检索结果-内蒙古大学图书馆

2nd International conference on Big data, Computational Intelligence, and Applications, BDCIA 2024

作者： Qian, Xiaorui Cai, Rongyan Shen, Yimin Du, Songyan Chen, Xiaojun State Grid Fujian Marketing Service Center Fujian Fuzhou350000 China State Grid Fujian Electric Power Co. Ltd. Fujian Fuzhou350000 China

ISBN: (纸本)9781510689053

Considering that the current method cannot effectively analyze the complex electricity bill credit risk behavior when conducting electricity bill credit risk analysis, the accuracy of electricity bill credit risk analysis is not high and the risk control effect is not good. Therefore, an automatic analysis method of electricity bill credit risk that integrates external data labels and knowledge graphs is proposed. An ideal credit model of electricity bill credit risk is constructed, the electricity bill credit risk indicators are normalized, and the credit risk of electricity bill credit risk is evaluated by constructing an evaluation model. Combined with the frequency of risk data, the distribution characteristics of power credit risk are predicted. According to the arrangement of external data labels of power credit risk, the external data labels of power credit risk are generated. The knowledge structure of electricity bill credit risk data is mined by using knowledge graphs, and the distribution of electricity bill credit risk data is analyzed by combining graph theory. The principle design of electricity bill credit risk analysis is completed, and the automatic analysis of electricity bill credit risk is realized. The experimental results show that the proposed method has high precision and recall in electricity bill credit risk analysis, can effectively control electricity bill credit risk, provides strong support for risk control of power enterprises, and continuously promotes the intelligent and automated process of electricity bill credit risk management. © 2025 SPIE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A General Framework for Closed Loop Negative Feedback Multivariable Physiological control Systems: Existence, Uniqueness, and Stability of Homeostatic Equilibrium Points

引用

IEEE ACCESS 2025年 13卷 17630-17651页

作者： Procopio, Anna Tedesco, Annarita Regio, Fabrizio Lo Cesarelli, Giuseppe Donisi, Leandro Ricciardi, Carlo Merola, Alessio Ponsiglione, Alfonso Maria Romano, Maria Montefusco, Francesco Cosentino, Carlo Amato, Francesco Univ Magna Graeciadi Catanzaro Dept Expt & Clin Med I-88100 Catanzaro Italy Univ Naples Federico II Dept Publ Hlth I-80131 Naples Italy Univ Naples Federico II Dept Elect Engn & Informat Technol I-80125 Naples Italy Univ Naples Parthenope Engn Dept Naples Italy Univ Campania Luigi Vanvitelli Dept Adv Med & Surg Sci I-80138 Naples Italy Univ Napoli Parthenope Dept Econ Law Cybersecur & Sports Sci Naples Italy

The study of homeostatic equilibrium is a key concern in several fields, from physiology and biology to medicine and biomedical engineering. control theory approaches can provide effective strategies to model physiological control systems, helping in understanding the dynamics of bio- and physio-logical regulation processes. However, the intrinsic complexity of living systems makes it difficult to identify unified biomodels that can represent a wide variety of physiological systems. In this context, the present work proposes a general framework to model the dynamics and describe the behavior of a wide class of multivariable physiological control systems, from the molecular to the whole-organ scale. The framework adopts a structure based on a closed-loop topology taking into account multiple inputs and outputs and with the negative feedback action intrinsically embedded within the model. The development of such a general model has at least three important repercussions: the first concerns the possibility of better understanding the basic mechanisms common to many physiological systems;the second is to develop a common theoretical framework to enable effective approaches to the analysis and design of synthetic biological control systems;finally, the investigation of the structural properties of the model in a general context, allows a guided and simplified application to specific cases. To this regard, in this paper, the existence, possible uniqueness and stability properties of the homeostatic equilibrium points of the general model are investigated;the theoretical framework is then illustrated through two real-world case-studies: (i) the PI3K/AKT/mTOR pathway nonlinear dynamics, a critical regulator of cellular growth, proliferation, and survival;(ii) the control mechanism of the neuromuscular stretch reflex, among the prime triggers implicated in postural control. Results proved the capability of the proposed framework to capture the intricate dynamics of multivari

关键词： Physiology Biological system modeling control systems Biology Negative feedback Regulation Homeostasis process control Integrated circuit modeling Delays Multivariable physiological control systems neuromuscular stretch reflex cellular growth dynamics stability of homeostatic equilibrium

来源：评论

学校读者我要写书评

暂无评论

Low Complexity Byzantine-Resilient Federated Learning

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2025年 20卷 2051-2066页

作者： Gouissem, A. Hassanein, S. Abualsaud, K. Yaacoub, E. Mabrok, M. Abdallah, M. Khattab, T. Guizani, M. Univ Doha Sci & Technol Coll Comp & Informat Technol Doha Qatar Qatar Univ Dept Elect Engn IIPL Lab Doha Qatar Qatar Univ Dept Comp Sci & Engn Doha Qatar Qatar Univ Coll Arts & Sci Dept Math & Stat Doha Qatar Hamad Bin Khalifa Univ Coll Sci & Engn Div Informat & Comp Technol Doha Qatar Mohamed Bin Zayed Univ Artificial Intelligence Machine Learning Dept Abu Dhabi U Arab Emirates

Federated learning (FL) has gained attention for enabling efficient distributed learning while maintaining data privacy. However, the data privacy constraint reduces the transparency in the agents' model update making the learning process vulnerable to Byzantine attacks. In this paper, a mathematical proof is provided to show that when the traditional model-combining scheme is used, the model will eventually diverge to non-useful solutions in the presence of Byzantine agents independently from their number or their contributions. A low complexity norm-control based aggregation approach is also proposed and shown to converge to the optimal and sub-optimal solutions in the absence or presence of Byzantine nodes, respectively. Monte-Carlo simulations are also conducted to verify and validate the mathematical derivations and the efficiency of the proposed approach in protecting the FL model.

关键词： data models Computational modeling Mathematical models Training Convergence Accuracy data privacy Complexity theory Heuristic algorithms Distributed databases Federated learning distributed learning Byzantine attacks convergence analysis e-health

来源：评论

学校读者我要写书评

暂无评论

Monitoring, modeling, and forecasting long-term changes in coastal seawater quality due to climate change

引用

NATURE COMMUNICATIONS 2025年第1期16卷 1-10页

作者： Guan, Xianghong Huang, Hua Ke, Xiong Cheng, Xiaoqian Zhang, Heng Chen, Acong Qiu, Guanglei Wu, Haizhen Wei, Chaohai South China Univ Technol Sch Environm & Energy Guangzhou 510006 Peoples R China South China Univ Technol Sch Biol & Biol Engn Guangzhou 510006 Peoples R China South China Univ Technol Sch Environm & Energy Guangdong Prov Key Lab Solid Wastes Pollut Control Guangzhou 510006 Peoples R China

As climate change affects the physicochemical properties of coastal water, the resulting element re-exposure may override the emission reductions achieved by human pollution control efforts. Here, we conduct an analysis the water quality-climate effect over eight consecutive years from 2015 to 2022 along the South China coast combined with CMIP6 Scenario Model Intercomparison Project. Then we utilized a data-driven model to predict the concentrations of trace metals and nutrients over the next 80 years. It is suggested that the acidification process carries the risk of triggering the ocean's buffering mechanisms. During this alkalinity replenishment process, trace metals, such as Cd, Cr, Cu, Fe, Hg, Mn, Pb, and Zn, in the sediment are released into the water phase, along with Ca2+ and Mg2+. Here, the aim of this study is to show that the nexus of re-exposure-eutrophication-emission reduction with human activities and climate feedback, cannot be ignored in the pursuit of effective environmental governance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring cracking resistance in modified asphalt mixtures through a comparative assessment of mechanical behavior and performance screening indicators

引用

CONSTRUCTION AND BUILDING MATERIALS 2025年 464卷

作者： Seitllari, Aksel Virginia Mil Inst 413 Letcher Ave Lexington VA 24450 USA

Fatigue cracking is a prevalent distress, affecting the service life of asphalt pavements. Traditional methods for assessing fatigue resistance can be complex and time-consuming, making it essential to implement more proactive approaches during the mix design and/or quality control process. Screening tests, such as the semi-circular bending (SCB) test with the Illinois flexibility index (FI) variant, have gained traction as a viable alternative. Despite its potential, the FI is often shown to exhibit high variability and lacks sensitivity to certain mix design variables. These limitations have prompted alternative data analysis methodologies and performance indices to evaluate the cracking potential of asphalt concrete. This study presents a comprehensive evaluation of cracking resistance derived from the SCB test results, where multiple performance indicators, including fracture energy (Gf), flexibility index (FI), cracking resistance index (CRI), toughness index (TI), fracture strain tolerance (FST), and Nflex factor, were adopted. Four polymer- modified, dense-graded asphalt mixtures, varying in aggregate types, gradations, and design gyrations, were tested. The efficacy of selected performance criteria to capture the cracking susceptibility of asphalt mixtures, focusing on consistency and reliability, was assessed. While useful for screening exercises, monotonic tests and associated performance indices often overlook critical behaviors, such as stress relaxation, highlighting the need for methods like cyclic loading tests and viscoelastic modeling to improve performance predictions of asphalt mixtures. Consequently, a comparative approach was initiated by benchmarking the results obtained against established fatigue characterization methods like the uniaxial tension/compression (T/C) fatigue test and viscoelastic continuum damage (VECD) analysis in a controlled laboratory environment. Results revealed varying degrees of correlation between SCB-based indicators a

关键词： Cracking resistance Fatigue assessment Performance indices Modified asphalt mixtures Viscoelastic continnum damage Linear elastic analysis

来源：评论

学校读者我要写书评

暂无评论

High-Precision Rotor Position Estimation via Cascaded Model-Based and data-Driven Estimator: An Integrated Method

引用

IEEE INDUSTRIAL ELECTRONICS MAGAZINE 2025年

作者： Jin, Luhan Wang, Xueqing Lu, Linlin Ma, Yao Wang, Zheng Chinese Acad Sci Key Lab Opt Engn Chengdu 610209 Peoples R China Chinese Acad Sci Inst Opt & Elect Chengdu 610209 Peoples R China Univ Chinese Acad Sci Beijing 101408 Peoples R China Sichuan Univ Coll Elect Engn Chengdu 610065 Peoples R China Chinese Acad Sci Natl Key Lab Opt Field Manipulat Sci & Technol Chengdu 610209 Peoples R China Southeast Univ Sch Elect Engn Nanjing 210096 Peoples R China

Typical sensors for rotor position measurement are susceptible to environmental factors and may even cause reliability concerns during online operation. Thus, sensorless control becomes increasingly crucial in motor drives. To fulfill the precise position estimation of permanent magnet synchronous motors (PMSMs), a novel hybrid-driven position estimation method is proposed in this article. Instead of employing huge neural networks (NNs) for direct position estimation with a laborious offline training process, the preliminary position information is extracted from the designed model-based estimator in the proposed method and fed to the data-driven radial basis function (RBF) NN compensator to predict the position residuals for high-precision position estimation. For the convenience of practical application, an online training scheme based on the gradient descent method is designed for the learning of RBF compensator. Additionally, a domain-related compensation strategy is introduced to enhance the dynamic performance of the proposed method. By combining the respective strengths of model-based and data-driven methods, the proposed method significantly alleviates the parameter-tuning burden in the conventional model-based methods with enhanced estimation precision and addresses the high computational complexity in the data-driven methods with better generalization performance. Finally, real-time experiments are presented to verify the effectiveness and viability of the proposed method.

关键词： Estimation Power harmonic filters Harmonic analysis Rotors Training Observers Artificial neural networks Sensors Computational modeling Inverters

来源：评论

学校读者我要写书评

暂无评论

Construction of a Student Information Literacy Evaluation Model Based on BP Neural Network Algorithm

Construction of a Student Information Literacy Evaluation Mo...

引用

2024 International conference on Mechatronics and Intelligent control, ICMIC 2024

作者： Xu, Shan Shandong Institute of Commerce and Technology Shandong Province Jinan250103 China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

This article aims to construct and validate a student information literacy evaluation model based on the BP neural network algorithm. In the current information age, the information literacy of students is crucial for their academic success and future development. However, traditional evaluation methods often lack accuracy and comprehensiveness. To address this issue, we have designed an evaluation model based on BP neural network, which can comprehensively analyze student questionnaire survey data and learning behavior logs, providing a more accurate and comprehensive assessment of information literacy. We demonstrated the training and optimization process of the model through detailed experimental design, and demonstrated its effectiveness through performance evaluation. The experimental results show that the model performs well in performance indicators such as accuracy, recall, and F1 score, and is superior to traditional machine learning models. Finally, we discussed the limitations of the model and its potential applications in the field of education. This study provides a new perspective and method for utilizing advanced machine learning techniques for educational evaluation and decision-making. © 2025 SPIE.

关键词： data modeling Neural networks Machine learning Education and training Performance modeling Design data processing Evolutionary algorithms Neurons Online learning

来源：评论

学校读者我要写书评

暂无评论

Fluid pulsation excitation characterization and pipeline vibration response analysis

引用

MECHANICAL SYSTEMS AND SIGNAL processING 2025年 231卷

作者： Cao, Yiming Ma, Hui Guo, Xumin Chen, Weijiao Wang, Weiwei Zhao, Tianyu Lin, Junzhe Northeastern Univ Sch Mech Engn & Automat Shenyang 110819 Liaoning Peoples R China Northeastern Univ Key Lab Vibrat & Control Aeroprop Syst Minist Educ Shenyang 110819 Liaoning Peoples R China Northeastern Univ Sch Sci Shenyang 110819 Liaoning Peoples R China

Due to the influence of the hydraulic pump, the fluid medium in the pipeline is accompanied by strong periodic pressure pulsation, which is easy to induce large forced vibration in the clamppipeline system. Thus, studying the vibration characteristics of pipeline systems under fluid pulsation excitation is particularly important. The finite element method based on beam elements has distinct advantages in the modeling of spatial pipelines and complex boundaries. However, its application is often restricted due to its low computational efficiency and inaccuracy in handling fluid pulsation excitation loads. Therefore, in this paper, the measured pressure pulsation functions are taken as inputs, and the vibration response of the pipeline system under fluid pulsation excitation is solved through two-way fluid-structure interaction (FSI) analysis. The validity of the simulation is verified by comparing the results with the experimental data. On this basis, the fluid pulsation excitation forces at different nodes of the pipeline are extracted, and an in-depth analysis of the magnitude and phase distribution patterns of the excitation forces at each node is carried out. Finally, a characterization method of fluid pulsation excitation is proposed, which is based on the node excitation force fitted by two-way FSI analysis. The results indicate that the proposed fluid pulsation excitation expression can approximate the actual fluid pulsation excitation. The amplitude error between the simulation and experimental vibration responses can be controlled within an acceptable range. Specifically, the error under a pressure of 8 MPa is controlled within 20 %, which verifies the effectiveness of the proposed characterization method.

关键词： Pipeline system Finite element method Fluid pressure pulsation Fluid-structure interaction

来源：评论

学校读者我要写书评

暂无评论

Predictive Maintenance of Wire Electrical Discharge Machining Using Long Short-Term Memory Networks for Improved process control 20

Predictive Maintenance of Wire Electrical Discharge Machinin...

引用

20th CIRP conference on modeling of Machining Operations in Mons, CIRP CMMO 2025

作者： Kumar, Namadi Vinod Chakradhar, D. Department of Mechanical Engineering Indian Institute of Technology Palakkad Palakkad678623 India

Time series forecasting and anomaly detection are becoming essential in smart manufacturing for prognostics and health management of a machine, especially where traditional methods struggle with the analysis of high frequency data. This study uses Long Short-Term Memory (LSTM) networks for detecting and predicting anomalies in wire electrical discharge machining (WEDM), specifically focusing on events like no-sparking and wire breaks. In closed-loop forecasting continuous numerical predictions are challenging in high-frequency data analysis, so a centroid-based approach was chosen. This method simplifies forecasting by using representative feature values that highlight important class differences in the data. With this closed-loop LSTM and centroid approach, the model effectively forecasts machine states up to five seconds ahead;a useful time frame for detecting critical issues such as wire breakage and no sparking before they impact operations. The results show that this method, combined with LSTM ability to capture time patterns, can handle complex, shifting conditions in WEDM. This approach could improve productivity and reduce unexpected downtime in smart manufacturing, offering a practical and efficient way to monitor and predict machine conditions. © 2025 The Author(s).

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis and Fault Tolerant control Algorithm based on Neural Network in Modular Multi-level Converter (MMC) 3

Fault Diagnosis and Fault Tolerant Control Algorithm based o...

引用

3rd International conference on Electronics and Renewable Systems, ICEARS 2025

作者： Xie, Jun Qian, Xiaodong Huang, Qiong Anhui Vocational and Technical College Anhui Hefei230011 China

ISBN: (纸本)9798331509675

The state-of-the-art modulation strategy of MMC is closely related to the quality of its output voltage waveform and system loss, and is related to whether the entire MMC system can maintain efficient and stable operation. In fact, all multi-level modulation technologies can be applied in MMC systems. To deal with the challenges, this study proposes a novel neural network-based MMC fault diagnosis (FD) and fault-tolerant efficient control (FTEC) algorithm. First, initial step for the modeling is to conduct the comprehensive analysis of the MMC architecture characteristics and prone faults. In particular, considering the schemes of open circuit (OC) and short circuit (SC) related faults, a model based on recurrent neural network (RNN) is established to extract and classify fault features, and the network structure of deep learning is improved. At the same time, an improved CNN model is applied to process the voltage signal of MMC sub-module. In improved part, efficient Softmax function is used to realize the probability distribution of multi-fault classification. The entire fault detection and analysis framework includes the following points: data collection, data pre-processing, network parameter initialization, fault feature training and classification decision. The experiment uses a self-built MMC simulation model to test the performance. At same time, in specific experiment, high voltage and low voltage are displayed independently to achieve a comprehensive analysis. © 2025 IEEE.

关键词： Recurrent neural networks

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：