ieeexplore最新文献_第9页

State of Health Estimation of Lithium-Ion Batteries Based on Stacked-LSTM Transfer Learning With Bayesian Optimization and Multiple Features 基于贝叶斯优化和多重特征的堆叠-LSTM 转移学习的锂离子电池健康状况评估

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-10-08 DOI: 10.1109/JSEN.2024.3472648

Liangliang Wei;Yiwen Sun;Qi Diao;Hongzhang Xu;Xiaojun Tan;Yuqian Fan

{"title":"State of Health Estimation of Lithium-Ion Batteries Based on Stacked-LSTM Transfer Learning With Bayesian Optimization and Multiple Features","authors":"Liangliang Wei;Yiwen Sun;Qi Diao;Hongzhang Xu;Xiaojun Tan;Yuqian Fan","doi":"10.1109/JSEN.2024.3472648","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3472648","url":null,"abstract":"It is critical to accurately estimate the state of health (SOH) to ensure the safe and efficient operation of lithium-ion batteries. To reduce the training amounts of existing data-driven methods, the transfer learning (TL) method has attracted more attention. However, most previous studies lack validation with different battery types and working conditions. Furthermore, the shared knowledge just relies on raw current and voltage data, resulting in insufficient accuracy. This article proposes a stacked-long short-term memory (LSTM) TL method based on Bayesian optimization (BO-Stacked-LSTM), which integrates multiple features to estimate SOH. By improving the structure of the BO-Stacked-LSTM networks and the fine-tuning strategy of TL, as well as employing a Bayesian optimization (BO) algorithm to optimize hyperparameters, the proposed method can achieve accurate SOH estimation. Experimental results demonstrate that it just requires a small quantity of target dataset to accurately estimate SOH on the target dataset. Furthermore, experiments were performed on three different lithium-ion battery datasets, to validate the effectiveness.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"24 22","pages":"37607-37619"},"PeriodicalIF":4.3,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dual-Actor Critic Adaptive Energy Management Method for EH-WSN Based on Battery Energy Neutral Operation 基于电池能量中性运行的 EH-WSN 双矢量自适应能量管理方法

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-10-08 DOI: 10.1109/JSEN.2024.3472089

Shuhua Yuan;Yongqi Ge;Xin Chen;Yalin Wang;Rui Liu;Jintao Gao

{"title":"Dual-Actor Critic Adaptive Energy Management Method for EH-WSN Based on Battery Energy Neutral Operation","authors":"Shuhua Yuan;Yongqi Ge;Xin Chen;Yalin Wang;Rui Liu;Jintao Gao","doi":"10.1109/JSEN.2024.3472089","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3472089","url":null,"abstract":"Energy harvesting wireless sensor nodes collect energy in a nonlinear dynamic change, resulting in low ability to dynamically match the collected and consumed energy of the node in the process of maintaining energy neutral operation (ENO).To address this problem, the concept of battery ENO (BENO) is proposed by analyzing the battery energy buffer characteristics, and the dual-actor critic energy harvesting wireless sensor node adaptive energy management (DAC) method is proposed based on BENO. The method designs a dual-actor critic structure, senses ENO through the battery energy neutral value, and dynamically adjusts the duty cycle based on this value, in order to achieve the purpose of improving the ability of dynamically matching the collected energy with the consumed energy. The experiments are carried out on three datasets with different energy harvesting capabilities, and compared and analyzed with three classical algorithms, RLman, AQL and FQL. The experimental results show that compared with the other three classical algorithms, DAC sacrifices a small amount of duty cycle, but effectively improves the stability of battery energy, and improves the energy utilization and ENO performance. The BENO concept and the DAC methodology can provide guidance and references for the research of energy management in energy-harvesting wireless sensor nodes.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"24 22","pages":"38466-38478"},"PeriodicalIF":4.3,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Toward Noncontact Muscle Activity Estimation Using FMCW Radar 利用 FMCW 雷达实现非接触式肌肉活动估算

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-10-08 DOI: 10.1109/JSEN.2024.3472571

Kukhokuhle Tsengwa;Stephen Paine;Fred Nicolls;Yumna Albertus;Amir Patel

{"title":"Toward Noncontact Muscle Activity Estimation Using FMCW Radar","authors":"Kukhokuhle Tsengwa;Stephen Paine;Fred Nicolls;Yumna Albertus;Amir Patel","doi":"10.1109/JSEN.2024.3472571","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3472571","url":null,"abstract":"Surface electromyography (sEMG) and ultrasound-based sonomyography (SMG) are established muscle activity monitoring techniques. However, both modalities require contact with the skin and are thus potentially uncomfortable and time-consuming to use. In this article, we propose a novel noncontact muscle activity monitoring approach that measures the muscle deformation signal using a frequency-modulated continuous wave (FMCW) mmWave radar which we call radiomyography (RMG). The RMG signal is a specific sequence of phase samples in the radar return, obtained through a series of operations: range bin selection, dc offset correction, arctangent demodulation, and phase unwrapping. We find that the RMG signal highly correlates with the sEMG signal across time, making RMG a reliable method for monitoring muscle activity. We also establish that our signal contains some characteristic features of the muscle deformation signal that are well known in biomechanics. Our main contribution is the proposal, development, and proof-of-concept usage of a novel noncontact muscle activity monitoring approach. This opens muscle activity monitoring up for use in rehabilitation, high-intensity contact sports analytics, performance arts, remote health monitoring, and wildlife healthcare and research. To the best of the authors’ knowledge, our approach is the first to measure the characteristic dimensional changes of muscles in vivo and without contact.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"24 22","pages":"37595-37606"},"PeriodicalIF":4.3,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Audible Noise Measurement of High-Voltage Transmission Lines Using Beamforming 利用波束成形测量高压输电线路的可听噪声

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-10-08 DOI: 10.1109/JSEN.2024.3472072

Penghui Zhao;Haiwen Yuan;Yingyi Liu;Jianxun Lv;Yuxin Deng

引用次数: 0

Ambient Temperature Estimation of Mountain Freeways Based on Roadside Camera Images 基于路边摄像头图像的山区高速公路环境温度估算

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-10-08 DOI: 10.1109/JSEN.2024.3472076

Zhu Sun;Yin-Li Jin;Yu-Jie Zhang;Wen-Peng Xu;Li Li

引用次数: 0

Energy-Balanced Routing Protocol With Nonuniform Clustering for Underwater Acoustic Sensors Networks 水下声学传感器网络的非均匀聚类能量平衡路由协议

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-10-07 DOI: 10.1109/JSEN.2024.3471878

Zhigang Jin;Haoyong Li;Ying Wang;Jiawei Liang;Simeng Cheng

{"title":"Energy-Balanced Routing Protocol With Nonuniform Clustering for Underwater Acoustic Sensors Networks","authors":"Zhigang Jin;Haoyong Li;Ying Wang;Jiawei Liang;Simeng Cheng","doi":"10.1109/JSEN.2024.3471878","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3471878","url":null,"abstract":"Energy consumption has been the focus of routing protocols in underwater acoustic sensor networks (UASNs), and many cluster-based routing protocols have been proposed to optimize energy consumption. However, there is the “hotspot” problem resulting from frequent data forwarding by cluster heads (CHs) and energy inefficiency caused by the transmission of data packets from shallow water to deep water. Therefore, we propose an energy-balanced routing protocol with nonuniform clustering (ERNC) to balance energy consumption and improve data transmission efficiency. First, without accurate 3-D localization, nodes exchange information with each other, and the combined coordinate of layer ID and hop ID is proposed to represent the node’s location information for subsequent CH selection and intercluster routing. Then, the combined coordinate, residual energy, and node density are considered comprehensively to select CHs for making their distribution uneven and equalizing the energy consumption. In the intercluster routing phase, the next hop candidate node sets with different forwarding priorities are constructed based on nodes’ coordinates to improve the network transmission efficiency. Moreover, we design the different holding times for the next-hop nodes in the same set to balance the energy consumption of CHs. The simulation results show that ERNC can effectively extend the network lifetime and improve the data transmission performance.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"24 22","pages":"38082-38091"},"PeriodicalIF":4.3,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Super-Resolution Micro-Range Curve Extraction for Precession Cone-Shaped Targets Based on Multidimensional Information 基于多维信息的超分辨率锥形目标微距曲线提取技术

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-10-07 DOI: 10.1109/JSEN.2024.3471797

Jing Wu;Zhiming Xu;Xiaofeng Ai;Yuqing Zheng;Qihua Wu

{"title":"Super-Resolution Micro-Range Curve Extraction for Precession Cone-Shaped Targets Based on Multidimensional Information","authors":"Jing Wu;Zhiming Xu;Xiaofeng Ai;Yuqing Zheng;Qihua Wu","doi":"10.1109/JSEN.2024.3471797","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3471797","url":null,"abstract":"The micro-range curve extraction of scattering centers is significant for estimating the motion and structural parameters of space targets. The curves are often extracted from high-resolution range profile (HRRP) for its range dimension information. However, most of the existing curve extraction algorithms based on HRRPs are with the accuracy of curves limited by range resolution. Moreover, due to noise interference, it is difficult to achieve extraction under low signal-to-noise ratio (SNR). Therefore, a super-resolution micro-range extraction algorithm based on the parameter correlation between micro-range curves and micro-Doppler (m-D) curves is proposed in this article. First, a parametric curve model is constructed and a rough parameter search of model is conducted to obtain the initial range curve, which ensures the robustness and real-time performance. Second, time-frequency analysis is applied to the range bins of the curve, and the m-D curve is refined by local maxima search to further improve the accuracy. The accurate micro-range curve is then reconstructed with the absolute range acquired by a 1-D search. Finally, simulation and experiment are carried out to verify the effectiveness and superiority of the proposed algorithm, which can achieve a better accuracy when SNR is −10 dB, compared with the existing methods.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"24 22","pages":"37544-37556"},"PeriodicalIF":4.3,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Generating Multiple Distinct Feasible Solutions for MEMS Accelerometers Using Deep Learning 利用深度学习为 MEMS 加速计生成多个不同的可行解决方案

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-10-07 DOI: 10.1109/JSEN.2024.3471618

Xiong Cheng;Zhixiang Zhai;Pengfei Zhang;Yiqi Zhou;Rui Wang;Wenhua Gu;Xiaodong Huang;Daying Sun

{"title":"Generating Multiple Distinct Feasible Solutions for MEMS Accelerometers Using Deep Learning","authors":"Xiong Cheng;Zhixiang Zhai;Pengfei Zhang;Yiqi Zhou;Rui Wang;Wenhua Gu;Xiaodong Huang;Daying Sun","doi":"10.1109/JSEN.2024.3471618","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3471618","url":null,"abstract":"Designing micro-electro-mechanical system (MEMS) sensors to meet specific performance requirements is essential. Traditional approaches, which rely heavily on expert knowledge and extensive finite-element simulations, are often time-consuming. Current deep learning (DL) methods in MEMS design typically focus on finding a single feasible solution, neglecting the need to generate multiple solutions simultaneously, which is critical in practical design scenarios. This article presents a methodology to address these limitations, introducing a hybrid network called the conditional variational autoencoder (VAE) and generative adversarial network (CVAE-GAN), along with a multisolution generator (G-MS). The CVAE-GAN enables high-accuracy and high-efficiency inverse design, while the G-MS, with its tailored noise updating strategy, generates multiple distinct feasible solutions for given performance criteria. This methodology has been experimentally validated on a piezoresistive MEMS accelerometer, finding the second solution in \u0000<inline-formula> <tex-math>$3.60~pm ~2.46$ </tex-math></inline-formula>\u0000 s, with a normalized distance of \u0000<inline-formula> <tex-math>$0.75~pm ~0.19$ </tex-math></inline-formula>\u0000, improving the existing method as much as \u0000<inline-formula> <tex-math>$3.63times $ </tex-math></inline-formula>\u0000 and \u0000<inline-formula> <tex-math>$7.19times $ </tex-math></inline-formula>\u0000, respectively. While traditional methods struggle to find more than two solutions, our G-MS can continuously output solutions according to the specified number, with the time taken to find each solution remaining nearly constant. This approach demonstrates the capability to quickly generate multiple accurate structural parameters based on desired performance, showcasing significant potential and providing valuable insights for MEMS sensor design.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"24 22","pages":"38377-38386"},"PeriodicalIF":4.3,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Point Cloud Registration Method Based on Segmenting Sphere Region Feature Descriptor and Overlapping Region Matching Strategy 基于分割球形区域特征描述和重叠区域匹配策略的点云注册方法

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-10-07 DOI: 10.1109/JSEN.2024.3471651

Yirui Zhang;Jiabo Xu;Yanni Zou;Peter X. Liu

{"title":"A Point Cloud Registration Method Based on Segmenting Sphere Region Feature Descriptor and Overlapping Region Matching Strategy","authors":"Yirui Zhang;Jiabo Xu;Yanni Zou;Peter X. Liu","doi":"10.1109/JSEN.2024.3471651","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3471651","url":null,"abstract":"Accurately registering point clouds is challenging due to three primary reasons: 1) it is difficult for point cloud feature descriptors to handle noise in complex scenes; 2) poorly descriptive features lead to incorrect sets of corresponding points; and 3) non-overlapping regions in the scene can adversely affect registration results. To address these issues, our approach consists of three key contributions. First, we propose a segmenting sphere region (SSR) feature descriptor that comprehensively preserves point cloud spatial coordinate information through the “sphere segmentation-furthest point preservation” operation, enabling robust registration in complex scenarios. Second, we design SSR-Net to improve the descriptiveness of SSR features, generating a soft matching matrix to estimate the correspondence between the improved features. Finally, we design an overlap region estimation module in SSR-Net, which employs attention to find the overlap region, thereby reducing the negative impact of non-overlapping regions in the soft matching matrix on registration results. We conducted comprehensive experiments on the B3R, ModelNet40, KITTI, unmanned aerial vehicle (UAV), and 3DMatch datasets, demonstrating the effectiveness of our proposed method.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"24 22","pages":"38387-38401"},"PeriodicalIF":4.3,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Novel Heavy Payload High-Resolution Actuator System: Design, Modeling, and Experiments 新型重型有效载荷高分辨率致动器系统：设计、建模和实验

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-10-07 DOI: 10.1109/JSEN.2024.3470817

Jianfeng Lin;Chenkun Qi;Yan Hu;Feng Gao

{"title":"A Novel Heavy Payload High-Resolution Actuator System: Design, Modeling, and Experiments","authors":"Jianfeng Lin;Chenkun Qi;Yan Hu;Feng Gao","doi":"10.1109/JSEN.2024.3470817","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3470817","url":null,"abstract":"The performance of actuator in nanopositioning system is significant to guarantee the rapidity and accuracy of closed-loop positioning control. However, the current actuators exhibit deficiencies including limited driving force and low accuracy because of the conflicting relationship between stiffness and resolution. In this article, a novel heavy payload high-resolution actuator (HPHRA) system is designed based on hydraulic transmission principle for nanopositioning robotic application. To achieve an accurate model, a compensatory Hammerstein model recognition strategy is proposed to capture the internal different physical characteristics, which is named compensatory nonlinear linear model (CNLM). The linear dynamics is captured by a linear transfer function, and the nonlinear dynamics is captured by a hysteresis PI model with several backlash operators. The residuals between nonlinear linear Hammerstein model and actual position, which is caused by external load, are compensated by a neural network. The CNLM recognition strategy is developed based on the regularized least square algorithm, singular value decomposition, and gradient descent algorithm. Experimental evidence on the HPHRA confirms the efficacy of the proposed CNLM method. The nanopositioning control in a 12-DOF macro–micro double parallel (12-MMDPR) robot under heavy load provides evidence of the HPHRA, CLNM strategy, and composite controller.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"24 22","pages":"37031-37041"},"PeriodicalIF":4.3,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0