检索结果-内蒙古大学图书馆

From Static and Dynamic Perspectives:A Survey on Historical data Benchmarks of Control Performance Monitoring

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 300-316页

作者： Pengyu Song Jie Wang Chunhui Zhao Biao Huang the State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University IEEE the Department of Chemical and Materials Engineering University of Alberta

In recent decades, control performance monitoring(CPM) has experienced remarkable progress in research and industrial applications. While CPM research has been investigated using various benchmarks, the historical data benchmark(HIS) has garnered the most attention due to its practicality and effectiveness. However, existing CPM reviews usually focus on the theoretical benchmark, and there is a lack of an in-depth review that thoroughly explores HIS-based methods. In this article, a comprehensive overview of HIS-based CPM is provided. First, we provide a novel static-dynamic perspective on data-level manifestations of control performance underlying typical controller capacities including regulation and servo: static and dynamic properties. The static property portrays time-independent variability in system output, and the dynamic property describes temporal behavior driven by closed-loop feedback. Accordingly,existing HIS-based CPM approaches and their intrinsic motivations are classified and analyzed from these two ***, two mainstream solutions for CPM methods are summarized, including static analysis and dynamic analysis,which match data-driven techniques with actual controlling behavior. Furthermore, this paper also points out various opportunities and challenges faced in CPM for modern industry and provides promising directions in the context of artificial intelligence for inspiring future research.

关键词： Control performance monitoring (CPM) data-driven method historical data benchmark (HIS) industrial process performance index static and dynamic analysis

来源：评论

学校读者我要写书评

暂无评论

A data-driven Time-Synchronization method to Convert Power Quality Waveform Measurements into Synchro-Waveforms

A Data-Driven Time-Synchronization Method to Convert Power Q...

引用

International Conference on Smart Grid Synchronized Measurements and Analytics (SGSMA)

作者： Ye, Zong-Jhen Mohsenian-Rad, Hamed Univ Calif Riverside Riverside CA 92521 USA

ISBN: (纸本)9798350312874;9798350312881

Synchronized waveform measurements, also known as synchro-waveforms, are gaining increasing attention in advanced power systems monitoring in recent years. However, there is a major gap in this field in practice. Although many utilities do have an existing infrastructure to measure voltage and current waveforms, such as by using conventional power quality sensors, those existing waveform measurements are not time-synchronized. In this paper, we propose novel methods to achieve data-driven time-synchronization among the conventional power quality sensors solely based on the analysis of the time-series of waveform measurements using statistical and optimization techniques. This will enable utilities to take advantage of the emerging applications of synchro-waveforms without the need to replace or retrofit their existing sensors. Experimental results confirm the high performance of the proposed methods.

关键词： Synchro-waveforms synchronized power system waveforms real-world data power quality sensors data-driven method time synchronization statistical analysis optimization

来源：评论

学校读者我要写书评

暂无评论

data-driven control synthesis for discrete-time semi-Markov jump systems

引用

JOURNAL OF THE FRANKLIN INSTITUTE 2025年第6期362卷

作者： Niu, Huawei Yang, Liu Li, Zhicheng Wang, Yang Harbin Univ Sci & Technol Dept Automat 52 Xuefu St Harbin 150080 Heilongjiang Peoples R China Shenzhen Polytech Univ IoT Res Inst 7098 Liuxian St Shenzhen 518055 Guangdong Peoples R China

In discrete-time semi-Markov jump systems, the system matrix for each subsystem is usually determined by the system identification method. For such systems, a large amount of data and computation are generally required to obtain system parameters close to the real ones. This method has a lot of difficulties in practical applications, especially when there are too many subsystems. In contrast, the data-driven method can skip the system identification step and directly design the controller based on the input and output data. Therefore, the data- driven method is investigated to solve the control problem of discrete-time semi-Markov jump systems. Firstly, a data model for discrete-time semi-Markov hopping systems is proposed. Secondly, the controller design method for the semi-Markov jump system with known and partly unknown transition probabilities is carried out using Lyapunov functions. Thirdly, for the practical situation, the time when the jump occurs is unknown;a new algorithm for mode estimation and the application conditions of this algorithm are given. Finally, a discrete-time semi-Markov jump system is constructed with the car model as an example to verify the effectiveness of the proposed method.

关键词： data-driven method Discrete-time semi-Markov jump system Semi-Markov chain Lyapunov function

来源：评论

学校读者我要写书评

暂无评论

Robustness of data-driven Approaches in Limited Angle Tomography

引用

SIAM JOURNAL ON IMAGING SCIENCES 2025年第1期18卷 345-358页

作者： Wang, Yiran Zhong, Yimin Emory Univ Dept Math Atlanta GA 30322 USA Auburn Univ Dept Math & Stat Auburn AL 36830 USA

The limited angle Radon transform is notoriously difficult to invert due to its ill-posedness. In this work, we give a mathematical explanation that data-driven approaches can stably reconstruct more information compared to traditional methods like filtered back-projection. In addition, we use experiments based on the U-Net neural network to validate our theory.

关键词： limited angle tomography data-driven method stablity Radon transform inverse problem

来源：评论

学校读者我要写书评

暂无评论

High-Resolution Real-Time Power Systems State Estimation: A Combined Physics-Embedded and data-driven Perspective

引用

IEEE TRANSACTIONS ON POWER SYSTEMS 2025年第2期40卷 1532-1544页

作者： Hu, Jianxiong Wang, Qi Ye, Yujian Tang, Yi Southeast Univ Sch Elect Engn Nanjing 210096 Peoples R China

Real-time perception of the power system operating state with high resolution is essential for enabling online dynamic security assessment. However, challenges associated with limited redundant measurements, dynamic model complexity and balancing state and non-state variables' accuracy hinder conventional model-driven and data-driven state estimation (SE) methods from delivering real-time states with high temporal-spatial precision. This paper proposes a novel physics-embedded and data-driven SE framework. By incorporating physics knowledge into both SE model development and training, this framework systematically bolsters previous high-resolution data-driven SE framework. By utilizing the physics model to translate hybrid measurements into node features and provide recent system state, the multi-head graph attention network is employed to extract spatial features, correcting discrepancies between the current and recent states through a Residual Network. To enhance accuracy of both state and non-state variables, the SE model undergoes training by a novel physics-embedded training method. This approach adaptively adjusts the weighting of state and non-state variables in the loss function, ultimately enhancing their estimation accuracy. Case studies verify its superior performance in terms of accuracy, efficiency, scalability and robustness on the IEEE 39-bus and 118-bus test systems. Furthermore, its advantages compared to traditional data-driven methods are proved theoretically in this paper.

关键词： Context modeling Training Accuracy Feature extraction Real-time systems Power system dynamics Power measurement data-driven method multi-heads graph attention network physics-embedded deep learning state estimation

来源：评论

学校读者我要写书评

暂无评论

Remaining useful life prediction for vehicle-oriented PEMFCs based on organic gray neural network considering the influence of dual energy source synergy

引用

ENERGY 2025年 322卷

作者： Yang, Jibin Chen, Li Zhang, Bo Zhang, Han Chen, Bo Wu, Xiaohua Deng, Pengyi Xu, Xiaohui Xihua Univ Sch Automobile & Transportat Vehicle Measurement Control Prov Engn Res Ctr New Energy Vehicle Intelligent C Chengdu 610039 Sichuan Peoples R China Xihua Univ Prov Engn Res Ctr New Energy Vehicle Intelligent C Sch Automobile & Transportat Safety Key Lab Sichuan Prov Chengdu 610039 Peoples R China CRRC Ind Acad Co Ltd Beijing 100070 Peoples R China Changzhou ECTEK Automot Elect Syst Co Ltd Changzhou 213000 Peoples R China Xihua Univ Yibin Inst Yibin 644000 Peoples R China

Accurately predicting the remaining useful life (RUL) of the fuel cell is essential for effective prognostics and health management of vehicle-oriented fuel cells. Herein, the synergistic influences of proton-exchange membrane fuel cells (PEMFCs) and batteries as dual energy sources for a city bus are considered to develop a datadriven method for predicting the RUL of vehicle-oriented PEMFCs under real-world traffic conditions. First, gray relational analysis is applied to extract relevant features as inputs for a data-driven model. Then, the Pauta criterion and wavelet threshold method are employed to correct gross errors and denoise the data acquired from real-world scenarios. Finally, an organic gray neural network model (OGNNM), which combines four gray models and a backpropagation neural network and uses the output voltage of the PEMFC as a health indicator, is improved to incorporate the battery state of charge (SOC), hydrogen tank pressure, as well as the stack temperature, output voltage, output current, and hydrogen consumption rate of the PEMFC as inputs for the RUL prediction of PEMFCs. The improved OGNNM is validated against two datasets obtained under real-world traffic conditions, and the results demonstrate its high prediction accuracy, surpassing that achieved when the influence of the battery SOC is neglected.

关键词： Proton-exchange membrane fuel cell Remaining useful life data-driven method Dual energy source Gray model Artificial neural network

来源：评论

学校读者我要写书评

暂无评论

data-driven model identification and control of the quasi-zero-stiffness system

引用

NONLINEAR DYNAMICS 2025年第5期113卷 3999-4013页

作者： Jiang, Jiyuan Tang, Jie Sun, Ke Chen, Huatao Li, Yinghui Cao, Dengqing Southwest Jiaotong Univ Sch Mech Engn Chengdu 610097 Peoples R China Shandong Univ Technol Sch Math & Stat Zibo 255000 Peoples R China Harbin Inst Technol Sch Astronaut Harbin 150001 Peoples R China

Nonlinear vibraion isolation technique is widely employed for vibration suppression. An identification-control integrated method based on data-driven approaches is proposed for solving the optimal control law of a nonlinear time-continuous dynamic system. A dynamic surrogate model of the quasi-zero-stiffness (QZS) vibration isolation system is established by using an identification algorithm combined physical information neural network and Runge-Kutta method with the input and output signals of the original model. Two approximate optimal controllers are trained through the particle swarm optimization with 'loser-out' skill and the twin delayed deep deterministic policy gradient (TD3) in the sense of a self-defined objective function, where controllers communicate with the dynamic surrogate model during the training process. Then, the comprehensive performance in the condition of variable load and Gaussian noise excitation, and the displacement transmissibility are tested on the original model. The results show that the identified surrogate model can accurately reproduce the dynamic characteristics of the original model and the trained controllers are able to accomplish the control tasks successfully with a certain adaptability, further enhancing the low-frequency vibration isolation of the QZS isolator.

关键词： Active quasi-zero-stiffness isolation Physical information neural network (PINN) Particle swarm optimization (PSO) Twin delayed deep deterministic policy gradient (TD3) data-driven method

来源：评论

学校读者我要写书评

暂无评论

data-driven climate resilience assessment for distributed energy systems using diffusion transformer and polynomial expansions

引用

APPLIED ENERGY 2025年 380卷

作者： He, Jiaming Tan, Qinliang Lv, Hanyu North China Elect Power Univ Sch Econ & Management Beijing Peoples R China Beijing Key Lab New Energy & Low Carbon Dev Beijing Peoples R China Res Ctr Beijing Energy Dev Beijing Peoples R China

A growing consensus is reaching that climate mitigation measures could fail to reach a sustainable future without immediate counterparts on climate adaptation, especially for global power systems driven by increasing share of renewable energy. A reasonable assessment procedure on the impact of arbitrary climate conditions should be studied before necessary countermeasures could be done. This paper concentrates on distributed energy systems with distributed renewable generators and studies how to quantitatively assess their climate resilience degrees for the first time. A data-driven diffusion transformer model is suggested to generate any climate scenarios according to both prior feature variables and historical climate datasets. Then, the interactive mechanisms between climate change and distributed energy system operations are analyzed. And three quantitative capacity credit criteria are proposed to measure system climate resilience degrees. Moreover, polynomial expansions yield an alternative model to alleviate the burden of replicative computations during criteria solutions. Case study applies historical climate data from Zhangbei, China. Results indicate that 1) the proposed diffusion transformer is capable of up to 20 % fluctuations tolerance of subjective feature expectations;2) nominal capacity of renewable energy and hydrogen storage are closely related with climate resilience degrees;3) third order polynomial expansion model estimates climate resilience results safely with R2 over 98.4 %;4) practical policy recommendations are suggested to combat the impact of climate changes on distributed energy systems.

关键词： Climate resilience Distributed energy system Capacity credit Diffusion transformer Polynomial expansions data-driven method

来源：评论

学校读者我要写书评

暂无评论

Fabrication-Specific Simulation of Mn-Zn Ferrite Core-Loss for Machine Learning-Based Surrogate Modeling With Limited Experimental data

引用

IEEE TRANSACTIONS ON POWER ELECTRONICS 2025年第1期40卷 1519-1531页

作者： Choi, Minwook Park, Soyeon Jang, Eunyoung Ouk, Minae Park, Kwangho Lee, Sangwon Noh, Gunwoo Korea Univ Sch Mech Engn Computat Mech & Design Optimizat Lab Seoul 02792 South Korea LG Innotek Co Ltd Devices & Mat Lab R&D Ctr Seoul 07796 South Korea

Mn-Zn ferrite is widely used as a core material in power electronic applications. However, core-loss modeling is challenging owing to the complexity of core-loss mechanisms and associated factors. The scarcity of experimental data is another significant impediment to the development of Mn-Zn ferrites. In this study, we propose a novel data-driven framework to construct an effective machine learning (ML) based surrogate model for estimating the core-loss of Mn-Zn ferrites. We developed a fabrication-specific finite element analysis model, simulating the experimental results of fabricated Mn-Zn ferrites, to generate simulation-driven data for expanding the training dataset. We considered various ML techniques for material property estimations in the fabrication-specific simulation and core-loss calculations. A case study using six limited experimental datasets with sample sizes of 3, 6, 8, 12, 20, and 30 showed that the proposed ML-based surrogate model can estimate core-loss with an accuracy of approximately 91.78%, a 17% increase in accuracy compared to the Steinmetz equation-based model. With the inclusion of the fabrication-specific simulation data, the accuracy of the ML-based surrogate model improved more rapidly as the amount of experimental data increased, and the models exhibited enhanced converged accuracy. Notably, the accuracy of each surrogate model was significantly enhanced for a sample size of less than 8, resulting in an improvement of approximately 35%.

关键词： Ferrites data models Accuracy Mathematical models Transformer cores Fabrication Magnetic properties Core-loss data-driven method machine learning Mn-Zn ferrite surrogate model

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis for Electric Drives Using Averagely Pooled and Downsampled data Fusion on Embedded Systems

引用

IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS 2025年第1期13卷 1224-1241页

作者： Shim, Jaehoon Cheol Lim, Gyu Lee, Sangwon Ha, Jung-Ik Samsung Elect Co Ltd Yongin 17113 South Korea Seoul Natl Univ Dept Elect & Comp Engn Seoul 08826 South Korea Seoul Natl Univ Elect Power Res Inst Seoul 08826 South Korea Southern Methodist Univ Dept Mech Engn Dallas TX 75205 USA

This study introduces a data-driven approach for diagnosing faults in electric drive systems on embedded systems. The method is designed to diagnose current Hall sensor offset, scale errors, and power switch open faults without the need for additional sensors or external computing resources. The proposed approach addresses three key points. First, it identifies and suggests data types in electric drive systems that are rich in fault-related information. Additionally, it uses statistical analysis to propose an effective fusion method for the input data types to create a diagnostic model among the various candidates. Second, a downsampling method utilizing average pooling (AP) is introduced to effectively sample data from the large volume of raw data processed by the digital signal processor (DSP), preserving essential information while reducing data size. Finally, a diagnostic scheme employing a neural network (NN)-based classifier is proposed to accurately diagnose faults using the downsampled data. The proposed method's effectiveness, from sampling to diagnosis, is demonstrated through both analytical and statistical validation. Furthermore, real-time diagnostic results are presented using the TMS320F28379S DSP.

关键词： Feature extraction Fault diagnosis data models data integration Sampling methods Digital signal processors Switches Embedded systems Analytical models Uncertainty data-driven method data fusion digital signal processor (DSP) downsampling electric drive fault diagnosis neural network (NN)

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：