IEEE Transactions on Instrumentation and Measurement最新文献

{"title":"Word Length-Aware Text Spotting: Enhancing Dense Text Detection and Recognition for Camera-Captured Document Image","authors":"Hao Wang;Huabing Zhou;Yanduo Zhang;Jiayi Ma;Haibin Ling","doi":"10.1109/TIM.2025.3560748","DOIUrl":"https://doi.org/10.1109/TIM.2025.3560748","url":null,"abstract":"Text spotting in camera-captured document images faces significant challenges, especially with dense text of variable lengths. Existing approaches falter with the long-tailed distribution of word lengths, leading to decreased performance on words with extreme lengths. To address this issue, we present WordLenSpotter, an end-to-end framework incorporating word length awareness to improve detection and recognition across a wide range of word lengths. Our method utilizes a dilated convolutional fusion module in its image encoder and a transformer framework for joint detection and recognition guided by word length priors. Our innovations include a spatial length predictor (SLP) and a length-aware segmentation (LenSeg) proposal head, enhancing the model’s sensitivity to the spatial distribution of text. Evaluated on our newly constructed DSTD1500 dataset and existing public datasets with dense text, WordLenSpotter demonstrates superior text spotting capabilities, especially in handling the diversity of word lengths in dense text scenes. The code is available at <uri>https://github.com/unxiaohao/WordLenSpotter</uri>","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-15"},"PeriodicalIF":5.6,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143875104","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}

{"title":"Digital Twin-Driven Physically Constrained Generative Adversarial Network for Industrial Boiler Fault Diagnosis","authors":"Qibing Wang;Xinhan Zhang;Jiawei Lu;Gang Xiao;Yaxing Ren;Wenjian Li","doi":"10.1109/TIM.2025.3558806","DOIUrl":"https://doi.org/10.1109/TIM.2025.3558806","url":null,"abstract":"As important energy equipment, industrial boilers require more reliable fault diagnosis technology to ensure their continuous safe operation under high-temperature and high-pressure conditions. Due to the difficulty in collecting fault data, traditional fault diagnosis methods based on a large amount of labeled fault data cannot be effectively applied to actual industrial scenarios. This article proposes a physically constrained generative adversarial network (PCGAN) driven by digital twins (DTs) for industrial boiler fault diagnosis, which can accurately diagnose boiler faults when training data is insufficient. First, this article uses DT technology to establish a virtual model of the boiler and uses the constructed DT model to emulate the failure conditions of the boiler and generate simulated data. Then, a novel PCGAN fault diagnosis method is designed, and data obtained by the DT model is used to train and validate its effectiveness. Finally, the feasibility of the proposed method in industrial boiler fault diagnosis is verified by experimental results. The results show that the fault diagnosis accuracy of this method reaches 96.28%, which is significantly higher than other data-driven fault-diagnosis methods.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-15"},"PeriodicalIF":5.6,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10964521","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870992","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}

{"title":"Evolving Through Steps: Double-Memory-Driven Anti-Forgetting Framework for Incremental Zero-Shot Fault Diagnosis","authors":"Jiancheng Zhao;Chunhui Zhao;Jiaqi Yue","doi":"10.1109/TIM.2025.3560740","DOIUrl":"https://doi.org/10.1109/TIM.2025.3560740","url":null,"abstract":"Zero-shot fault diagnosis (ZSFD) can identify unseen faults by predicting fault attributes labeled by human experts. We recognize the need for ZSFD to handle continuous changes in practical industrial processes, that is, the model’s ability to update for newly collected fault categories and attributes while avoiding forgetting the diagnosis ability learned before. Therefore, the incremental ZSFD (IZSFD) paradigm is proposed, which incorporates category increment and attribute increment tasks for both conventional and generalized ZSFD (GZSFD) paradigms. For the category increment, the number of categories continuously increases due to new categories being collected or recognized. For the attribute increment, the number of attributes continuously increases as experts deepen their understanding of each category. To achieve IZSFD, we present a double-memory driven anti-forgetting framework (DM-AF) that aims to learn new fault categories and attributes. DM-AF accumulates knowledge from two perspectives: features and attribute prototypes. The feature memory is established through a generative model that employs designed anti-forgetting training strategies, addressing the accumulation of generation errors over multiple learning stages. The attribute prototype memory is established through the diagnosis model, and the proposed memory-driven prototype update strategy allows the update of the attribute prototype memory without requiring the storage of samples. The effectiveness of the proposed method is verified by a real hydraulic system and the Tennessee-Eastman benchmark.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-10"},"PeriodicalIF":5.6,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871041","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}

{"title":"Noniterative Wet Gas Flow Metering in Annular Mist Flow by Combining Vortex Meter and Liquid Film Parameters","authors":"Jinxia Li;Ji Lin;Yi Huang;Hongbing Ding;Hongjun Sun","doi":"10.1109/TIM.2025.3560723","DOIUrl":"https://doi.org/10.1109/TIM.2025.3560723","url":null,"abstract":"Wet gas metering in annular mist flow is important for it is typically used in fiscal metering, and the traditional iteration-based methods are limited due to their sensitivity to initial values and time-consuming in the iteration process. To improve the real-time performance and reliability, this study tries to develop noniterative wet gas metering method based on the vortex meter-conductance dual-modality system. To adapt to different application scenarios, two models are proposed, named nonlinear regression model and neural network model, respectively. The tests are conducted on a DN 15 vertical pipeline with a gas flow rate range of 12–24 m3/h and liquid volume fraction within 1.30‰. To obtain the flow parameters of liquid film thickness, disturbance wave frequency, and velocity simultaneously, the dual-ring liquid film sensor is designed and optimized. The input features are selected by the importance ranking of the correlation heatmap, and the optimized hyperparameters and K-fold cross-validation ensure the generalization of the trained neural network. Finally, the predicted performances are evaluated and compared in detail. It indicates that mean film thickness could be regarded as the unique scale parameter of vortex meter overreading (OR), and <inline-formula> <tex-math>$textrm {OR}=1+2.64{delta _{m}} / D$ </tex-math></inline-formula> gives a predicted error of ±1.5% for gas flow rate. Liquid flow could be directly predicted by combining different liquid film flow parameters, and <inline-formula> <tex-math>$U_{textrm {sl}}=535.62f_{textrm {DW}}^{0.214}D^{2.034}delta _{m}^{0.655}V_{textrm {DW}}^{2.090}$ </tex-math></inline-formula> gives a predicted full-scale error of ±5.0% for liquid flow rate. The neural network model gives satisfactory prediction both for gas and liquid flow rates, gas flow accuracy within ±1.0% error bands, and liquid flow within ±1.5% full-scale error bands. Finally, comparisons and practical suggestions for the application are given for the two proposed noniterative wet gas metering models.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871033","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}

{"title":"110 kV Power Cable External Disturbance Optical Fiber Sensing Detection and Identification Method Based on ResNeXt and Attention Mechanism","authors":"Haoyuan Tian;Jianxin Wang;Weikai Zhang;Hong Liu;Yuxuan Song;Weigen Chen","doi":"10.1109/TIM.2025.3560744","DOIUrl":"https://doi.org/10.1109/TIM.2025.3560744","url":null,"abstract":"Power cable is a core equipment for the operation of power transmission and distribution systems. Effective detection and identification of external disturbances of power cable is of great significance to the stable operation of power transmission and distribution systems. Optical fiber sensor has the characteristics of antielectromagnetic interference and small size and is widely used in built-in detection of equipment. Based on 110 kV power cable and optical fiber Mach-Zehnder interferometer (MZI), the signal difference between built-in optical fiber and external optical fiber is compared, and the effectiveness of built-in optical fiber detection is verified. Subsequently, the detection performance of built-in optical fiber under four different external disturbances is studied, and the signal denoising method based on slime mould algorithm-variational mode decomposition (SMA-VMD) is used for the built-in optical fiber detection signal to obtain 1-D data with improved quality. The Gramian angular field (GAF) is used for time-frequency joint analysis to expand the 1-D information into a 2-D image for ResNeXt to identify the type of external disturbance. By introducing the attention mechanism, the recognition rate of the system is improved. The results show that the best recognition index of the model can reach 98.35%. This method provides a new idea for the detection of external disturbances of intelligent power cables.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143875105","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}

{"title":"Stiffness Measurement of Flexure Hinge-Based Compliant Mechanisms by Utilizing the Nanoindentation Method","authors":"Chunxue Yi;Dayu Wei;Hu Huang;Zhi Xu;Hongwei Zhao","doi":"10.1109/TIM.2025.3560746","DOIUrl":"https://doi.org/10.1109/TIM.2025.3560746","url":null,"abstract":"Flexure hinge-based compliant mechanisms find extensive applications in micro/nano actuation, where their transmission characteristics are significantly affected by stiffness. Traditional theoretical analysis methods generally ignore some influences and overidealize the load and boundary conditions, making it challenging to accurately evaluate the actual stiffness of compliant mechanisms. To address this limitation, a nanoindentation method was proposed to experimentally measure the stiffness of flexure hinge-based compliant mechanisms. In this method, the compliant mechanism was placed under the sample, thereby introducing an additional frame compliance for the nanoindentation instrument. Via comparative analysis of the load-depth curves obtained with and without the compliant mechanism, the stiffness of compliant mechanism could be calculated. To validate the effectiveness of this method, three compliant mechanisms based on rectangular, circular, and V-shaped flexure hinges were designed. Their stiffnesses were evaluated by the matrix-based compliance modeling (MCM) method, the finite element simulation (FES) method, the proposed nanoindentation method, and the traditional method. In the comparison of these four methods, the nanoindentation method can accurately evaluate the stiffness of compliant mechanisms, and the uncertainty is less than 3%. Being different from the theoretical analysis, the proposed nanoindentation method serves as an experimental evaluation tool, and it allows for the direct measurement of the stiffness of compliant mechanisms after manufacturing. The instrumented measurement method also significantly reduces the effects of human error. This is of practical significance and scientific value for guiding the design of compliant mechanisms and predicting their transmission characteristics in-service.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871073","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}

{"title":"GLFNet: An RGB-T Crowd Counting Network Based on Global–Local Multimodal Feature Fusion","authors":"Yingxiang Hu;Yanbo Liu;Guo Cao;Jin Wang","doi":"10.1109/TIM.2025.3555712","DOIUrl":"https://doi.org/10.1109/TIM.2025.3555712","url":null,"abstract":"RGB-T crowd counting methods aim to enhance the counting accuracy of network models under conditions of uneven lighting and low visibility by fusing features from the RGB and thermal modalities. Previous approaches primarily utilized attention mechanisms to extract and fuse complementary RGB and thermal features. However, these methods lack guidance and constraints during the extraction and fusion of multimodal features and do not fully leverage the complementary advantages between global and local features, leading to suboptimal performance. This article argues that by transitioning from global attention to local attention, extracting and fusing the complementary information between global and local multimodal features can significantly improve the model’s counting performance. To achieve this, we propose an RGB-T crowd counting network based on global-local multimodal feature fusion (GLFNet). Specifically, we first use a multihead attention mechanism to fuse global multimodal features and guide the global multimodal fusion using learnable block-counting guided tokens (BCTs). Next, we employ composite spatial attention mechanisms (CSAMs) to focus on the local detail information of multimodal crowd features and facilitate the fusion of local multimodal features. Finally, we utilize a detail contrast loss function (<inline-formula> <tex-math>$L_{mathbf {d}}$ </tex-math></inline-formula>) to capture the complementary advantages between global and local multimodal features and to guide and constrain the fusion process of multimodal features. Experimental results on the RGBT-CC and DroneRGBT datasets demonstrate the superior performance of our method.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-18"},"PeriodicalIF":5.6,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143865244","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}

{"title":"Separation, Identification, and Compensation of Damping, Detection, and Actuation Errors for Rate-Integrating Hemispherical Resonator Gyroscopes","authors":"Kaixin Deng;Yao Pan;Pengbo Xiao;Xingyuan Tang;Jingyu Li;Tao Xia;Jie Yuan","doi":"10.1109/TIM.2025.3555670","DOIUrl":"https://doi.org/10.1109/TIM.2025.3555670","url":null,"abstract":"Damping mismatch, detection error, and actuation error are the primary sources of the output drift in rate-integrating hemispherical resonator gyroscopes (HRGs). To date, separating the three errors remains a challenge, which hinders the accurate compensation of HRGs. This article proposes a novel method to separate the damping, detection, and actuation errors of HRGs. Theoretically, a dynamics model of HRGs considering the three errors is developed, where the detection and actuation errors are modeled using Fourier analysis. The effects of these three errors on the scale factor and the bias under different operation modes are discussed in detail for the first time. It is found that the three errors can be decoupled under the decay with quadrature control (DQC) mode, a special operation mode designed in this article. In the experiments, by measuring the angle dependence of the scale factor and the bias of the energy loop, the damping, detection, and actuation errors of three HRGs are successfully identified and then comprehensively compensated. For one typical tested HRG, after compensation, the angle-dependent error of the scale factor decreases from 1.08% to 0.036% by a factor of 30, the angle-dependent variation of the static drift reduces from <inline-formula> <tex-math>$5.14 times 10^{-3} ; ^{circ }$ </tex-math></inline-formula>/s to <inline-formula> <tex-math>$2.37 times 10^{-4} ; ^{circ }$ </tex-math></inline-formula>/s by a factor of 22, and the fluctuation of the dynamic output at different input rates decreases 14–25 times. Our method can also be conveniently applied to other rate-integrating Coriolis vibrating gyroscopes (CVGs).","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-13"},"PeriodicalIF":5.6,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143845458","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}

{"title":"High-Precision UWB TDOA Localization Algorithm Based on UKF-FNN-CHAN-RIC","authors":"Ershen Wang;Yongkang Wang;Shuning Zhang;Song Xu;Yunhao Chen;Yanwen Wang;Tengli Yu;Hong Lei","doi":"10.1109/TIM.2025.3554908","DOIUrl":"https://doi.org/10.1109/TIM.2025.3554908","url":null,"abstract":"Ultrawideband (UWB) technology has garnered significant attention due to its extensive applications in indoor positioning. However, its performance is susceptible to interference from environmental factors. In response to the positioning accuracy issues in time difference of arrival (TDOA) scenarios, this article proposes an integrated TDOA-UKF-FNN-Chan-RIC algorithm that incorporates the unscented Kalman filter (UKF), feedforward neural networks (FNNs), Chan’s algorithm, and redundant information correction (RIC) to effectively enhance the positioning accuracy and robustness of UWB systems. Initially, by investigating the redundant information within the UWB solution model in TDOA scenarios, the inter-relationship between redundant information and measurement vectors is revealed. Subsequently, a gradient descent error correction algorithm for redundant information suitable for TDOA scenarios is proposed, and UKF and FNN transformations are combined to ensure that the data meet the preconditions for algorithmic application. To address the stability issues of positioning algorithms based on implicit function solutions in TDOA scenarios, Chan’s algorithm is employed to convert range difference measurements into range measurements, thereby enhancing computational robustness. Ultimately, the TDOA-UKF-FNN-Chan-RIC algorithm is proposed, and its effectiveness is validated through simulation and practical experiments. The experimental results demonstrate that this algorithm significantly improves positioning accuracy and robustness, achieving millimeter-level fixed-point accuracy and centimeter-level track accuracy in practical experiments.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-13"},"PeriodicalIF":5.6,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848892","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}

{"title":"Spurious Suppression and Frequency Accuracy Enhancement in Direct Digital Frequency Synthesis: Analysis, Simulation, and Experiment","authors":"Jiawen Lan;Liangqi Gui;Weihua She;Jinbo Hu;Liang Lang;Quanliang Huang","doi":"10.1109/TIM.2025.3557825","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557825","url":null,"abstract":"Direct digital frequency synthesis (DDS) technology has extensive applications across various fields, including instrumentation, communication, measurement, and aerospace. However, due to technical limitations in the digitization process, DDS still faces several challenges, such as spurs and frequency inaccuracy. Conventional dithering methods are limited in suppressing spurs, often increase the noise floor, and do not consider the improvement of frequency accuracy. This article proposes a random frequency compensation (RFC) method to address these issues, which effectively suppresses spurs without raising the noise floor and improves frequency accuracy. The main contributions of this work are threefold. First, we propose an innovative RFC method, which introduces a 1-bit random sequence to disrupt the periodic error sequence and compensate for the fractional part of the frequency control word, thereby simultaneously suppressing spurs and enhancing frequency accuracy. Second, we mathematically analyze the spurious suppression and frequency accuracy of the proposed method, supported by simulations to validate the theoretical effectiveness of the proposed RFC. Finally, to assess real-world performance, we implement the proposed RFC method on a field-programmable gate array (FPGA) and conduct experiments, demonstrating its superiority over conventional dithering methods and its potential for practical use.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.6,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848788","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}