检索结果-内蒙古大学图书馆

Battery pack SOC estimation by Noise Matrix Self Adjustment-Extended Kalman filter algorithm based on cloud data

JOURNAL OF ENERGY STORAGE 2024年 84卷

作者： Wang, Limei Gao, Kaixu Han, Jiyan Zhao, Xiuliang Liu, Liang Pan, Chaofeng Li, Guochun Wang, Yun Jiangsu Univ Automot Engn Res Inst Zhenjiang 212013 Peoples R China Jiangsu Univ Sch Automot & Traff Engn Zhenjiang 212013 Peoples R China Jiangsu Autoparts New Energy Technol Co Ltd Zhenjiang 212132 Peoples R China

Due to the limited computing capacity of the Battery Management System (BMS), the closed-loop estimation method represented by the Kalman filter algorithm is not really widely used, resulting in estimated errors in State of Charge (SOC). Given the strong computing power and large storage capacity of the cloud platform, a SOC estimation algorithm based on cloud data is proposed in the paper. Firstly, the impact of model parameter timevariability on SOC estimation is researched. Subsequently, the adaptability of the Noise Matrix Self AdjustmentExtended Kalman filter (NMSA-EKF) algorithm to the long data transmission period and low data transmission accuracy is discussed. Then, the adaptability of the model parameter identification algorithm is also analyzed. Furthermore, the model parameters are calculated by the combination of the direct method and Variable Forgetting Factor Recursive Least Square (VFFRLS) algorithm. Finally, the NMSA-EKF algorithm is used to estimate the SOC of the cloud-based discharging fragments. The results show that SOC estimation based on the NMSA-EKF algorithm has a high accuracy, and the overall relative error is within 3 %. The results also further validate the accuracy of the proposed parameter identification method.

关键词： Cloud data Parameter identification State of charge filter algorithm Noise Matrix Self Adjustment-Extended Kalman

来源：评论

学校读者我要写书评

暂无评论

Design of Dynamic Calf Weighing System Based on Moving-IIR filter algorithm

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2021年第2期16卷 1059-1069页

作者： Zhao, Wenwen Luo, Jinjun Li, Shenglin Qi, Jiangtao Meng, Hewei Li, Yaping Shihezi Univ Coll Elect Engn Shihezi 832000 Peoples R China Minist Agr & Rural Affairs Lab Northwest Agr Equipment Shihezi 832000 Peoples R China First Div Xinjiang Prod & Construct Corps Agr Technol Promot Stn Shihezi 832000 Peoples R China

In order to solve the problems of high intensity, low collecting efficiency, poor information real-time performance and low precision in the calf weighing process, a kind of dynamic calf weighing system was designed. It was based on moving-IIR by establishing a test platform to verify filter algorithm. The software MATLAB was applied to design the moving average filter algorithm, IIR filter algorithm and moving-IIR filter algorithm, respectively, to process and analyze the dynamic data collected in slow, violent and slow-violent states of calves. Test results showed that, the error rates of moving-IIR filter algorithm in slow, violent and slow-violent states of calves were within 1.12%, 0.32% and 2.82%, which were lower than that of moving-average filter algorithm and IIR filter algorithm. In slow state of calves, the moving-IIR filter was not very smooth. In violent and slow-violent states of calves, the standard deviations were within 1.1126 and 1.1520, showing significant smoothness. The study showed that, information collection system based on moving-IIR filter algorithm has fully taken the stability of moving filter and dynamic nature of IIR filter into consideration and had advantages of low error rate and high stability. Therefore, it can realize real time precise collection, display, storage and historical data query of weight information.

关键词： Calves Dynamic weighing filter algorithm System design

来源：评论

学校读者我要写书评

暂无评论

Collaborative Motivation Framework Leveraging Similar Interest Behavior in Semantic Web Applications

引用

INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION SYSTEMS 2025年第1期21卷

作者： Xu, Yanjun Tian, Chunqi Sun, Yaoru Zhang, Haodong Tongji Univ Shanghai Peoples R China

With the growth of web technology, the semantic web offers a promising framework for online knowledge collaboration. However, trust issues can undermine users' willingness to collaborate, reduce the frequency of interaction and collaboration efficiency. This paper introduces a super node-based trust management model designed to enhance semantic networks by linking nodes through trust relationships. The model exploits the synergistic incentives of similar interest behaviours to achieve a steady construction of trust relationships. We propose a similarity filtering algorithm that calculates the similarity to filter out false, misleading, or unfair information effectively. Through simulations, we compare our model with RRGRET, Surework, and community-based approaches, and the results show that our model has good network properties, while also resisting multiple malicious attacks and guaranteeing collaboration success. This research contributes to optimizing node relationships within semantic networks and strengthening network robustness against interference.

关键词： Semantic Network Knowledge Collaborative Trust Management Similar Interests Reputation System filter algorithm

来源：评论

学校读者我要写书评

暂无评论

Comparative study of a new semi-empirical model of the proton exchange membrane fuel cell for online prognostics applications

引用

ENERGY CONVERSION AND MANAGEMENT 2025年 331卷

作者： Perez, L. M. Jemei, Samir Boulon, Loic Ravey, Alexandre Kandidayeni, Mohsen Solano, Javier Univ Franche Comte FEMTO ST Inst CNRS FCLAB F-90000 Belfort France Univ Quebec Trois Rivieres Dept Elect & Comp Engn Hydrogen Res Inst Trois Rivieres PQ G8Z 4M3 Canada UTBM CNRS Inst FEMTO ST FCLAB F-90000 Belfort France European Inst Energy Res EIFER Emmy Noether Str 11 D-76131 Karlsruhe Germany

The prognostic of the proton exchange membrane fuel cell is a current topic of research. Consequently, the complexity of its degradation mechanisms has led to the development of semi-empirical models to improve predictive analysis. The accurate estimation of parameters for these models is a challenging task due to their multivariate, nonlinear, and complex characteristics. This work proposes anew semi-empirical model of the proton exchange membrane fuel cell and compares it with a widely used model in the literature. Unlike other similar studies, this comparison not only focuses on minimizing the sum of squared errors in relation to the experimental data but also evaluates the variation in the solution set and the computational effort involved. For both models, the unknown parameters are estimated using the recent Pelican Optimization algorithm. Four datasets are used to evaluate the development of the proposed model and the selected benchmark model. The first three datasets are open-access and well-recognized in academic literature, whereas the fourth dataset was obtained from a developed experimental test bench. The results show that the proposed model achieves high accuracy, with a mean absolute percentage error lower than 0.89% and the sum of squared errors below 0.9272 for all the studied scenarios. This model reduces parameter variation and decreases the relative standard deviation by over 12.7% compared to the utilized benchmark model for the first three datasets. Hence, the proposed model not only improves the precision of the estimated parameters without a notable increase in error but also reduces the computational load by at least 21.7% across all case studies.

关键词： Proton exchange membrane fuel cell Parameter estimation Pelican optimization algorithm Model identification Prognostic and degradation filter algorithm

来源：评论

学校读者我要写书评

暂无评论

Weight optimized unscented Kalman filter for degradation trend prediction of lithium-ion battery with error compensation strategy

引用

ENERGY 2022年第0期251卷 1页

作者： Zhang, Yong Tu, Lei Xue, Zhiwei Li, Sai Tian, Lulu Zheng, Xiujuan Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430081 Peoples R China Beijing Xiaoyu Yilian Technol Co Ltd Dept Video Cloud Media Platform Beijing 100080 Peoples R China Wuhan Inst Technol Sch Elect & Informat Engn Wuhan 430205 Peoples R China Univ Elect Sci & Technol China Sch Automat Engn Chengdu 611731 Peoples R China

Due to the inevitable degradation of Lithium-ion batteries (LIBs) during its lifetime, remaining useful life (RUL) prediction methods are adopted for ensuring the stable and safety operation of electrical equipment. To make up the deficiencies of single model-based or data-driven prediction approach, this paper proposes a new hybrid framework using a weight optimization unscented Kalman filter (WOUKF) and attention based bi-directional long short-term memory (BiLSTM-AM). To be specific, firstly, a Fourier model is proposed to describe the degradation of LIBs instead of the traditional double exponential model. Then, a WOUKF algorithm is designed to identify the model parameters efficiently even in the case of poor initialization. Next, the trends of prediction residual between the WOUKF and the true capacity is established by BiLSTM-AM, which is fed back to the WOUKF for updating model parameters during the prediction period. In addition, an error compensation scheme is developed to further improve prediction performance. Finally, the effectiveness of the proposed prognosis framework is verified on two battery datasets. The simulation results show that the proposed method has better prediction accuracy. The maximum root mean squared error (RMSE) and mean absolute error (MAE) of the proposed hybrid framework are 3.5% and 3%, respectively.(c) 2022 Elsevier Ltd. All rights reserved.

关键词： Remaining useful life prediction Weight optimization unscented Kalman filter algorithm Error compensation strategy Fourier degradation model Bi-directional long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A novel unsupervised adaptive density-based clustering filter for remaining useful life prediction of bearings

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2024年第12期35卷 126121-126121页

作者： Wang, Wei Zhou, Gongbo He, Zhenzhi Zhou, Ping Ma, Guoqing Yan, Xiaodong Ma, Tianbing China Univ Min & Technol Sch Mechatron Engn Jiangsu Key Lab Mine Mech & Elect Equipment Xuzhou Jiangsu Prov Peoples R China Jiangsu Normal Univ Sch Mech & Elect Engn Xuzhou Jiangsu Prov Peoples R China State Key Lab Min Response & Disaster Prevent & C Huainan 232000 Anhui Prov Peoples R China

Constructing the health indicator (HI) and predicting the remaining useful life (RUL) are essential steps in bearing health management. Some prediction methods depend on prior information about HIs, especially when these indicators are generated by deep learning models. However, acquiring such prior information can be challenging in practical applications. This paper introduces a novel unsupervised adaptive density-based clustering filter (UADCF) for RUL prediction of bearings, which operates without the need for prior knowledge. Firstly, a post-hoc interpretation HI model (PIHIM) is proposed to characterize the deep learning constructed HIs from the perspective of what the deep learning has done. Then, leveraging the classical density-based clustering algorithm, we introduce the UADCF for unsupervised estimation of model parameters, which can dynamically adjust density parameters based on the current conditions. Finally, we develop a prediction framework combining PIHIM and UADCF, enabling unsupervised RUL prediction of bearings. The experimental studies validate the effectiveness of the proposed method.

关键词： density-based spatial clustering filter algorithm remaining useful life prediction rolling bearing

来源：评论

学校读者我要写书评

暂无评论

filter-processing-assisted Fourier transform Raman spectroscopy for forensic discrimination lubricant machinery oils

引用

MICROCHEMICAL JOURNAL 2024年 204卷

作者： Zhu, Mi Wu, Ting Chen, Yaoqing Zhu, Hongjian Hunan Police Acad Sch Forens Sci Changsha 410138 Peoples R China Hunan Police Acad Inst Food & Environm & Drug Monitoring & Testing Changsha 410138 Peoples R China Changsha Publ Secur Bur Yuelu Branch Changsha 410207 Peoples R China

The primary objective of this study was to investigate the potential value of filtering algorithms in enhancing spectral model performance. 290 mechanical lubricants oils samples from various applications underwent measurement using Fourier transform Raman spectroscopy (FT -Raman). Subsequently, three discrimination models were developed employing C5.0, Bayes discriminant analysis, and support vector machine algorithms. The emphasis was on evaluating the efficacy of four filter algorithms -Fast Fourier Transform (FFT), Discrete Wavelet Transform (DWT), Finite Impulse Response (FIR), and Hilbert Transform (HT) -for enhancing model performance. Among these, the FFT filter-SVM model, DWT filter-SVM model, and FIR (low-pass or band -stop filter)-SVM model emerged as optimal choices for identification. These models demonstrated outstanding performance, achieving 100 % accuracy across all 290 samples. Modelling using FT -Raman and chemometrics offered a simpler, more robust, and valuable approach for identifying mechanical lubrication oils across diverse applications, exploiting the potential of filtering algorithms in forensic spectroscopy.

关键词： Fourier transform Raman spectroscopy Mechanical lubricants oils Chemometrics filter algorithm Forensic science

来源：评论

学校读者我要写书评

暂无评论

A Block-Scale FFT filter Based on Spatial Autocorrelation Features of Speckle Noise in SAR Image

引用

REMOTE SENSING 2023年第1期15卷 247-247页

作者： Wang, Xigang Meng, Zhiguo Chen, Si Feng, Zhuangzhuang Li, Xinbiao Guo, Tianhao Wang, Chunmei Zheng, Xingming Jilin Univ Coll Geoexplorat Sci & Technol Changchun 130026 Peoples R China Chinese Acad Sci Northeast Inst Geog & Agroecol Changchun 130102 Peoples R China Changchun Jingyuetan Remote Sensing Test Site Changchun 130102 Peoples R China Jilin Jianzhu Univ Sch Geomatics & Prospecting Engn Changchun 130118 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China

In order to reduce the impact of noise on the accuracy of inversion products based on SAR images, many filtering algorithms have been developed for noise reduction of SAR images. This paper proposes a filtering method based on the spatial autocorrelation feature of the block fast Fourier transform (BFFT). The method statistically analyses the autocorrelation length of speckle noise on Sentinel-1B images for different features and then constructs a relationship between autocorrelation length and noise period. After that, the size of the optimal FFT filtering window radius was determined based on the relationship between the noise period and the components in the image frequency domain. Finally, we filtered the SAR image within the parcels. We compared BFFT with six commonly used filtering methods. The results show that: (1) The noise periods of the soybean, corn, paddy, and water objects on the SAR image have little difference, with noise periods of 3.36, 3.17, 3.13, and 3.14 pixels on the VV polarization and 3.49, 3.17, 2.94, and 2.42 pixels on the VH polarization;(2) after the BFFT filtering in the land parcel area, the mean value of the backscattering coefficient (BC) kept constant, whilst at the same time, the standard deviation (STD) was reduced to half of that before the filtering and (3) the BFFT and NLM filtering methods have a better effect on noise reduction inside the block. The BFFT filtering method retains the variation trend between different regions within the block and preserves the block boundary's clarity. This study provides a new idea for refined image processing.

关键词： FFT BFFT SAR land parcel speckle noise filter algorithm spatial autocorrelation the speckle noise period

来源：评论

学校读者我要写书评

暂无评论

Automated technique for EEG signal processing to detect seizure with optimized Variable Gaussian filter and Fuzzy RBFELM classifier

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2022年第0期74卷 103450-103450页

作者： Harishvijey, A. Raja, J. Benadict Anna Univ Chennai Tamilnadu India PSNA Coll Engn & Technol Dindigul Tamilnadu India

Epileptic seizure in patients is detected from EEG signals with the use of automatic signal classification tech-niques. The accurate detection of epilepsy is essential to reduce the risk of seizure related complications. However the available automatic signal detection techniques give poor sensitivity and accuracy. In this work, an automatic signal classification method for detecting seizure from EEG signal is presented for obtaining good classification results. The proposed work improves the performance of detection using Variable Gaussian filter (VGF) with social spider algorithm (SSA) (SSA-VGF), Empirical Wavelet Transform (EWT) feature extraction method, K-Principal component analysis (K-PCA) based feature reduction and Fuzzy logic embedded RBF kernel based ELM algorithm (FRBFELM). The SSA-VGF method is used for removing noise artifacts from the given EEG signals. EWT is employed for feature extraction and the size of extracted features is reduced using K-PCA method. Finally the signals are classified as normal signals and epileptic signals using FRBFELM classifier. The perfor-mance of the proposed method is evaluated by measuring the metrics;PSNR, accuracy, sensitivity, and speci-ficity. The value of performance metrics obtained for the proposed work is 98.48%, 98.44% and 98.51%.

关键词： EEG signals Signal classification Noise removal filter algorithm Feature extraction Feature reduction Optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

FGCAN: filter-based Gated Contextual Attention Network for event detection

引用

KNOWLEDGE-BASED SYSTEMS 2021年 228卷 107294-107294页

作者： Yao, Shunyu Shuang, Kai Li, Rui Su, Sen Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Sci & Technol Commun Networks Lab Shijiazhuang Hebei Peoples R China

Contextual information is widely used in natural language processing and is important for event detection. How to make full use of contextual information is a challenging problem. Traditional event detection methods mainly use sentence-level information to identify event triggers and classify them into specific types. Event trigger is defined as the word or phrase that most clearly expresses an event occurrence. However, the information used for detecting events is usually spread across multiple sentences, and sentence-level information is often insufficient to resolve ambiguities for some types of events. In this paper, we propose a novel filter-based Gated Contextual Attention Network model called FGCAN, which is augmented with hierarchical contextualized representations to utilize both sentence-level and document-level information. In document level, we construct a gated contextual attention layer to extract document-level information by considering the relatedness between the current and other sentences and dynamically incorporate it into words. In this way, we can get cross-sentence clues without designing complex inference rules. In sentence level, we feed sentences into the classifier to get global information of them, and devise a rule-based filter algorithm to rectify the prediction of each word based on the probability ranking of the sentence labels, which is highly interpretable. These two mechanisms focusing on different scopes of contextual information can complement each other. The experimental results on the widely used ACE 2005 and KBP 2015 datasets show that our approach outperforms the state-of-the-art methods and the two components are effective in using contextual information. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Contextual information filter algorithm Neural network Event detection

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

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

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：