IEEE Transactions on Instrumentation and Measurement最新文献_第9页

Airborne Interferometric Cloud Particle Imager: Instrumentation and Applications to Icing Wind Tunnel 机载干涉云粒子成像仪：结冰风洞的仪器和应用

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-04-02 DOI: 10.1109/TIM.2025.3556826

Zhenyu Wang;XinHao Wang;Yingchun Wu;Botong Wen;Boyi Wang;Qiao Wang;Senyun Liu;Xiangdong Guo;Si Li;Mei Zheng;Xuecheng Wu

{"title":"Airborne Interferometric Cloud Particle Imager: Instrumentation and Applications to Icing Wind Tunnel","authors":"Zhenyu Wang;XinHao Wang;Yingchun Wu;Botong Wen;Boyi Wang;Qiao Wang;Senyun Liu;Xiangdong Guo;Si Li;Mei Zheng;Xuecheng Wu","doi":"10.1109/TIM.2025.3556826","DOIUrl":"https://doi.org/10.1109/TIM.2025.3556826","url":null,"abstract":"An instrument for characterizing icing cloud particles in wind tunnels is urgently needed to enhance the understanding of aircraft icing mechanisms. Measuring multiscale and multiphase icing cloud particles presents significant challenges, particularly under extreme environmental conditions. Interferometric particle imaging (IPI) has been established as an effective technique for analyzing multiphase cloud particles. In this work, an advanced instrument, Airborne Interferometric Cloud Particle Imager (AICPI), has been developed and validated by accurate calibration and a wide range of applications. AICPI’s optical-mechanical–electronic-thermal integrated design ensures reliable operation in icing wind tunnels. Validation experiments, conducted using a monodisperse droplet generator and a high-speed microscopic imaging system, confirmed that AICPI achieves a relative size measurement error of less than 5%. AICPI was deployed in one normal temperature wind tunnel and two industrial icing wind tunnels with test section dimensions ranging from <inline-formula> <tex-math>$0.6times 0.6$ </tex-math></inline-formula> m to <inline-formula> <tex-math>$3.0times 2.0$ </tex-math></inline-formula> m, wind speeds up to 50 m/s, and temperatures as low as <inline-formula> <tex-math>$- 14~^{circ }$ </tex-math></inline-formula>C. In practical applications, the AICPI measures particle sizes in the range of 10–<inline-formula> <tex-math>$200~mu $ </tex-math></inline-formula>m. Results from wind tunnel tests demonstrate the instrument’s feasibility for particle size measurement and phase discrimination in mixed-phase cloud fields.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-8"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Advanced Multiobjective Structure Optimization and Excitation Method of Metal Resonant Gyro 金属谐振陀螺的先进多目标结构优化与激励方法

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-04-02 DOI: 10.1109/TIM.2025.3557121

Ning Liu;Xuesi Yang;Zhong Su;Lianxi Xia;Taochen Gu;Zhenyu Zhao;Wensong Wang

{"title":"Advanced Multiobjective Structure Optimization and Excitation Method of Metal Resonant Gyro","authors":"Ning Liu;Xuesi Yang;Zhong Su;Lianxi Xia;Taochen Gu;Zhenyu Zhao;Wensong Wang","doi":"10.1109/TIM.2025.3557121","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557121","url":null,"abstract":"The metal resonant gyro is characterized by small size, low cost, and strong overload resistance, and shows broad application prospects in the field of inertial navigation. Currently, structural optimization methods of resonators are based on single-objective parameter optimization and fail to consider the comprehensive impact of multiple structural parameters on overall performance indices. In this article, a metal resonator with a tooth structure is designed based on thin shell theory and the energy loss principle. Using a finite element simulation method combined with multivariate linear regression equations, the linear influence of each structural parameter on overall performance is investigated. A multiobjective optimization model using three key indices as objective functions is constructed and optimized with the non-dominated sorting genetic algorithm II (NSGA-II) algorithm, providing a set of optimization parameters for subsequent research. It establishes equivalent mathematical models for different forms of electrostatic forces and verifies their validity using finite element simulations. Finally, the resonator’s response under different excitation forms is experimentally validated. Results show that the resonator exhibits optimal resonance under single-octave sinusoidal excitation: the four-wave belly oscillation pattern remains intact in driving mode with no frequency crosstalk. The resonant amplitude limit is 0.34 nm, significantly greater than under other excitation forms. The proposed method achieves comprehensive performance optimization of the metal resonator and provides a theoretical basis for selecting excitation forms in resonant gyros.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-13"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MCNN-VIO: A High-Accuracy Multi-Camera Visual-Inertial Odometry With Neural Networks 基于神经网络的高精度多相机视觉惯性里程计

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-04-02 DOI: 10.1109/TIM.2025.3557101

Shangru Yang;Yudong Liu;Shenwei Qu;Rizhi Dong;Boo Cheong Khoo;Sutthiphong Srigrarom;Qingjun Yang

{"title":"MCNN-VIO: A High-Accuracy Multi-Camera Visual-Inertial Odometry With Neural Networks","authors":"Shangru Yang;Yudong Liu;Shenwei Qu;Rizhi Dong;Boo Cheong Khoo;Sutthiphong Srigrarom;Qingjun Yang","doi":"10.1109/TIM.2025.3557101","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557101","url":null,"abstract":"Visual-inertial odometry (VIO) has the advantages of small size and low hardware cost as one of the methods for state estimation. Especially, the accuracy of the filtering-based system is high and its computational load is low. The multiple cameras configured in different directions are always applied to expand the observation scope so that the poor robustness of single-camera estimation and the abilities of object perception will be improved. However, multiple cameras will track more features, which not only increases calculation but also adds many features with large errors into programs, leading the low accuracy. In this article, a new framework, multi-camera with neural networks VIO (MCNN-VIO), based on multistate constraint Kalman filter (MSCKF) is proposed. It fuses two stereo cameras with non-overlapping fields of view (FoV) and an inertial measurement unit (IMU). The feature processing strategies between different cameras have been redesigned. The method is capable of using neural networks to intelligently select features in a variety of complex environments. Besides, a novel strategy of feature selection is proposed to obtain the closest poses to the true value for network training. This strategy can find the optimal solution in a limited number of stochastic and inclined combinations. The method was tested in scenes with both rich features and challenging darkness. The experimental results show that the method exhibits higher accuracy and better robustness compared to the multi-camera configuration of the conventional algorithm. Meanwhile, it maintains a competitive performance and low calculation cost compared to a single-camera version.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Target-to-Target Interaction Ghost Suppression Algorithm Based on Joint DoD and DoA Estimation 基于DoD和DoA联合估计的目标间交互鬼影抑制算法

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-04-02 DOI: 10.1109/TIM.2025.3557126

Haoran Zhao;Jiahui Chen;Zhihao Zhu;Yu Yao;Shisheng Guo;Guolong Cui;Lingjiang Kong

{"title":"Target-to-Target Interaction Ghost Suppression Algorithm Based on Joint DoD and DoA Estimation","authors":"Haoran Zhao;Jiahui Chen;Zhihao Zhu;Yu Yao;Shisheng Guo;Guolong Cui;Lingjiang Kong","doi":"10.1109/TIM.2025.3557126","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557126","url":null,"abstract":"In practical multitarget scenarios, the targets will interact with each other, yielding undesired multipath signals. These signals, appearing as “ghosts” in radar images, can severely hinder reliable target identification. In this article, we propose a novel approach for suppressing multipath ghosts induced by target-to-target interactions based on joint estimation of the Direction of Departure (DoD) and Direction of Arrival (DoA) using the multiple-input-multiple-output (MIMO) radar. Specifically, first, the multipath signal model for multitarget scenarios, which accounts for target-to-target interactions, is established. Then, based on the ellipse-cross-localization (ECL) method and geometric relationships, the unique features of ghosts, including defocusing, DoD, and DoA features, are explored. Inspired by these discriminative features, we perform joint DoD and DoA estimation on the echoes corresponding to candidate targets and introduce a new criterion based on the DoD-DoA heat maps for ghost identification. Following ghost identification, the ghost-free image is obtained by applying a weighting function to filter out the ghost echoes from the received signals. Finally, simulation and experimental results demonstrate that the proposed method achieves good performance in suppressing ghosts across different scenarios and varying signal-to-noise ratio (SNR) conditions.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-13"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning Task-Specific Sampling Strategy for Sparse-View CT Reconstruction 学习稀疏视图 CT 重构的特定任务采样策略

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-04-02 DOI: 10.1109/TIM.2025.3554318

Liutao Yang;Jiahao Huang;Yingying Fang;Angelica I Aviles-Rivero;Carola-Bibiane Schönlieb;Daoqiang Zhang;Guang Yang

{"title":"Learning Task-Specific Sampling Strategy for Sparse-View CT Reconstruction","authors":"Liutao Yang;Jiahao Huang;Yingying Fang;Angelica I Aviles-Rivero;Carola-Bibiane Schönlieb;Daoqiang Zhang;Guang Yang","doi":"10.1109/TIM.2025.3554318","DOIUrl":"https://doi.org/10.1109/TIM.2025.3554318","url":null,"abstract":"Sparse-view computed tomography (SVCT) offers low-dose and fast imaging but suffers from severe artifacts. Optimizing the sampling strategy is an essential approach to improving the imaging quality of SVCT. However, current methods typically optimize a universal sampling strategy for all types of scans, overlooking the fact that the optimal strategy may vary depending on the specific scanning task, whether it involves particular body scans (e.g., chest computed tomography (CT) scans) or downstream clinical applications (e.g., disease diagnosis). The optimal strategy for one scanning task may not perform as well when applied to other tasks. To address this problem, this article proposes a deep learning framework that learns task-specific sampling strategies with a multitask approach to train a unified reconstruction network while tailoring optimal sampling strategies for each individual task. Thus, a task-specific sampling strategy can be applied for each type of scan to improve the quality of SVCT imaging and further assist in the performance of downstream clinical usage. Extensive experiments across different scanning types provide validation for the effectiveness of task-specific sampling strategies in enhancing imaging quality. Experiments involving downstream tasks verify the clinical value of learned sampling strategies, as evidenced by notable improvements in downstream task performance. Furthermore, the utilization of a multitask framework with a shared reconstruction network facilitates deployment on current imaging devices with switchable task-specific modules, and allows for easily integrate new tasks without retraining the entire model.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Low-Cost Approach to Generate MV Distorted Voltage for VT Characterization up to 150 kHz 一种低成本产生MV失真电压的方法用于高达150khz的VT表征

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-04-02 DOI: 10.1109/TIM.2025.3557104

Palma Sara Letizia;Gabriella Crotti;Giovanni D’Avanzo;Antonio Delle Femine;Claudio Iodice;Mario Luiso;Domenico Giordano

{"title":"A Low-Cost Approach to Generate MV Distorted Voltage for VT Characterization up to 150 kHz","authors":"Palma Sara Letizia;Gabriella Crotti;Giovanni D’Avanzo;Antonio Delle Femine;Claudio Iodice;Mario Luiso;Domenico Giordano","doi":"10.1109/TIM.2025.3557104","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557104","url":null,"abstract":"The increase in disturbances at frequencies higher than 10 kHz in medium voltage (MV) grids has led to new metrological challenges related to the accurate characterization of instrument transformers (ITs), which serve as the primary element in the measurement chain for the monitoring of these disturbances. In this context, this article presents a simple architecture of a generation system for the characterization of MV voltage transformers (VTs) up to 150 kHz under realistic power system waveforms. It is able to generate a MV tone at power frequency and superimposed disturbances having reduced amplitude and higher frequency. Unlike other approaches recently discussed in scientific literature that need two separate voltage sources, the main advantage of the proposed solution is the use of a single source, by suitably compensating its systematic errors through a simple compensation method. As first application, the experimental tests related to the characterization of two commercial VTs (LPVT), an inductive VT and a low power VT, are discussed.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-9"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10947584","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Low-Cost High-Accuracy Online Electrochemical Impedance Spectroscopy Measurement Strategy for Fuel Cell Electric Vehicle Application 一种用于燃料电池汽车的低成本高精度在线电化学阻抗谱测量策略

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-04-02 DOI: 10.1109/TIM.2025.3557105

Yaxu Sun;Hanqing Wang;Ruihua Li;Bo Hu;Jian Fang;Yawen Lei;Zhongliang Li;Daniel Hissel

{"title":"A Low-Cost High-Accuracy Online Electrochemical Impedance Spectroscopy Measurement Strategy for Fuel Cell Electric Vehicle Application","authors":"Yaxu Sun;Hanqing Wang;Ruihua Li;Bo Hu;Jian Fang;Yawen Lei;Zhongliang Li;Daniel Hissel","doi":"10.1109/TIM.2025.3557105","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557105","url":null,"abstract":"This article proposes an improved online electrochemical impedance spectroscopy (EIS) measurement strategy for fuel cell electric vehicle (FCEV) applications. A two-phase interleaved boost converter (IBC) is designed to regulate the output power of a proton exchange membrane fuel cell (PEMFC). Then, the alternating disturbance signals are injected into the fuel cell via the controller of the direct current to direct current (dc/dc) converter without any additional equipment. An injection strategy based on bandwidth distinguishment is proposed to determine the frequency and injection position of disturbance signals. Furthermore, a closed-loop control strategy is introduced to stabilize the response signal’s amplitude at the desired value. The perturbations are effectively regulated to satisfy the signal-to-noise ratio requirement of sensors. Hence, a low-cost high-accuracy online EIS measurement solution is realized. The effectiveness of the approach is validated with a 1-kW converter prototype. The experimental results indicate that the proposed approach can achieve impedance detection with a relatively high degree of accuracy. When testing the setting varies, such as relative humidity fluctuation, the observed spectroscopy clearly demonstrates the noticeable variation in the internal electrochemical reaction.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Single-Channel Multifrequency Simultaneous Excitation System Using Bandpass Filter Circuit Modules for Lamb Wave-Based Damage Imaging 基于Lamb波损伤成像的带通滤波单通道多频同步激励系统

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-04-02 DOI: 10.1109/TIM.2025.3557099

Zhongjie Zhang;Liang Zeng;Tingzhong Xu;Chuang Zhang;Jiahui Yu

引用次数: 0

Effects of Shielding and Guarding Electrodes on Electrostatic-Force Balance Measurements in a Coaxial Cylindrical Capacitor 屏蔽和保护电极对同轴圆柱形电容器静力平衡测量的影响

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-04-02 DOI: 10.1109/TIM.2025.3557113

Kazuaki Fujita;Nobu-Hisa Kaneko;Atsushi Domae;Yasutaka Amagai;Takayasu Fujino;Naoki Kuramoto

{"title":"Effects of Shielding and Guarding Electrodes on Electrostatic-Force Balance Measurements in a Coaxial Cylindrical Capacitor","authors":"Kazuaki Fujita;Nobu-Hisa Kaneko;Atsushi Domae;Yasutaka Amagai;Takayasu Fujino;Naoki Kuramoto","doi":"10.1109/TIM.2025.3557113","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557113","url":null,"abstract":"This article reports on a numerical simulation using the finite-element method (FEM) on the effects of shielding and guarding electrodes of a vacuum-gap capacitor using coaxial cylindrical electrodes on the capacitance gradient measurements for an electrostatic-force balance apparatus. The electric field of the coaxial cylindrical capacitor with a shielding electrode was computed when the capacitor was open or semi-closed using a grounded-guarding electrode placed around the positive-terminal electrode. The capacitance and unwanted capacitive coefficients between the positive-terminal and grounded electrodes were calculated using the computed electric fields. The FEM results suggested that, under given conditions, there is an optimal overlapping length in the longitudinal direction of the coaxial cylindrical electrodes of the capacitor. This is based on the linearity of the capacitance gradient and parasitic capacitances that resulted in an error in the determination of the capacitance gradient using a three-terminal capacitance bridge in the electrostatic-force balance measurement. The FEM simulations also suggested that the use of a guarding electrode reduced the unwanted parasitic capacitive coefficients between the terminal and shielding electrodes, whereas the guarding electrode had no significant impact on the linearity of the capacitance gradient. Experiments were also conducted to confirm the consistency of the FEM results, which showed good agreement with the measurement uncertainties.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143840158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Multiscale Pooling Attention-Based Graph Attention Network for Remaining Useful Life Prediction 基于多尺度池化注意力的剩余使用寿命预测图网络

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-04-02 DOI: 10.1109/TIM.2025.3557109

Jiayin Tang;Yonghao Miao;Yu Xia;Qiuyang Zhou;Cai Yi

{"title":"A Multiscale Pooling Attention-Based Graph Attention Network for Remaining Useful Life Prediction","authors":"Jiayin Tang;Yonghao Miao;Yu Xia;Qiuyang Zhou;Cai Yi","doi":"10.1109/TIM.2025.3557109","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557109","url":null,"abstract":"Owing to the intricate spatial and temporal relationships inherent in data collected from multiple sensors, achieving precise predictions of remaining useful life (RUL) becomes a challenging task. Recently, deep learning (DL)-based approaches have made substantial advancements in RUL prediction. However, the traditional neural network-based methods have encountered some trouble in extracting spatial features. Graph neural network (GNN) has demonstrated the ability to effectively capture the spatial dependencies between multisensor data, but current GNN-based approaches cannot achieve much in terms of the spatial-temporal dependencies at various scales. Motivated by this, a multiscale pooling attention-based graph attention network (MSPA-GAT) is proposed. First, a multi-GATv2 network is designed for the spatial dependencies modeling, and a bidirectional long short-term memory (BiLSTM) network is used for modeling the temporal dependencies. Second, a multiscale pooling attention (MSPA) mechanism is constructed to highlight the local details of different scales and capture multilevel information. Finally, the effectiveness of the proposed MSPA-GAT to consider spatial and temporal dependencies is validated using two datasets. Moreover, the experimental results have shown that MSPA-GAT outperforms current state-of-the-art methods in RUL prediction.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-14"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143840155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0