书评

暂无评论

Can periodic perceptrons replace multi-layer perceptrons?

引用

PATTERN RECOGNITION LETTERS 2000年第12期21卷 1019-1025页

作者： Racca, R Univ Antilles & Guyane French W Indies UFR Sci Exactes & Nat F-97159 Pointe A Pitre France

We propose an efficient alternative to multi-layer perceptron (MLP): two-layer periodic perceptron (PP). We prove then that PP can compute every binary boolean function, we give an efficient learning algorithm for PP ... 详细信息

关键词： multi-layer perceptron periodic perceptron learning algorithm parity problem character recognition speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Blind source separation - Semiparametric statistical approach

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 1997年第11期45卷 2692-2700页

作者： Amari, S Cardoso, JF ECOLE NATL SUPER TELECOMMUN BRETAGNE CNRSSIGNAL DEPTPARISFRANCE UNIV TOKYO BUNKYO KUTOKYO 113JAPAN

The semiparametric statistical model is used to formulate the problem of blind source separation. The method of estimating functions is applied to this problem, It is shown that an estimator of the mixing matrix or its learning version can be described in terms of an estimating function. The statistical efficiencies of these algorithms are studied. The main results are as follows. 1) The space consisting of all the estimating functions is derived. 2) The spare is decomposed into the orthogonal sum of the admissible part and redundant ancillary part. For any estimating function, one can find a better or equally good estimator in the admissible part. 3) The Fisher efficient (that is, asymptotically best) estimating functions are derived4) The stability of learning algorithms is studied.

关键词： blind source separation estimating function independent component analysis learning algorithm semiparametric statistical model

来源：评论

学校读者我要写书评

暂无评论

Fast learning in Spiking Neural Networks by learning Rate Adaptation

引用

Chinese Journal of Chemical Engineering 2012年第6期20卷 1219-1224页

作者：方慧娟罗继亮王飞 College of Information Science and Engineering Huaqiao University

For accelerating the supervised learning by the SpikeProp algorithm with the temporal coding paradigm in spiking neural networks (SNNs), three learning rate adaptation methods (heuristic rule, delta-delta rule, and delta-bar-delta rule), which are used to speed up training in artificial neural networks, are used to develop the training algorithms for feedforward SNN. The performance of these algorithms is investigated by four experiments: classical XOR (exclusive or) problem, Iris dataset, fault diagnosis in the Tennessee Eastman process, and Poisson trains of discrete spikes. The results demonstrate that all the three learning rate adaptation methods are able to speed up convergence of SNN compared with the original SpikeProp algorithm. Furthermore, if the adaptive learning rate is used in combination with the momentum term, the two modifications will balance each other in a beneficial way to accomplish rapid and steady convergence. In the three learning rate adaptation methods, delta-bar-delta rule performs the best. The delta-bar-delta method with momentum has the fastest convergence rate, the greatest stability of training process, and the maximum accuracy of network learning. The proposed algorithms in this paper are simple and efficient, and consequently valuable for practical applications of SNN.

关键词： spiking neural networks learning algorithm learning rate adaptation Tennessee Eastman process

来源：评论

学校读者我要写书评

暂无评论

A type-3 logic fuzzy system: Optimized by a correntropy based Kalman filter with adaptive fuzzy kernel size

引用

INFORMATION SCIENCES 2021年 572卷 424-443页

作者： Qasem, Sultan Noman Ahmadian, Ali Mohammadzadeh, Ardashir Rathinasamy, Sakthivel Pahlevanzadeh, Bahareh Al Imam Mohammad Ibn Saud Islamic Univ IMSIU Coll Comp & Informat Sci Comp Sci Dept Riyadh 11432 Saudi Arabia Taiz Univ Fac Appl Sci Comp Sci Dept Taizi 6803 Yemen Univ Bonab Elect Engn Dept Bonab Iran Bharathiar Univ Dept Appl Math Coimbatore 641046 Tamil Nadu India Reg Informat Ctr Sci & Technol RICeST Dept Design & Syst Operat Shiraz Fars Iran

In this study, a self-organizing interval type-3 fuzzy logic system (SO-IT3FLS) with a new learning algorithm is presented. An adaptive kernel size using fuzzy systems is introduced to improve the robustness of conventional correntropy based Kalman filters against non-Gaussian noise. The maximum correntropy Kalman filter (MCKF) and maximum correntropy unscented Kalman filter (MCUKF) with the proposed adaptive fuzzy kernel size are reformulated to optimize both rule and antecedent parameters, respectively. In addition to the rule parameters, the proposed membership function (MF) parameters and the level of alpha-cuts are also optimized. Five simulation examples with real-world data sets are given for examination. The simulations show that the introduced SO-IT3FLS and learning algorithm result in better accuracy in contrast to the other kind of fuzzy neural networks and conventional learning techniques. Furthermore, it is verified that the robustness of the proposed learning method against non-Gaussian noise is improved in contrast to the conventional Kalman filter, maximum correntropy Kalman filter and unscented Kalman filter. (C) 2021 Elsevier Inc. All rights reserved.

关键词： Interval type-3 fuzzy logic systems Self-organizing Kalman filter Correntropy criterion learning 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：