{"title":"A Cross-Domain Online Diagnosis Framework Under Small Fault Sample","authors":"Zuoshuang Chen;Dongdong Zhang;Zuoyi Chen;Jun Wu;Hong-Zhong Huang","doi":"10.1109/TIM.2025.3606021","DOIUrl":"https://doi.org/10.1109/TIM.2025.3606021","url":null,"abstract":"Cross-domain fault diagnosis in industrial applications presents a major challenge, especially when only a limited number of fault samples are available. Existing data-driven and transfer learning (TL) methods often struggle with real-time diagnosis, insufficient generalization across domains, and the inability to adapt to continuously evolving fault conditions. To address these limitations, this article proposes a novel cross-domain online fault diagnosis framework (CDODF). The framework leverages the contrastive language-image pretraining (CLIP) model to extract robust, domain-invariant features from limited fault data. To further enable cross-domain adaptation without costly fine-tuning, a lightweight Adapter module is introduced, which incorporates few-shot learning and online adaptation to target-domain features. Moreover, CDODF supports a continuous learning strategy that dynamically updates the model using accumulated target-domain data, ensuring long-term adaptability and diagnostic accuracy. Experimental results across scenarios, including cross-working conditions, cross-device diagnosis, and emerging fault types, show that CDODF consistently outperforms existing deep learning (DL), TL, and few-shot methods.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.9,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145036727","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}
Weixin Xu;Penghua Zhai;Zhongwei Bian;Yao Fu;Yukun Wu;Chaojuan Yang;Jie Tian;Wei Mu
{"title":"Rethinking the Fourier Transform: Frequency Split-Enhance Network for Fast System Matrix Calibration in Magnetic Particle Image","authors":"Weixin Xu;Penghua Zhai;Zhongwei Bian;Yao Fu;Yukun Wu;Chaojuan Yang;Jie Tian;Wei Mu","doi":"10.1109/TIM.2025.3606035","DOIUrl":"https://doi.org/10.1109/TIM.2025.3606035","url":null,"abstract":"Magnetic particle imaging (MPI) is an emerging molecular tomographic technique known for its high sensitivity and spatiotemporal resolution. Typically, high-quality images are obtained using the system matrix (SM)-based reconstruction method. Unlike other tomographic methods, SM calibration in MPI requires a time-consuming process to measure voxel-level responses across the MPI scanner’s field of view. Since the image resolution is directly affected by the size of the SM, the need for full-size SM calibration presents challenges for practical applications. This issue is further compounded by the necessity for repeated recalibration when changes occur in the tracer’s characteristics or the magnetic field environment. Consequently, efficient and rapid SM calibration is crucial. Existing calibration approaches often assume that each voxel in the SM is independent, overlooking the intrinsic relationships between voxels and their frequency-domain sparsity. To address this, we propose a novel framework dubbed frequency split-enhance network (FSE-Net), wherein the Fourier transform driven feature modulation block, the frequency split-enhance module (FSEM), is introduced to simultaneously split and enhance high- and low frequency features in distinct ways. By effectively capturing and utilizing frequency-domain features from a low-resolution (LR) SM obtained through fast sparse sampling, FSE-Net bridges the gap between LR and high-resolution (HR) volumetric images, achieving HR images with accurate shapes and refined textures. Extensive experiments on widely used OpenMPI public benchmark and simulation datasets demonstrate that our FSE-Net outperforms existing methods, achieving state-of-the-art performance in SM calibration tasks. Furthermore, FSE-Net significantly improves the resolution of an in-house field-free point (FFP) MPI system without requiring time-consuming full-size SM calibration, providing an efficient and practical solution for real-world applications.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.9,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050809","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":"Position-Aware Self-Supervised Learning for Wafer Map Defect Pattern Recognition","authors":"Wei Yuan;Jinda Yan;Minghao Piao","doi":"10.1109/TIM.2025.3606012","DOIUrl":"https://doi.org/10.1109/TIM.2025.3606012","url":null,"abstract":"Wafer map defect pattern recognition is an indispensable component of semiconductor manufacturing, providing crucial information for identifying the root causes of defects in semiconductor production. In recent years, to address the overreliance on labeled data in supervised learning approaches, some efforts have introduced the concept of self-supervised learning into wafer map defect pattern recognition. However, these studies often ignore the significant data characteristics related to the spatial location of defect clusters on the wafer map itself. To address this issue, we designed an RingDistanceConv (RDConv) module to consider the impact of two types of position information—coordinates and distances—on wafer map defect recognition and proposed the position-aware self-supervised learning framework. Our framework achieved an accuracy of 96.41% on the WM-811K dataset with eight defect classes.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.9,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145036797","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":"EWHT-AIB: Enhanced Waist-Mounted Human Tracking Framework Based on Array IMU and Barometer","authors":"Feifan Lin;Qingzhong Cai;Yue Yu;Huizheng Yuan","doi":"10.1109/TIM.2025.3604120","DOIUrl":"https://doi.org/10.1109/TIM.2025.3604120","url":null,"abstract":"With the development of the Internet of Things (IoT) and artificial intelligence (AI), indoor location-based services have become an indispensable part of public daily life. The performance of 3-D indoor positioning is constrained by the low performance of consumer-grade micro-electromechanical systems (MEMS) inertial measurement unit (IMU), the lack of effective calibration for the barometer, and the poor adaptability to complex human motion modes. To address the above challenges, this article proposes an enhanced waist-mounted human tracking framework based on array IMU and barometer (EWHT-AIB) that combines array IMU data fusion, precise barometer calibration, and a motion-constrained position-attitude update algorithm to achieve robust and accurate indoor positioning. To enhance array IMU data fusion performance, a weighted data fusion algorithm for array IMU based on the bias instability coefficients is proposed to achieve effective weighted fusion of array IMU data. Subsequently, a barometer calibration algorithm based on nonlinear fitting is proposed to achieve accurate compensation for bias error and scale factor error of the barometer. Finally, a position-attitude update algorithm under motion constraints is designed to achieve accurate pedestrian 3-D indoor positioning using compensated array IMU and barometer data. Comprehensive experiments demonstrate that the proposed EWHT-AIB framework can achieve meter level positioning accuracy under typical indoor environments.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.9,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145036925","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":"A Shapley Value-Based Method for Formulating Physical Mechanism Semantics of Signal Sequences in Interpretable Fault Diagnosis","authors":"Zhen Wang;Guangjie Han;Li Liu;Yuanyang Zhu;Yilixiati Abudurexiti","doi":"10.1109/TIM.2025.3606044","DOIUrl":"https://doi.org/10.1109/TIM.2025.3606044","url":null,"abstract":"Despite significant advancements in deep learning (DL) for fault diagnosis, the black-box nature of DL models hinders their reliable deployment in industrial applications. Interpretability methods have emerged to address this opacity, yet their effectiveness remains limited due to the lack of unified semantic guidance. This semantic gap not only constrains their practical application but also creates a disconnect between post hoc model explanations and ante hoc model guidance. In addition, the absence of quantitative metrics makes it challenging to evaluate the trustworthiness of interpretability methods. To address these challenges, this article proposes a signal semantic evaluation strategy (SSES), establishing a unified semantic framework. SSES employs Shapley values to evaluate significant signal components in the frequency domain. By integrating physical mechanisms, SSES enhances evaluation accuracy and formulates interpretable fault semantics. Furthermore, adversarial training and model ensemble strategies are employed to enhance the evaluation stability. To assess the reliability of interpretability methods, we introduce two metrics that quantify the consistency between constructed semantics and actual semantics. Experiments on two public datasets demonstrate that SSES accurately identifies significant signal components, while the proposed metrics effectively quantify interpretation reliability. Experiments on the XJTU-SY and Case Western Reserve University (CWRU) datasets demonstrate that SSES accurately identifies significant signal components and achieves the highest diagnostic accuracy under noise interference, reaching 86.7% and 99.1% at 0 dB noise level, respectively. In addition, the proposed reliability metrics effectively quantify interpretation reliability, showing that models with higher reliability scores exhibit superior robustness to noise.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-16"},"PeriodicalIF":5.9,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027997","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":"A UAV-Based Measurement System for Aircraft Skin Defect Detection Using a State-Space Model Approach","authors":"Mengyao Feng;Yuanming Xu;Wei Dai;Haibo Luo","doi":"10.1109/TIM.2025.3606070","DOIUrl":"https://doi.org/10.1109/TIM.2025.3606070","url":null,"abstract":"This article presents an unmanned aerial vehicle (UAV)-based vision measurement system for real-time aircraft skin defect detection. Existing small-target detection algorithms often rely on transformer architectures, which, despite their accuracy, suffer from high computational complexity. To address this, we propose a novel object detection approach based on a learned neural state-space model (SSM), where image features are represented as latent dynamic systems governed by recurrent state updates rather than attention mechanisms. Experimental results show performance gains over You Only Look Once (YOLO) v8, with improvements of 2.1%, 8.1%, and 1.7% in precision, recall, and mAP50, respectively. The proposed model processes a single <inline-formula> <tex-math>$640 times 640$ </tex-math></inline-formula> frame in 4.2 ms (<inline-formula> <tex-math>$approx 238$ </tex-math></inline-formula> FPS) on an RTX 4090, demonstrating that while primarily improving detection accuracy, its linear-time complexity still ensures the real-time processing capability required for UAV-based inspection. Field tests on helicopters and transport aircraft confirm the system’s robustness, repeatability, and practical value for structural health monitoring. This work contributes a lightweight, efficient vision-based instrumentation solution incorporating dynamic modeling into the measurement process.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.9,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145078635","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":"A Taxonomic Review of Polarization Direction Metrology: From Rotating Malus to Vortex Devices","authors":"Chenning Shan;Xinyun Zhu;Bei Zhang;Jianhua Shi;Qiushi Zhang","doi":"10.1109/TIM.2025.3606026","DOIUrl":"https://doi.org/10.1109/TIM.2025.3606026","url":null,"abstract":"Polarization direction (PD) measurement of linearly polarized light is critical for applications ranging from biomedical diagnostics to aerospace navigation. While traditional rotating-element methods based on Malus’ law remain dominant due to their simplicity, they face limitations in speed, accuracy, and mechanical stability. In recent decades, significant advances have been made in non-rotating approaches, including electromagnetic modulation, Faraday rotation systems, and vortex phase retarders enabled by nanofabrication. However, the transition from laboratory prototypes to field-deployable solutions is hindered by disciplinary barriers and the absence of standardized performance benchmarks. This review provides a systematic taxonomy of PD measurement techniques, categorizing them into relative (e.g., optical rotation detection) and absolute (e.g., celestial navigation) measurement paradigms. We analyze six key methodologies—mechanical rotation, electromagnetic modulation, Faraday systems, space-variant polarizers, metasurface, and vortex devices—with comparative evaluation of their accuracy, measurement principles, mathematical models behind them, temporal resolution, and implementation complexity. By establishing cross-disciplinary connections between measurement physics and engineering requirements, this work serves as a roadmap for selecting optimal PD sensing configurations in emerging application scenarios and accelerating the adoption of next-generation polarization metrology solutions.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-13"},"PeriodicalIF":5.9,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073419","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":"In Situ Evaluation and Efficient Suppression of Magneto-Optical Misalignment in K–Rb–21Ne Comagnetometers","authors":"Longyan Ma;Haoying Pang;Xiaohan Ge;Ye Liu;Jiale Quan;Hao Xia;Zhihong Wu;Lihong Duan;Xusheng Lei;Wei Quan","doi":"10.1109/TIM.2025.3606058","DOIUrl":"https://doi.org/10.1109/TIM.2025.3606058","url":null,"abstract":"This study investigates the impact of magneto-optical misalignment on atomic spin responses in a spin-exchange relaxation-free (SERF) comagnetometer and proposes a method to measure and compensate for misalignment angles. By analyzing nuclear spin precession under varying bias magnetic field strengths, both the nuclear spin equivalent magnetic field (<inline-formula> <tex-math>$B_{n}$ </tex-math></inline-formula>) and the misalignment angle <inline-formula> <tex-math>$theta $ </tex-math></inline-formula> between the pump beam and the main magnetic field are extracted. To suppress the identified misalignment, a novel alignment technique based on periodic strong magnetic field pulses is introduced. This method enables rapid in situ adjustment of the pump beam direction, thereby enhancing nuclear spin self-compensation and overall system performance. Experimental validation demonstrates that the proposed approach improves the suppression of transverse magnetic field interference, with a 43.2% enhancement in magnetic response attenuation. Additionally, magneto-optical alignment optimization results in marked improvements in system stability and sensitivity: the Allan deviation at 100 s is reduced by 34%, and the inertial measurement noise at 1 Hz decreases by 43.3%, achieving a sensitivity of <inline-formula> <tex-math>$3.56times {10^{ - 6}}{{mathrm { }}^{circ } }/text {s}/sqrt {text {Hz}}$ </tex-math></inline-formula>.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.9,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145061872","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}
Salvador Andrés;Carlos Heras;Andrés Ocabo;Jorge Lanzuela;Rubén Martínez;Asier Villafranca;Iñigo Salinas;Rafael Alonso
{"title":"FMCW Radar for 3-D Tracking Based on MLBI Interferometer and MDS Estimation","authors":"Salvador Andrés;Carlos Heras;Andrés Ocabo;Jorge Lanzuela;Rubén Martínez;Asier Villafranca;Iñigo Salinas;Rafael Alonso","doi":"10.1109/TIM.2025.3604971","DOIUrl":"https://doi.org/10.1109/TIM.2025.3604971","url":null,"abstract":"This article presents the implementation of a C-band frequency-modulated continuous wave (FMCW) radar system, utilizing software-defined radio (SDR) hardware and integrated with a five-element multilong-baseline interferometer (MLBI) receiver, for the detection and 3-D tracking of passive moving targets. A key aspect is the generation of a low jitter, high signal-to-noise-and-distortion ratio (SINAD) signal, which significantly enhances the radar’s performance for angle of arrival (AoA) detection and micro-Doppler signature (MDS) estimation. The high signal quality achieved enables the detection and 3-D tracking of low radar cross-sectional (RCS) targets, such as small drones, at distances up to 800 m without requiring high radar power. In addition, this work demonstrates the effectiveness of a simple phase line assignment algorithm to mitigate errors in the AoA measurement of passive moving targets even when the MLBI geometry deviates from its optimal configuration. The performance of the radar system was evaluated in an open-field test using a DJI Mavic 3, and the results highlight the significant potential of this radar concept for medium-cost 3-D tracking and MDS identification applications.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-7"},"PeriodicalIF":5.9,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11151814","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145090043","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}
Chichao Cheng;Guangming Wang;Yin-Dong Zheng;Lu Liu;Hesheng Wang
{"title":"MonoPCFlow: Enabling Efficient Scene Flow Estimation From Monocular View","authors":"Chichao Cheng;Guangming Wang;Yin-Dong Zheng;Lu Liu;Hesheng Wang","doi":"10.1109/TIM.2025.3600732","DOIUrl":"https://doi.org/10.1109/TIM.2025.3600732","url":null,"abstract":"Scene flow captures the dynamic changes of points in a 3-D scene, essential for understanding motion in physical environments. Light detection and ranging (LiDAR)-based scene flow estimation methods face challenges related to resolution, refresh rate, and cost. In contrast, monocular image-based methods estimate optical flow and depth separately at different stages. This fragmented approach inevitably compromises spatial–temporal consistency and introduces error accumulation. We propose monocular point cloud FlowNet (MonoPCFlow), a novel framework for scene flow estimation directly from a pair of consecutive monocular images. We integrate pseudo-LiDAR representations with dense 3-D scene flow estimation, effectively bridging the 2-D-to-3-D domain gap for monocular motion analysis. We develop a depth-enhanced refinement module that mitigates information loss in pseudo-LiDAR generation, preserving critical geometric and appearance features to improve scene flow accuracy. Experimental validation demonstrates MonoPCFlow’s superior performance, achieving 37.0% (FlyingThings3D) and 39.7% Karlsruhe Institute of Technology and Toyota Institute of Technology (KITTI) relative reductions in endpoint-error compared to contemporary benchmarks.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-10"},"PeriodicalIF":5.9,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145051000","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}