检索结果-内蒙古大学图书馆

A Modified Kalman Filter Based on radial basis function neural networks for the Improvement of Numerical Weather Prediction Models

引用

ATMOSPHERE 2025年第3期16卷 248-248页

作者： Donas, Athanasios Galanis, George Pytharoulis, Ioannis Famelis, Ioannis Th. Univ West Attica Dept Elect & Elect Engn microSENSES Lab Ancient Ol Grove Campus 250Thivon Ave Athens 12241 Greece Hellen Naval Acad Math Modeling & Applicat Lab Piraeus 18539 Greece Aristotle Univ Thessaloniki Sch Geol Dept Meteorol & Climatol Thessaloniki 54124 Greece

This study introduces a novel enhancement to the Kalman filter algorithm by integrating it with radial basis function neural networks to improve numerical weather prediction models. Traditional Kalman filters frequently underperform when used by dynamical systems due to their reliance on fixed covariance matrices, resulting in inaccuracies and forecast uncertainty. The proposed modified Kalman filter utilizes radial basis function neural networks to estimate covariance matrices adaptively during the filtering process. This self-adaptive computational system enables the simultaneous targeting of the systematic and the remaining non-systematic parts of the forecast error, producing an innovative and efficient post-process strategy. The suggested methodology is evaluated on predictions of 10-meter wind speed and 2-meter air temperature obtained from the Weather Research and Forecasting model for observation stations in northern Greece. The derived results demonstrate a significant reduction in systematic error, as the bias decreased by up to 88% for 10-meter wind speed and 58% for 2-meter air temperature. Additionally, the forecast variability was successfully mitigated, with the RMSE reduced by 39% and 40%, respectively. Compared to the traditional Kalman filter, which exhibited increased RMSE in several cases and failed to control forecast uncertainty, the proposed approach consistently outperformed by providing stable and reliable predictions across all examined scenarios. These improvements validate the robustness of the method in comparison to conventional techniques, highlighting its potential to produce reliable and stable predictions for environmental applications.

关键词： air temperature post-process algorithms radial basis function neural networks Kalman filters Weather Research and Forecasting model wind speed

来源：评论

学校读者我要写书评

暂无评论

Adaptive learning observer and radial basis function neural networks based fixed-time fault-tolerant control of load following fora MHTGR with CRDM faults

引用

NUCLEAR ENGINEERING AND DESIGN 2025年 433卷

作者： Liu, Wangheng Liu, Hongliang Ouyang, Zigen Zeng, Wenjie Liu, Hua Univ South China Sch Math & Phys Hengyang 421001 Peoples R China Univ South China Sch Nucl Sci & Technol Hengyang 421001 Peoples R China Univ South China Sch Elect Engn Hengyang 421001 Peoples R China

Load following of the Modular High-Temperature Gas-Cooled Reactor (MHTGR) under Control Rod Drive Mechanism (CRDM) faults and disturbances remains a major challenge. This paper focuses on proposing a fixed-time fault-tolerant control method for this issue without considering the sensitivities associated with parameter setting. Firstly, to reconstruct some unmeasurable states of the MHTGR and the values of CRDM faults, an adaptive learning observer is established. Based on the learning characteristic of radial basis function neural networks (RBFNN), the lumped uncertainties can be approximated. And then a fixed-time fault-tolerant controller is developed to ensure that the actual load output of the MHTGR actually tracks the expected output power within a fixed time, which can be determined through the system and controller parameters. Finally, simulations under two operational conditions demonstrate the control method is effective and feasible to the MHTGR system under disturbance and CRDM faults.

关键词： Adaptive learning observer radial basis function neural networks Fixed-time fault-tolerant control Control rod drive mechanism faults Load following for modular high-temperature gas-cooled reactor

来源：评论

学校读者我要写书评

暂无评论

A time-varying second-order sliding mode control of super-twisting based on radial basis function neural networks

引用

JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING 2025年第6期47卷 1-13页

作者： Chen, Jiqing Zhang, Haiyan Pan, Shangtao Zhu, Tongtong Lin, Yizhong Guangxi Univ Coll Mech Engn Nanning 530004 Peoples R China

A manipulator often cannot converge rapidly within finite time and has low tracking accuracy owing to factors such as manipulator model errors and external disturbances. To address these problems, this paper proposes a time-varying second-order sliding mode control of super-twisting based on radial basis function neural networks. First, three radial basis neural networks are optimized by the gradient descent method to approximate the parameters of the dynamic model of the manipulator, thus getting rid of the dependence on the model. Second, a time-varying nonsingular fast terminal sliding mode surface is designed to achieve fast convergence in finite time. Meanwhile, an improved super-twisting algorithm is adopted in combination with the boundary layer concept, which not only eliminates the chattering but also improves the tracking accuracy. Finally, simulation experiments are carried out by simulating a 2-DOF and a 6-DOF manipulator. The results verify the effectiveness and superiority of the proposed method.

关键词： Manipulator Second-order sliding mode control Super-twisting algorithm radial basis function neural networks Trajectory tracking

来源：评论

学校读者我要写书评

暂无评论

radial basis function neural networks in non-destructive determination of compound aspirin tablets on NIR spectroscopy

引用

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 2006年第1期65卷 79-83页

作者： Dou, Ying Mi, Hong Zhao, Lingzhi Ren, Yuqiu Ren, Yulin Jilin Univ Coll Chem Changchun 130021 Peoples R China Jilin Inst Tradit Chines Med Changchun 130021 Peoples R China Baicheng Med Coll Baicheng 137000 Peoples R China

The application of the second most popular artificial neural networks (ANNs), namely, the radial basis function (RBF) networks, has been developed for quantitative analysis of drugs during the last decade. In this paper, the two components (aspirin and phenacetin) were simultaneously determined in compound aspirin tablets by using near-infrared (NIR) spectroscopy and RBF networks. The total database was randomly divided into a training set (50) and a testing set (17). Different preprocessing methods (standard normal variate (SNV), multiplicative scatter correction (MSC), first-derivative and second-derivative) were applied to two sets of NIR spectra of compound aspirin tablets with different concentrations of two active components and compared each other. After that, the perfonnance of RBF learning algorithm adopted the nearest neighbor clustering algorithm (NNCA) and the criterion for selection used a cross-validation technique. Results show that using RBF networks to quantificationally analyze tablets is reliable, and the best RBF model was obtained by first-derivative spectra. (c) 2005 Elsevier B.V. All rights reserved.

关键词： radial basis function neural networks NIR spectroscopy preprocessing compound aspirin tablets

来源：评论

学校读者我要写书评

暂无评论

radial basis function neural networks based on projection pursuit approach and solvatochromic descriptors: single and full column prediction of gas chromatography retention behavior of polychlorinated biphenyls

引用

JOURNAL OF CHEMOMETRICS 2016年第10期30卷 589-601页

作者： Hassanzadeh, Zeinabe Ebrahimi, Parastoo Kompany-Zareh, Mohsen Ghavami, Raouf Univ Kurdistan Dept Chem Fac Sci POB 416 Sanandaj Kurdistan Iran Inst Adv Studies Basic Sci IASBS Dept Chem Zanjan Iran

The ultimate goal of projection methods is to search interesting projections in a low-dimensional subspace that can uncover the natural structure of the data. The aim of this work is to compare the ability of projection pursuit (PP) and principal component analysis (PCA) in dimension reduction. For this purpose to be achieved, the scores of PP and PCA, by a different number of factors, were used as inputs of radial basis function (RBF) neural network. RBF neural network was used as a nonlinear regression method in a quantitative structure-retention relationships study of 209 polychlorinated biphenyls (PCBs). The dependent variable was the high-resolution gas chromatographic relative retention times of PCBs on 18 different stationary phases, and independent variables were solvatochromic solute descriptors. The results demonstrate that the dimension reduction ability of the PP is better than that of the PCA for both single and full column retention models. The present article compares the ability of projection pursuit (PP) and principal component analysis (PCA) in dimension reduction. The scores of PP and PCA, by a different number of factors, were used as inputs of radial basis function neural network. radial basis function was used as a nonlinear regression method in a quantitative structure-retention relationship study of 209 polychlorinated biphenyls. The results demonstrate that the dimension reduction ability of the PP is better than that of the PCA.

关键词： polychlorinated biphenyls PP-RBF projection pursuit radial basis function neural networks

来源：评论

学校读者我要写书评

暂无评论

radial basis function neural networks for optimal control with model reduction and transfer learning

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartA期136卷

作者： Zhao, Anni Xing, Siyuan Wang, Xi Sun, Jian-Qiao Univ Calif Merced Sch Engn Dept Mech Engn Merced CA 95343 USA Calif Polytech State Univ San Luis Obispo Dept Mech Engn San Luis Obispo CA USA Xi An Jiao Tong Univ State Key Lab Strength & Vibrat Xian 710049 Peoples R China

This paper proposes a method to compute the solutions of linear optimal control expressed in terms of the radial basis function neural networks with Gaussian activation functions for multi-degree-of-freedom dynamic systems. Hamilton-Jacobi-Bellman equation is adopted to formulate the optimal control problem. The radial basis function neural networks are proposed to approximate the value function to solve the Hamilton-Jacobi- Bellman equation with a policy iteration algorithm. A dominant stabilizing control is proposed as an initial control to start the policy iteration that guarantees the convergence of the iteration, particularly for openloop unstable dynamic systems. The balanced truncation technique is applied to the multi-degree-of-freedom dynamic system to reduce the dimension of the original system, which provides multiple advantages when applying the radial basis function neural networks to unstable dynamic systems in a relatively high dimensional state space. Transfer learning is also adopted to update radial basis function neural networks with experimental data, which results in further control performance improvement. Numerical simulations and experimental studies show that the radial basis function neural networks not only find accurate optimal controls for linear systems, but also offer excellent performance in trajectory tracking and stabilization applications.

关键词： Hamilton-Jacobi-Bellman equation radial basis function neural networks Policy iteration Balanced truncation Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Polynomial-based radial basis function neural networks (P-RBF NNs) and their application to pattern classification

引用

APPLIED INTELLIGENCE 2010年第1期32卷 27-46页

作者： Park, Byoung-Jun Pedrycz, Witold Oh, Sung-Kwun Elect & Telecommun Res Inst Telemat & USN Res Dept Taejon 305700 South Korea Univ Alberta Dept Elect & Comp Engn Edmonton AB T6R 2G7 Canada Polish Acad Sci Syst Res Inst PL-01447 Warsaw Poland Univ Suwon Dept Elect Engn Hwaseong Si Gyeonggi Do South Korea

Polynomial neural networks have been known to exhibit useful properties as classifiers and universal approximators. In this study, we introduce a concept of polynomial-based radial basis function neural networks (P-RBF NNs), present a design methodology and show the use of the networks in classification problems. From the conceptual standpoint, the classifiers of this form can be expressed as a collection of "if-then" rules. The proposed architecture uses two essential development mechanisms. Fuzzy clustering (Fuzzy C-Means, FCM) is aimed at the development of condition parts of the rules while the corresponding conclusions of the rules are formed by some polynomials. A detailed learning algorithm for the P-RBF NNs is developed. The proposed classifier is applied to two-class pattern classification problems. The performance of this classifier is contrasted with the results produced by the "standard" RBF neural networks. In addition, the experimental application covers a comparative analysis including several previous commonly encountered methods such as standard neural networks, SVM, SOM, PCA, LDA, C4.5, and decision trees. The experimental results reveal that the proposed approach comes with a simpler structure of the classifier and better prediction capabilities.

关键词： Polynomial neural networks radial basis function neural networks Pattern classification Fuzzy clustering Two-class discrimination

来源：评论

学校读者我要写书评

暂无评论

Development of intelligent sorting system realized with the aid of laser-induced breakdown spectroscopy and hybrid preprocessing algorithm-based radial basis function neural networks for recycling black plastic wastes

引用

JOURNAL OF MATERIAL CYCLES AND WASTE MANAGEMENT 2018年第4期20卷 1934-1949页

作者： Roh, Seok-Beom Park, Sang-Beom Oh, Sung-Kwun Park, Eun-Kyu Choi, Woo Zin Univ Suwon Dept Elect Engn San 2-2 Hwaseong Si 445743 Gyeonggi Do South Korea Univ Suwon Dept Environm & Energy Engn San 2-2 Hwaseong Si 445743 Gyeonggi Do South Korea

Plastic recycling has been the key issue for reducing environmental problems and resolving resource depletion. To improve the recovery rate of plastics, the plastic wastes are correctly identified according to their resin type. However, the identification system, which is able to identify black plastics according to not only the type of black plastics but also the grade of resins correctly, has not been introduced. In this paper, laser-induced breakdown spectroscopy, intelligent algorithms and preprocessing algorithms are used to improve the identification of black plastics such as polypropylene, polystyrene (PS), and acrylonitrile butadiene styrene (ABS). The laser-induced breakdown spectroscopy is capable of obtaining the characteristic spectrum regardless of material's physical state. To extract the new features which are very valuable to improving learning performance, increasing computational efficiency, and building better generalization models from the obtained spectra through laser-induced breakdown spectroscopy, the hybrid preprocessing algorithm, composed of principal component analysis and independent component analysis, is used. In addition, the intelligent algorithm named the extended radial basis function neural networks inheriting the advantages of fuzzy theory and neural networks is used to identify black plastic samples into several categories with respect to their resins. The proposed identification system, composed of three parts such as laser induced breakdown spectroscopy, hybrid preprocessing algorithms, and an efficient intelligent classification algorithm, is able to show the synergy effect on the black plastic identification problem. From several experimental results, it can be seen that the identification system based on laser-induced breakdown spectroscopy and the intelligent algorithm is used for identification of black plastics by resin type.

关键词： Sorting system Hybrid preprocessing algorithm radial basis function neural networks Laser-induced breakdown spectroscopy (LIBS) Black plastic wastes

来源：评论

学校读者我要写书评

暂无评论

Nondestructive Prediction of Tilapia Fillet Freshness During Storage at Different Temperatures by Integrating an Electronic Nose and Tongue with radial basis function neural networks

引用

FOOD AND BIOPROCESS TECHNOLOGY 2018年第10期11卷 1840-1852页

作者： Shi, Ce Yang, Xinting Han, Shuai Fan, Beilei Zhao, Zhiyao Wu, Xiaoming Qian, Jianping Beijing Acad Agr & Forestry Sci Beijing Res Ctr Informat Technol Agr Beijing 100097 Peoples R China NERCITA Beijing 100097 Peoples R China Natl Engn Lab Agriprod Qual Traceabil Beijing 100097 Peoples R China Beijing Technol & Business Univ Sch Comp & Informat Engn Beijing 100048 Peoples R China

This study developed principal component analysis and radial basis function neural networks (PCA-RBFNNs) for predicting freshness in tilapia fillets stored at different temperatures by integrating an electronic nose and electronic tongue. Total volatile basic nitrogen (TVB-N), total aerobic counts (TAC), and K value increased at 0, 4, 7, and 10 degrees C, while sensory scores decreased significantly. The electronic nose and tongue acquired the volatiles and dissolved chemical compounds in the stored samples. Gas chromatography-mass spectrometry (GC-MS) verified the changes in gas species and contents in fillets stored for different periods of time at different temperatures. PCA-RBFNNs based on data fusion were developed and presented good performance for prediction of TVB-N, TAC, K value, and sensory score in tilapia fillets. The established PCA-RBFNNs based on feature variables of the electronic nose and tongue is a promising method to predict changes in the freshness of fillets stored from 0 to 10 degrees C in the cold chain.

关键词： Electronic nose and tongue Chilled storage radial basis function neural networks Tilapia fillets Quality prediction

来源：评论

学校读者我要写书评

暂无评论

Identification of Damping and Dynamic Young's Modulus of a Structural Adhesive Using radial basis function neural networks and Modal Data

引用

EXPERIMENTAL MECHANICS 2010年第5期50卷 607-619页

作者： Jahani, K. Nobari, A. S. Univ Tabriz Fac Mech Engn Tabriz Iran Amirkabir Univ Technol Dept Aerosp Engn Tehran Iran

In this paper, the radial basis function neural networks (RBFNN) was applied to the problem of identifying dynamic Young's modulus and damping characteristic of a structural adhesive, using modal data. To identify Young's modulus from undamped model, an appropriate RBFNN using modal data (mode shape and natural frequency) in each mode is developed. Based on a previous work, in order to identify loss factor, two approaches adopted in the identification process. In the first one, a two stage RBFNN is developed. In stage I, Young's modulus is identified from undamped model and in stage II using the results of stage I an appropriate RBFNN is developed in each mode for identification of loss factor by implementing real parts of eigenvalues of damped model. In the second approach, a one stage RBFNN is developed using real and imaginary parts of eigenvalues of damped model to identify Young's moduli and loss factors simultaneously. The repeatability and consistency of the method is proved by repeating the identification process for several times. The validity of results is proved by comparing the results with those identified in a previous work.

关键词： radial basis function neural networks Adhesive Young's Modulus Damping Loss factor

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：