ieeexplore最新文献_第5页

A Study on Concrete Crack Monitoring Method Based on Time–Frequency Characteristics of Electromagnetic Radiation Signals 基于电磁辐射信号时频特性的混凝土裂缝监测方法研究

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2025-04-29 DOI: 10.1109/JSEN.2025.3563512

Jinghua Zhang;Shuzhi Wen;Bingkun Wei;Lisha Peng;Songling Huang

{"title":"A Study on Concrete Crack Monitoring Method Based on Time–Frequency Characteristics of Electromagnetic Radiation Signals","authors":"Jinghua Zhang;Shuzhi Wen;Bingkun Wei;Lisha Peng;Songling Huang","doi":"10.1109/JSEN.2025.3563512","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3563512","url":null,"abstract":"Concrete generates weak electromagnetic radiation (EMR) signals during the cracking process. The EMR monitoring method for concrete cracking is a noncontact and nondestructive monitoring approach. However, substantial interference from environmental EMR noise degrades the consistency of monitoring signals, resulting in low recognition accuracy and a limited monitoring range. To address this, this study introduces a resonance noise reduction method based on the structure of EMR monitoring sensors. The proposed approach enhances the clarity and interpretability of monitored EMR signals through frequency-domain amplitude transformation and discrete wavelet decomposition. The time–frequency characteristics of both EMR signals and noise are comprehensively analyzed by utilizing continuous wavelet transform. A parallel network architecture integrating a convolutional neural network (CNN) and long short-term memory (LSTM) is employed to extract features from EMR signals associated with concrete cracking. Additionally, multiscale convolutional kernels and attention mechanisms (AMs) are integrated according to the time–frequency characteristics of the signals. Experimental results reveal that the proposed method effectively distinguishes EMR signals from four common types of EMR noise, achieving an average signal recognition accuracy of over 98% on the validation and test datasets, with a crack identification accuracy rate of 94.6%. This approach significantly enhances the applicability and potential use of EMR monitoring in concrete cracking scenarios.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"20238-20249"},"PeriodicalIF":4.3,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144206159","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

Excellent Sensitivity and Selectivity of g-C4N3 Monolayer-Based Gas Sensors for Efficiently Detecting Nitrogen Oxides: Spin-Resolved Quantum Transport Behaviors 基于g-C4N3单层气体传感器高效检测氮氧化物的卓越灵敏度和选择性：自旋分辨量子输运行为

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2025-04-29 DOI: 10.1109/JSEN.2025.3563359

Wensheng Zhou;Cheng Luo;Peng Tang;Xianbo Xiao;Songbo Xiong;Tong Chen

{"title":"Excellent Sensitivity and Selectivity of g-C4N3 Monolayer-Based Gas Sensors for Efficiently Detecting Nitrogen Oxides: Spin-Resolved Quantum Transport Behaviors","authors":"Wensheng Zhou;Cheng Luo;Peng Tang;Xianbo Xiao;Songbo Xiong;Tong Chen","doi":"10.1109/JSEN.2025.3563359","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3563359","url":null,"abstract":"NO and NO2 are the important gases that can lead to the formation of photochemical smog and acid rain. Therefore, it is important to develop high-performance nitrogen oxide sensors. Here, the electronic structure, spin transport characteristics, and gas sensitivity of 2-D graphitic carbon nitride 2D g-C4N3) monolayers with doped magnetic metal atoms were studied via first-principles methods. A g-C4N3 monolayer exhibited ferromagnetic half-metallic and high-sensitivity properties for NO and NO2 detection. The monolayer nanodevices also exhibited perfect single-spin conduction with a spin-filtering efficiency of up to 100%. A designed g-C4N3 monolayer sensor strongly chemisorbed both NO and NO2, resulting in the formation of electrons in the local scattering region. This directly affected spin transport properties, resulting in NO and NO2 sensitivity up to 100%. A g-C4N3 sensor with transition metal doping (especially Fe) slightly improved NO detection and significantly reduced NO2 detection. Hence, an FE-doped g-C4N3 sensor in a complex gas environment containing both NO and NO2 largely eliminated NO2 interference and increased NO detection. A g-C4N3 monolayer with excellent half-metal properties and high gas sensitivity will have potential applications in high-performance spin devices and spin-gas sensitive devices.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"20687-20694"},"PeriodicalIF":4.3,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205944","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

DGAN: Flight Data Anomaly Detection Based on Dual-View Graph Attention Network 基于双视图图注意网络的飞行数据异常检测

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2025-04-28 DOI: 10.1109/JSEN.2025.3562842

Wenlong Yan;Xu Li;Linjiang Zheng;Jiaxing Shang;Lin Wu;Hongtao Liu;Xiuyi Li;Yu Qian

{"title":"DGAN: Flight Data Anomaly Detection Based on Dual-View Graph Attention Network","authors":"Wenlong Yan;Xu Li;Linjiang Zheng;Jiaxing Shang;Lin Wu;Hongtao Liu;Xiuyi Li;Yu Qian","doi":"10.1109/JSEN.2025.3562842","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3562842","url":null,"abstract":"A large number of flight data is collected by various sensors during flight, including altitude, speed, pitch, etc. Flight unsafe events, such as hard landings, can be reflected in flight anomaly data. Thus, flight data anomaly detection is crucial for aviation safety, enabling the identification of deviations from normal operations. However, due to the complexity and high dimensionality of the flight data, existing methods often fail to adequately extract temporal and variable information. As a result, these methods exhibit poor detection performance, especially when the anomaly data is scarce. To address these issues, we propose a novel dual-view graph attention network (DGAN) model for flight data anomaly detection. Specifically, two parallel graph attention (GAT) layers are employed to create embeddings that are rich in temporal correlations and variable dependencies. A TCN-based autoencoder module is proposed for data augmentation on these embeddings to extract two views consistent with the underlying data patterns. Furthermore, DGAN constructs pairs of positive and negative samples both within a single view and between different views. A dual-view contrastive training strategy is proposed to construct contrastive loss, which can learn a good representation of the flight sequence and ensure effective anomaly detection even in cases of scarce anomaly data. We conduct experiments on a dataset comprising 44808 real-world flight samples from the Airbus A321. The results demonstrate that the performance of DGAN exceeds state-of-the-art (SOTA) models. Moreover, we examine the effectiveness of DGAN through further visualizations and case studies.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"20956-20969"},"PeriodicalIF":4.3,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144196660","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

MgGaO Solar-Blind Photodetectors With Ultralow Dark-Current Prepared by Adjusting MgO Cycle Ratio 调节MgO循环比制备超低暗电流MgGaO日盲光电探测器

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2025-04-28 DOI: 10.1109/JSEN.2025.3562810

Fang-Bin Ren;Zhan-Bo Su;Xiao-Ying Zhang;Shui-Yang Lien

{"title":"MgGaO Solar-Blind Photodetectors With Ultralow Dark-Current Prepared by Adjusting MgO Cycle Ratio","authors":"Fang-Bin Ren;Zhan-Bo Su;Xiao-Ying Zhang;Shui-Yang Lien","doi":"10.1109/JSEN.2025.3562810","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3562810","url":null,"abstract":"Gallium oxide 2O<inline-formula> <tex-math>$(Ga_{{3}}text {)}$ </tex-math></inline-formula> is regarded as a promising material for solar-blind photodetectors owing to its wide bandgap properties. However, oxygen vacancy defects within the material limit its further enhancement of optoelectronic performance. Current research primarily focuses on doping modifications to improve the properties of Ga2O3, because the doping concentration significantly influences the performance of films. In this work, magnesium (Mg) doping was introduced to enhance the optoelectronic properties of Ga2O3 films. Mg-doped Ga2O3 (MgGaO) films were fabricated using plasma-enhanced atomic layer deposition (PEALD) through adjusting the magnesium oxide (MgO) cycle ratio. The structural, chemical, morphological, and optical properties of MgGaO films were analyzed using X-ray diffraction, X-ray photoelectron spectroscopy, atomic force microscopy, scanning electron microscopy, and ultraviolet-visible spectroscopy. The results indicate that as the MgO cycle ratio increases, the crystallinity and surface roughness of MgGaO films improve, and the optical bandgap increases from 4.84 to 5.91 eV. The oxygen vacancy content in the films decreases initially but increases at higher MgO cycle ratios. Additionally, the films with different MgO cycle ratios were applied to fabricate solar-blind photodetectors. The photodetector demonstrated the best performance at an MgO cycle ratio of 5%, exhibiting a dark current as low as <inline-formula> <tex-math>$4.90times 10^{-{15}}$ </tex-math></inline-formula> A, an ultrahigh photocurrent-to-dark current ratio of <inline-formula> <tex-math>$9.70times 10^{{6}}$ </tex-math></inline-formula>, and rise/decay times of 74.7/45.7 ms, with the highest responsivity of 13.2 mA/W in the 200–280 nm range. This study demonstrates that MgGaO films hold great potential application in high-performance solar-blind photodetectors.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"18812-18820"},"PeriodicalIF":4.3,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144196668","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

Wideband Signal Generation Using Egyptian Fractions and Application to Instantaneous Impedance Measurements 宽带信号的产生使用埃及分数和应用瞬时阻抗测量

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2025-04-28 DOI: 10.1109/JSEN.2025.3563340

Sohaib Majzoub;Anis Allagui;Ahmed S. Elwakil;Di Zhang

{"title":"Wideband Signal Generation Using Egyptian Fractions and Application to Instantaneous Impedance Measurements","authors":"Sohaib Majzoub;Anis Allagui;Ahmed S. Elwakil;Di Zhang","doi":"10.1109/JSEN.2025.3563340","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3563340","url":null,"abstract":"In this work, we investigate the use of Egyptian fractions to construct wideband signals with a near-flat power spectrum. In particular, it is well-known that wideband signals can be obtained using composite multisine signals. However, the choice of the frequencies and/or phase shifts in these sinusoids is critical to approach a flat power spectrum with a low crest factor. A number of known methods, such as using Rudin-Shapiro polynomials or random phases, have been used in this problem. However, the use of Egyptian fractions has not been explored yet, despite being easier to generate and implement. Here, we construct multisine signals (in the form of a voltage) based on different Egyptian fraction sequences (EFSs) and use them to measure the linear time-invariant impedance of an RC circuit and then the instantaneous impedance of nonlinear time-varying solar cell. Two methods are used to generate these signals: 1) the EFSs are assigned to the phase angles or 2) they are used to set the values of the angular frequencies. The accuracy of measurements is assessed via comparison to the standard sine-sweep method using a research-grade Biologic VSP-300 electrochemical station showing acceptable results.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"19555-19562"},"PeriodicalIF":4.3,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144196629","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

GLCII-DenseNet Integrated With Multiple Blocks for Waist Action Recognition Based on Surface Electromyographic Signals 基于表面肌电信号的腰部动作识别的多块集成GLCII-DenseNet

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2025-04-28 DOI: 10.1109/JSEN.2025.3562961

Shuhong Cheng;Chuqiang Hu;Fei Liu;Yonghong Hao;Chao Zhang

{"title":"GLCII-DenseNet Integrated With Multiple Blocks for Waist Action Recognition Based on Surface Electromyographic Signals","authors":"Shuhong Cheng;Chuqiang Hu;Fei Liu;Yonghong Hao;Chao Zhang","doi":"10.1109/JSEN.2025.3562961","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3562961","url":null,"abstract":"As low-back pain prevalence rises, lumbar rehabilitation robots are becoming more common. By analyzing surface electromyographic (EMG) signals, lumbar movements can be recognized, enabling real-time feedback for personalized training. Deep learning methods are increasingly used to recognize these movements. Conventional deep learning models only capture local spatial information and deep features during the feature extraction process, which limits their ability to extract global temporal dependence features and shallow features. Furthermore, their capability to capture the global contextual information is also relatively restricted. To this end, this article presents a new model that integrates the global–local feature extraction (GLFE) block, the contextual transformer (CoT) block, and a modified backbone architecture of DenseNet: the global and local contextual information integrated denseNet (GLCII-DenseNet) model, designed for the recognition of sparse surface EMG signals from the waist. This model extracts rich shallow, deep, local, and global features, enhancing its capability for feature representation and context feature information capture. It effectively integrates feature information from different locations while extracting a large amount of feature data, thereby improving the accuracy and robustness of EMG signal recognition. To verify the practical validity of the model, we recorded ten healthy subjects, each of whom extracted EMG signals from four muscles while performing six common lumbar exercises. Comparison experiments with other networks show that the model outperforms other methods in recognizing sparse surface EMG signals. In addition, we conducted model generalization comparison experiments to further evaluate the model’s performance. The results show that our model is more robust to noise interference.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"20158-20168"},"PeriodicalIF":4.3,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205849","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

Elbow Angle Monitoring and Error Analysis Using a Wearable PDMS Embedded FBG Sensor 基于可穿戴式PDMS嵌入式FBG传感器的弯头角监测与误差分析

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2025-04-28 DOI: 10.1109/JSEN.2025.3563078

Archana Thrikkaikuth Chalackal;Srijith Kanakambaran

{"title":"Elbow Angle Monitoring and Error Analysis Using a Wearable PDMS Embedded FBG Sensor","authors":"Archana Thrikkaikuth Chalackal;Srijith Kanakambaran","doi":"10.1109/JSEN.2025.3563078","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3563078","url":null,"abstract":"Elbow flexion and extension are necessary movements for daily tasks. Elbow joint impairments can be brought on by aging, accidents, and repetitive motions making the monitoring of elbow angles critical. In this work, a sensor for elbow angle monitoring during bending and extension using a fiber Bragg grating (FBG) embedded in polydimethylsiloxane (PDMS) with a wearable band is proposed. Two methods for measuring elbow angles, wearable and platform-based sensing are investigated. The wearable sensor-based measurements are consistent over different trials with a linear variation of Bragg wavelength with flexion/extension angle up to 90°. The sensitivities for flexion and extension are 0.0029 and 0.0037 nm/°, respectively. Further, the factors contributing to error in the measurement of elbow angle such as tightness of wearable band, spatial and angular misalignment of the sensor, and the removal and replacement of sensor are studied. The findings show that the error is maximum for an angular misalignment followed by tightly bound sensor and spatial misalignment. The desirable configuration for elbow angle measurement is a tightly bound sensor at the mean position for high mean sensitivity with a tolerable level of error and a left/right-aligned sensor with moderate tightness for minimum error at a low sensitivity. The PDMS-embedded FBG-based wearable sensor, in an optimal configuration, can be used for monitoring elbow angles.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"19341-19348"},"PeriodicalIF":4.3,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144196657","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

Distributed Optical Fiber Vibration Signal Recognition Based on Dual-Layer VMD and ICDET 基于双层VMD和ICDET的分布式光纤振动信号识别

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2025-04-28 DOI: 10.1109/JSEN.2025.3562847

Haiyan Xu;Xinyu Feng;Kangjian Mei;Yingjuan Xie

{"title":"Distributed Optical Fiber Vibration Signal Recognition Based on Dual-Layer VMD and ICDET","authors":"Haiyan Xu;Xinyu Feng;Kangjian Mei;Yingjuan Xie","doi":"10.1109/JSEN.2025.3562847","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3562847","url":null,"abstract":"In order to improve the recognition accuracy of vibration signals in distributed optical fiber vibration sensing (DOFVS) systems, this article proposes a method combing dual-layer variational mode decomposition (DL-VMD) and improved compensation distance estimation technology (ICDET). First, this article proposes the DL-VMD method to achieve a more refined decomposition of optical fiber vibration signals, which finally obtains three optimal intrinsic mode functions (IMFs) with richer information. Second, the time-domain and frequency-domain features of the three IMFs are extracted as feature vectors. Then the proposed ICDET is used to optimize the extracted features. Finally, the support vector machine (SVM) acts as the classifier to realize the recognition of optical fiber vibration signals. In order to verify the effectiveness of the proposed method, this article carries out experiments on four common optical fiber vibration signals, and the results show that the recognition accuracy of this scheme on four vibration signals is 98.3%. This shows that the method proposed in this article has great potential for application in the field of DOFVS system.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"20136-20146"},"PeriodicalIF":4.3,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205844","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

New Convenient Composite Probes With 0°/180° Hybrid Couplers for Near-Field Scanning Measurements 用于近场扫描测量的带有0°/180°混合耦合器的新型方便复合探头

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2025-04-28 DOI: 10.1109/JSEN.2025.3563221

Lei Wang;Rui-Qi Wang;Chengyang Luo;Guoguang Lu

{"title":"New Convenient Composite Probes With 0°/180° Hybrid Couplers for Near-Field Scanning Measurements","authors":"Lei Wang;Rui-Qi Wang;Chengyang Luo;Guoguang Lu","doi":"10.1109/JSEN.2025.3563221","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3563221","url":null,"abstract":"In this work, we propose two new convenient composite probes with 0°/180° hybrid couplers for near-field scanning measurements. The proposed probes (denoted as A and B) integrate a U-shaped loop as the driven element and a parallel U-shaped loop as the parasitic element, two different 0°/180° hybrid couplers, two interconnected vias, and a pair of 50-<inline-formula> <tex-math>$Omega $ </tex-math></inline-formula> striplines. The design leverages the driven and parasitic U-shaped loops to concurrently detect electric-field (E-field) and magnetic-field (H-field) components and improve detection sensitivity, thereby extending the probes’ capability to capture a wider spectrum of electromagnetic fields. The integrated 0°/180° hybrid couplers enable precise differentiation and superposition of outputs from the driven loop, effectively isolating the E-field and H-field responses. Crucially, this architecture permits direct connectivity to oscilloscopes, eliminating dependence on vector network analyzers (VNAs) for electromagnetic component sensing. The design, simulation, measurement, and characterization of two Probes A and B are detailed. Measurement results demonstrate these probes’ enhanced sensitivity and dual-field measurement capability. The ability of directly link to oscilloscopes, bypassing the need for a VNA, makes these probes highly suitable for practical interference source location testing.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"18982-18988"},"PeriodicalIF":4.3,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144206057","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

Parallel Channel-Temporal Attention-Based Temporal Convolutional Network for Marine Engine Performance Prediction Under Varying Load Conditions 基于并行通道-时间注意的时间卷积网络在变负载条件下船舶发动机性能预测中的应用

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2025-04-28 DOI: 10.1109/JSEN.2025.3562851

Jiawen Sun;Hongxiang Ren;Hong Zeng;Xiao Yang;Yi Zhou

{"title":"Parallel Channel-Temporal Attention-Based Temporal Convolutional Network for Marine Engine Performance Prediction Under Varying Load Conditions","authors":"Jiawen Sun;Hongxiang Ren;Hong Zeng;Xiao Yang;Yi Zhou","doi":"10.1109/JSEN.2025.3562851","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3562851","url":null,"abstract":"The safe operation and intelligent optimization of ships heavily rely on the predictive maintenance of marine engine performance. However, existing methods for predicting engine performance face limitations due to the various characteristics of ship engines, which depend on the sailing state and environmental conditions. To address this, a novel deep learning framework, the parallel channel-temporal attention-based temporal convolutional network (PCTA-TCN), is proposed to predict marine engine performance across varying load ranges. The PCTA-TCN framework introduces channel attention and temporal attention mechanisms in two independent branches, adaptively adjusting the focus on important features and temporal dependencies in the measured data. Parallel temporal convolutional network (TCN) backbones are used to extract high-level feature representations from different sequences. Finally, the model generates predictions by performing a nonlinear mapping on the extracted features at multiple levels. Experimental validation using sensor-acquired data demonstrates that PCTA-TCN consistently achieves an <inline-formula> <tex-math>${R}^{{2}}$ </tex-math></inline-formula> value exceeding 0.956 across all datasets. Compared to the baseline TCN model, the proposed method improves the prediction accuracy by 13.95%, 49.81%, 15.64%, and 19.73% under four different load conditions. Furthermore, PCTA-TCN outperforms other state-of-the-art methods, particularly under complex and variable operating conditions.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"19506-19521"},"PeriodicalIF":4.3,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144196590","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