检索结果-内蒙古大学图书馆

Online Fault Diagnosis of Electromagnetic Launch System via Time Series Anomaly Detection

IEEE TRANSACTIONS ON PLASMA SCIENCE 2024年第8期52卷 3285-3293页

作者： Zeng, Delin Lu, Junyong Naval Univ Engn Natl Key Lab Electromagnet Energy Wuhan 430033 Peoples R China

As a special nonperiodic transient system, the electromagnetic launch system realizes the conversion of ultrahigh power of energy in a few seconds, which is harmful when the system fails. It is urgent to study the online fault diagnosis method of the system to stop the launch in time. Fault diagnosis based on online detection of abnormal waveform of time series in launch period is an important direction to solve the problems. Compared with traditional waveforms anomaly detection, the time series data points of electromagnetic launch system are very large, the time distortion is serious, and the abnormal waveform characteristics are not obvious. Therefore, the traditional methods can not realize online anomaly detection and location. This article analyzes the characteristics of electromagnetic launch time series and proposes a novel named FWSSP-TSAD anomaly detection method. To verify the performance of the proposed method, multiple discharge tests were conducted based on an electromagnetic launch system, and the obtained PFN voltage time series dataset was used as an algorithm input. The results show that the proposed algorithm accurately identifies all abnormal waveforms and extracts all abnormal sub waveforms, achieving fault diagnosis and localization. The average calculation time is less than the window time, which meets the requirements of online fault diagnosis.

关键词： Electromagnetics Time series analysis Anomaly detection Fault diagnosis Process control Electromagnetic scattering Transient analysis Electromagnetic launch system online fault diagnosis particle filter algorithm shapelets clustering time series anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Quantifying Streamflow Prediction Uncertainty Through Process-Aware Data-Driven Models

引用

HYDROLOGICAL PROCESSES 2024年第11期38卷

作者： Roy, Abhinanda Kasiviswanathan, K. S. Indian Inst Technol Roorkee Dept Water Resources Dev & Management Roorkee India Indian Inst Technol Roorkee Mehta Family Sch Data Sci & Artificial Intelligenc Roorkee India

The hydrological model simulation accompanied with uncertainty quantification helps enhance their overall reliability. Since uncertainty quantification including all the sources (input, model structure and parameter) is challenging, it is often limited to only addressing model parametric uncertainty, neglecting other uncertainty sources. This paper focuses on exploiting the potential of state-of-the-art data-driven models (or DDMs) in quantifying the prediction uncertainty of process-based hydrological models. This is achieved by integrating the robust predictive ability of the DDMs with the process understanding ability of the hydrological models. The Bayesian-based data assimilation (DA) technique is used to quantify uncertainty in process-based hydrological models. This is accomplished by choosing two DDMs, random forest algorithm (RF) and support vector machine (SVM), which are distinctly integrated with two process-based hydrological models: HBV and HyMOD. particle filter algorithm (PF) is chosen for uncertainty quantification. All these combinations led to four different process-aware DDMs: HBV-PF-RF, HBV-PF-SVM, HyMOD-PF-RF and HyMOD-PF-SVM. The assessment of these models on the Baitarani, Beas and Sunkoshi river basins exemplified an improvement in the accuracy of the daily streamflow simulations with a reduction in the prediction uncertainty across all the models for all the basins. For example, the nash-sutcliffe efficiency improved by 54.69% and 10.61% in calibration and validation of the Baitarani river basin, respectively. Equivalently, average bandwidth improved by 79.37% and 71.59%, respectively. This signified the (a) potential of the DDMs in quantifying and reducing the prediction uncertainty of the hydrological model simulations, (b) transferability of the model with an appreciable performance irrespective of the choice of basins having varying topography and climatology and (c) ability to perform significantly irrespective of different process-bas

关键词： data-driven models hydrological models particle filter algorithm predictive uncertainty streamflow simulation

来源：评论

学校读者我要写书评

暂无评论

An adaptive hybrid approach for online battery state of charge estimation

引用

JOURNAL OF ENERGY STORAGE 2025年 115卷

作者： Lin, Qiongbin Hong, Huiyang Huang, Ruochen Fan, Yuhang Chen, Jia Wang, Yaxiong Dan, Zhimin Fuzhou Univ Coll Elect Engn & Automat Fuzhou 350108 Peoples R China Fujian Engn Res Ctr High Energy Biatteries & New E Fuzhou 350108 Fujian Peoples R China Fuzhou Univ Coll Mech Engn & Automat Fuzhou 350108 Fujian Peoples R China Contemporary Amperex Technol Co Ltd Ningde 352100 Fujian Peoples R China

With the widespread adoption of electric vehicles (EVs) and energy storage in renewable energy systems, the use of lithium-ion batteries has increased significantly, making the battery safety performance a primary concern. The accurate state of charge (SOC) estimation can help mitigate the safety risks for the utilisation of EVs and renewable energy systems. Due to the dynamic and non-linear properties of batteries, an adaptive online SOC estimation is proposed in this paper by combining the online parameters estimation using equivalent circuit model (ECM) and the improved particle filter (PF) algorithm. It firstly deduces ECM parameters equations using bilinear transformation with the elimination of the variation caused by the ambient temperature. Then, the seeker optimization algorithm (SOA)-based fixed-length weighted least square (LS) algorithm is introduced to online estimate the battery parameters accurately. With the established ECM, the battery SOC can be estimated by the improved genetic algorithm (IGA) resampling-based PF algorithm, which effectively alleviates the particle degeneracy problem during the estimation, consequently, offering a better performance in SOC estimation. Both simulations and experiments have been conducted to validate the effectiveness of the proposed method. Compared with other existing algorithms, it shows that the proposed algorithm can accurately model the battery with the root mean squared error (RMSE) <0.1 % and achieve the real-time SOC estimation with less computation burden and high accuracy.

关键词： State of charge Equivalent circuit model Parameter estimation particle filter algorithm Genetic algorithm Batteries

来源：评论

学校读者我要写书评

暂无评论

Fuzzy energy management strategy for hybrid electric vehicles on battery state-of-charge estimation by particle filter

引用

SN APPLIED SCIENCES 2022年第10期4卷 256页

作者： Feng, Na Ma, Tiehua Chen, Changxin North Univ China State Key Lab Dynam Testing Technol Taiyuan 030051 Peoples R China North Univ China Sch Elect & Control Engn Taiyuan 030051 Peoples R China

The battery/ultracapacitor hybrid power supply system can solve the problems of high cost and short life of a single power system, and the energy management of hybrid power system has become a vital issue in the field of electric vehicles. In this paper, a fuzzy energy management strategy on the state-of-charge (SOC) estimation of power battery is proposed. particle filter (PF) algorithm is used to estimate SOC of power battery, then estimated result is regarded as the input variable of fuzzy energy management controller, and the energy distribution result is obtained after fuzzy logic operation. The simulation results show that the SOC estimation result of the PF algorithm is closer to the actual value of power battery SOC. When the SOC estimation result of PF is embedded into the fuzzy controller for joint simulation, it is found that the charge and discharge current, and SOC consumption of the power battery are reduced, which shows the algorithm's effectiveness. It also provides a specific reference value for the further study of the power supply control strategy of hybrid electric vehicles.

关键词： Hybrid electric vehicle (HEV) SOC estimation Energy management strategy Fuzzy controller particle filter algorithm

来源：评论

学校读者我要写书评

暂无评论

A new crankshaft bending fatigue test method: both residual life prediction and statistical analysis

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2023年第3期6卷 347-355页

作者： Liu, Jinyan Sun, Songsong Gong, Xiaolin Nanjing Forestry Univ Coll Automobile & Traff Engn Nanjing 210037 Peoples R China

In modern engineering application, for the metal engine parts such as the crankshafts and some other related objects, sufficient high-cycle fatigue strength is necessary to guarantee the system reliability during the working period. The traditional resonant crankshaft fatigue test bench can determine the load-life relationship of the given crankshaft directly, but the experiment process usually lasts tens of days, which may result in the large consumption of time. In this paper, the fatigue test speed was accelerated based on the prediction of the residual fatigue life during the experiment process. Then the system state-space equation was modified based on the theory of fracture mechanics to improve the accuracy of the predictions. Finally, the statistical analysis based on the predicted data was adopted to determine the fatigue limit load of the crankshaft. The main conclusion of this paper is that the combination of the particle filter algorithm and the dynamic response signal can predict the residual fatigue life of the crankshaft conveniently based on the modified sampling range, and thus is able to shorten the experiment process and has very wide popularization and application prospects in actual engineering.

关键词： Inherent frequency Crankshaft Bending fatigue Residual fatigue life prediction particle filter algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on adaptive selection method of radiation sources in passive radar based on GNSS signal

引用

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2023年第6期23卷 2825-2833页

作者： Tang, Huatao Cha, Hao Liu, Feng Tian, Bin Zuo, Lei Naval Univ Engn Coll Elect Engn Wuhan 430033 Hubei Peoples R China

Due to limitations in computing power, the passive radar based on GNSS signal may not be able to use all the GNSS signals, requiring to make signal selection. Based on CRLB, a new radiation sources adaptive selection method for passive radar is proposed. With the goal of minimizing the CRLB of GNSS signals and the number of GNSS signals as constraints, an adaptive selection model is established. Simulation experiments were conducted using the selection model and particle filter algorithm. Experimental results show that the calculation accuracy of this algorithm is slightly lower than the tracking results obtained using all six satellites, but the calculation time is greatly reduced, reducing the requirement for radar computing power.

关键词： Passive radar GNSS signal CRLB particle filter algorithm target tracking

来源：评论

学校读者我要写书评

暂无评论

A Nonlinear Suboptimal Fusion algorithm Weighted by Matrices Based on LMI and NARX 43

A Nonlinear Suboptimal Fusion Algorithm Weighted by Matrices...

引用

43rd Chinese Control Conference (CCC)

作者： Guo, Hangyan Hao, Gang Heilongjiang Univ Elect Engn Inst Harbin 150080 Peoples R China Key Lab Informat Fus Estimat & Detect Harbin 150080 Peoples R China

ISBN: (纸本)9798350366907;9789887581581

In order to solve the fusion estimation problem of multi-sensor with unknown cross-covariance, an improved suboptimal fusion algorithm weighted by matrices is proposed for nonlinear systems. Firstly, for significance of linear minimum variance, the simplest constraints based on fusion weighted by matrices are derived by Shure complement theorem. These constraints can ensure the positive definiteness of the fusion estimate error covariance, and the consistency of the proposed suboptimal fusion estimation. Further, a suboptimal fusion estimation weighted by matrices is proposed based on linear matrix inequality (LMI). Considering the time-consuming problem in the optimization process of LMI algorithm and the complexity of the nonlinear system, the optimal value is obtained by the nonlinear auto-regressive neural network with exogenous input (NARX). Finally, a nonlinear suboptimal fusion algorithm weighted by matrices based on LMI and NARX is proposed in combination with the particle filter algorithm (PF).

关键词： Suboptimal fusion algorithm weighted by matrices linear matrix inequality particle filter algorithm nonlinear auto-regressive neural network with exogenous input (NARX)

来源：评论

学校读者我要写书评

暂无评论

Research of STF-CPF-SLAM algorithm for Indoor Space Detection Mobile Robot 7

Research of STF-CPF-SLAM algorithm for Indoor Space Detectio...

引用

7th International Conference on Electronic Information Technology and Computer Engineering (EITCE)

作者： Xian, Ning Li, Danyi Shenyang Jianzhu Univ Sch Design & Art Shenyang Peoples R China

ISBN: (纸本)9798400708305

Aiming at the problem of indoor space detection mobile robots using particle filter SLAM algorithm, which may experience poor system stability and particle degeneracy after multiple iterations and updates, this paper proposes a Strong Tracking Cubature particle filter SLAM algorithm (STF-CPF-SLAM). Firstly, the Cubature Kalman (CKF) algorithm are used as the importance sampling functions of the particle filter algorithm (PF) to generate the mean and covariance distributions, simultaneously utilizing the fading factor of the Strong Tracking algorithm (STF) to compensate the system and enhance its robustness;Then, Strong Tracking Cubature particle filter algorithm is used to filter and fuse the observation data with the system model to obtain the optimized pose data of the mobile robot, thereby constructing a more accurate indoor space map;Finally, the effectiveness of the algorithm was verified through a mobile robot simulation platform. The simulation results show that the proposed algorithm reduces the error of simultaneous localization and mapping by 55.7% compared to traditional particle filter algorithms, verifying the feasibility and effectiveness of the algorithm, and improving the accuracy of indoor space exploration mobile robots in map construction. This algorithm provides a new reference for simultaneous localization and mapping of mobile robots.

关键词： Simultaneous Localization and Mapping (SLAM) Indoor Mobile Robot particle filter algorithm Strong Tracking filter

来源：评论

学校读者我要写书评

暂无评论

Study of SOH Estimation of EMU Battery Based on Improved particle filter 40

Study of SOH Estimation of EMU Battery Based on Improved Par...

引用

40th Chinese Control Conference (CCC)

作者： Niu, Buzhao Li, Liwei Xu, Chao Yu, Fei CRRC Qingdao Sifang Co Ltd Dept Qual Management Qingdao 266111 Shandong Peoples R China Qingdao Univ Weihai Innovat Inst Weihai 264200 Shandong Peoples R China Qingdao Univ Sch Elect Engn Qingdao 266071 Shandong Peoples R China China Railway Guangzhou Grp Co Ltd Guangzhou 511483 Guangdong Peoples R China

ISBN: (纸本)9789881563804

With lithium-ion batteries are more and more widely used in transportation, the estimation of battery state-of-health (SOH) is of great significance in the safe and reliable operation of battery management system and the reduction of maintenance cost. Based on the analysis of the traditional particle filter algorithm, the genetic factor of genetic algorithm (GA) is introduced into the particle filter and improved by adaptive mutation. In order to predict the SOH of lithium-ion battery, the health index (HI) is extracted from the measurable parameters of lithium-ion battery. The mapping model between HI index and SOH is established and applied to the observation of state space model. In this paper, a battery SOH estimation method based on improved particle filter algorithm is proposed. The experimental results show that the proposed method is superior to the traditional particle filter (PF) algorithm and has good accuracy in estimating the degradation process of lithium-ion batteries.

关键词： particle battery SOH estimation genetic algorithm particle filter algorithm health indicator

来源：评论

学校读者我要写书评

暂无评论

Night vehicle target recognition based on fuzzy particle filter

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2020年第4期38卷 3707-3716页

作者： Wang, Pin Fan, En Wang, Peng Shenzhen Polytech Sch Mech & Elect Engn Shenzhen Guangdong Peoples R China Shenzhen Polytech Sch Artificial Intelligence Shenzhen Guangdong Peoples R China Chinese Acad Sci Garden Ctr South China Bot Garden Guangzhou Guangdong Peoples R China

All along, the identification of night-driving safety car features is a major research direction in the field of intelligent traffic management, with a wide range of applications and development space, and these identification technologies include theoretical knowledge and important theoretical research in many fields. Due to the interference of lights and other light sources, the gray value of the background area also changes frequently. A common method during the day is to detect these background areas as moving vehicles, which greatly reduces the detection accuracy. The most reliable information at night is the headlights. If the light can be accurately detected and other sources are excluded, accurate detection can be performed and tracking accuracy can be guaranteed. Vehicle safety assisted driving technology is one of the main research directions of intelligent transportation systems. It mainly uses computer technology, sensor technology and communication technology to collect and analyze the state information of roads, other vehicles and drivers. Provide advice and warnings to the driver before reaching the danger, determine current traffic conditions and avoid traffic accidents in advance. This paper studies some problems of night vehicle target recognition and detection, mainly the division of target and background, and the classification and recognition of target extraction. To solve these problems, a particle filter algorithm is introduced to introduce nonlinear statistics. The fuzzy theory is introduced to classify the video processed by the particle filter algorithm. The target recognition is realized by the method, and the purpose of identifying the night vehicle target is achieved. Comparative experimental analysis shows that this method is more accurate and powerful than the common target recognition algorithm and can be applied to real scenes.

关键词： Night vehicle recognition particle filter algorithm nonlinear statistics fuzzy clustering

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：