IEEE Transactions on Instrumentation and Measurement最新文献_第2页

Parallelization Strategy of Laser Stripe Center Extraction for Structured Light Measurement 结构光测量激光条纹中心提取的并行化策略

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-06-20 DOI: 10.1109/TIM.2025.3581633

Tao Ye;Xiangpeng Deng;Guopeng Liu;Wei Chen

{"title":"Parallelization Strategy of Laser Stripe Center Extraction for Structured Light Measurement","authors":"Tao Ye;Xiangpeng Deng;Guopeng Liu;Wei Chen","doi":"10.1109/TIM.2025.3581633","DOIUrl":"https://doi.org/10.1109/TIM.2025.3581633","url":null,"abstract":"Structured light, known for its high precision and noncontact advantages, is widely used in the fields of 3-D reconstruction and object measurement. The extraction of the light stripe center line has a significant impact on the high-precision measurement of structured light. However, traditional geometric approaches and gray centroid methods often struggle to reliably extract the stripe center, while Steger’s subpixel method is hindered by intensive computational demands, making real-time applications challenging. To address these limitations while ensuring the accuracy of laser stripe center extraction, we propose a parallelization strategy for the Steger algorithm, addressing the challenges associated with high-computational load. The proposed method consists of three key components. First, a perspective projection model acts as a filter, transforming high-resolution images into a lower resolution format, thus lightening the load when identifying the region of interest (ROI). The purpose of this step is to enable laser stripe positioning. Second, we enhance the Gaussian convolutional process by implementing a separable convolutional technique, which decomposes 2-D convolution into two 1-D convolutions, thus lowering computational complexity. Finally, we adopt a dual-layer heterogeneous parallel computing mode, where laser stripe positioning and center extraction tasks are executed in parallel across CPU threads, with each thread utilizing the GPU for computation, enhancing operational efficiency by promoting in-depth collaboration between CPU and GPU. Through extensive experiments, our method demonstrates subpixel-level extraction capabilities in high-resolution laser stripe images, significantly improving execution speed while maintaining extraction accuracy. The findings indicate that the proposed approach has significant real-time application potential in the field of stripe center extraction and lays a solid foundation for improving the measurement precision of structured light.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Noncoplanar Positive Compensation Decoupling Technology in a Small-Loop Transient Electromagnetic System 小回路瞬变电磁系统的非共面正补偿解耦技术

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-06-20 DOI: 10.1109/TIM.2025.3579831

Yitong Shi;Lihua Liu;Dengke He;Jiangjie Huang;Jiankai Li;Shichu Yan;Guangyou Fang

{"title":"Noncoplanar Positive Compensation Decoupling Technology in a Small-Loop Transient Electromagnetic System","authors":"Yitong Shi;Lihua Liu;Dengke He;Jiangjie Huang;Jiankai Li;Shichu Yan;Guangyou Fang","doi":"10.1109/TIM.2025.3579831","DOIUrl":"https://doi.org/10.1109/TIM.2025.3579831","url":null,"abstract":"In the transient electromagnetic method (TEM), the early primary field signals can interfere with the secondary field signals due to the turn-off time and mutual inductance between the transmitting and receiving coils, resulting in a shallow blind area. This primary field coupling interference (PFCI) is particularly pronounced when using a multiturn, small-loop coil structure, which significantly limits TEM’s effectiveness in near-surface detection. To address this issue, several decoupling techniques have been proposed. Among them, the off-center self-compensation technology is considered effective and has been applied in systems such as airborne TEM. However, this approach has drawbacks because it is susceptible to primary field remanence caused by structural errors, and its eccentric design results in inadequate detection capabilities and lateral resolution. To overcome these limitations, we proposed a new noncoplanar positive compensation decoupling technology. This device enhances structural stability by positioning a positive compensation coil coaxially with the transmitting coil and coplanar with the receiving coil. Additionally, the positive compensation coil effectively enhances the device’s shallow detection capability by both reducing the relative horizontal distance between the transmitting and receiving coils and providing stronger shallow excitation signals. Simulation and field experiment results demonstrate the effectiveness of the new device.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.6,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Image Visibility Patch-Aided Partial Discharge Recognition Framework for Identifying Defects in XLPE Cables 基于图像可视性贴片辅助的XLPE电缆局部放电缺陷识别框架

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-06-20 DOI: 10.1109/TIM.2025.3581664

Sayanjit Singha Roy;Ashish Paramane;Jiwanjot Singh;Soumya Chatterjee

{"title":"Image Visibility Patch-Aided Partial Discharge Recognition Framework for Identifying Defects in XLPE Cables","authors":"Sayanjit Singha Roy;Ashish Paramane;Jiwanjot Singh;Soumya Chatterjee","doi":"10.1109/TIM.2025.3581664","DOIUrl":"https://doi.org/10.1109/TIM.2025.3581664","url":null,"abstract":"Partial discharge (PD) is a critical degradation phenomenon in cross-linked polyethylene (XLPE)-insulated polymeric power cables, which is responsible for premature failure if left unattended. Therefore, accurately identifying PD defects is essential to prevent such incidents in the XLPE cable. This study proposes a novel image visibility graph (IVG) theory-aided phase-resolved PD (PRPD) pattern analysis and recognition framework employing an optimally tuned bi-directional long short-term memory (bi-LSTM) classifier for automated PD detection. To this end, several PD defects have been synthetically emulated inside an 11-kV XLPE cable, and the PD signals corresponding to each type of defect are measured using an HFCT sensor. From the obtained HFCT data, the PRPD patterns were generated, which were converted into connected graphs using IVG. Moreover, image visibility patches (VPs) were computed from the graph-converted PRPD plots to quantify the intricate pixel-level changes due to altering discharge patterns. Following that, the frequency of occurrences (FOCs) of the unique visibility codes was computed from the extracted VPs. The visibility features were further employed to train the bi-LSTM classifier for PD defect identification, which yielded high accuracy. Ablation studies with classical convolutional neural network (CNN) models and comparison with previously reported state-of-the-art methods also revealed superior efficiency of the proposed PD detection methodology, suggesting its potential application for automated health monitoring of XLPE cable insulation.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-10"},"PeriodicalIF":5.6,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating Ordinary Differential Equations With Sparse Attention for Power Load Forecasting 基于稀疏关注的常微分方程积分的电力负荷预测

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-06-20 DOI: 10.1109/TIM.2025.3581667

Jiacheng Li;Wei Chen;Yican Liu;Junmei Yang;Zhiheng Zhou;Delu Zeng

{"title":"Integrating Ordinary Differential Equations With Sparse Attention for Power Load Forecasting","authors":"Jiacheng Li;Wei Chen;Yican Liu;Junmei Yang;Zhiheng Zhou;Delu Zeng","doi":"10.1109/TIM.2025.3581667","DOIUrl":"https://doi.org/10.1109/TIM.2025.3581667","url":null,"abstract":"Accurate load forecasting plays an essential role in the measurement, monitoring, and control frameworks of modern power systems, particularly given the continuous influx of high-resolution data from advanced metering devices. Traditional forecasting methods often struggle due to the inherent nonstationarity and multiscale dynamics observed in these data streams. To address these challenges, this article introduces EvolvInformer, a novel long-sequence forecasting framework that integrates ordinary differential equations (ODEs) solver within a ProbSparse self-attention decoder architecture. The ODE module provides a physics-inspired, continuous-time representation of hidden state dynamics, enabling the model to capture subtle fluctuations and abrupt regime shifts commonly found in instrumented load profiles. Comprehensive experiments conducted on five large-scale power load datasets demonstrate that EvolvInformer achieves a 29.7% reduction in mean-squared error (mse) compared to state-of-the-art baseline models while preserving the logarithmic memory complexity characteristic of ProbSparse attention. Moreover, EvolvInformer consistently models both global trends and localized transient phenomena under stringent computational constraints, making it particularly suitable for embedded and edge-based metering applications. By effectively coupling continuous-time modeling via ODE with an efficient sparse attention mechanism for long-sequence forecasting, EvolvInformer provides a robust and scalable solution for measurement-centric load prediction tasks, with broad potential applications in adaptive energy management, grid load forecasting, and metering data quality assessment.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.6,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rapid Mueller Matrix Holographic Microscopy Imaging for Polarization Sensitive Materials 偏振敏感材料的快速穆勒矩阵全息显微成像

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-06-19 DOI: 10.1109/TIM.2025.3580876

Xintian Yu;Lei Liu;Zhi Zhong;Lei Yu;Qing Dong;Bei Lu;Nan Li;Mingguang Shan

{"title":"Rapid Mueller Matrix Holographic Microscopy Imaging for Polarization Sensitive Materials","authors":"Xintian Yu;Lei Liu;Zhi Zhong;Lei Yu;Qing Dong;Bei Lu;Nan Li;Mingguang Shan","doi":"10.1109/TIM.2025.3580876","DOIUrl":"https://doi.org/10.1109/TIM.2025.3580876","url":null,"abstract":"Mueller matrix polarimetry (MMP) is a powerful technique employed in various fields, such as biomedical optics, material science, and remote sensing. However, existing MMP techniques typically require multiple exposures (12 or more), which compromises measurement efficiency and increases susceptibility to errors. In this study, a rapid Mueller matrix holographic microscopy (RMHM) was proposed for extracting the complete <inline-formula> <tex-math>$4times 4$ </tex-math></inline-formula> Mueller matrix (MM) of polarization-sensitive materials. Based on an off-axis digital holography (DH) interferometer, the geometric phase is determined to reconstruct the MM using the Pancharatnam-Berry (PB) phase theory and a division algorithm. Our method retains the advantages of existing DH techniques, requiring only three acquisitions to capture the complete MM. The proposal is validated through the application of a rotating quarter-wave plate (QWP), followed by the measurement of polarization parameters including circular and linear retardance, depolarization, and the birefringent fast-axis angle. The analysis covers various materials, such as plant roots, potato starch granules, and pathological lung cancer tissues.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multivariate Variable-Step Multiscale Extended Dispersion Entropy-Based Lempel–Ziv Complexity and Its Application in Fault Diagnosis 基于多元变步多尺度扩展色散熵的Lempel-Ziv复杂度及其在故障诊断中的应用

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-06-19 DOI: 10.1109/TIM.2025.3580860

Yuxing Li;Xuanming Cheng;Junxian Wu;Yan Yan

{"title":"Multivariate Variable-Step Multiscale Extended Dispersion Entropy-Based Lempel–Ziv Complexity and Its Application in Fault Diagnosis","authors":"Yuxing Li;Xuanming Cheng;Junxian Wu;Yan Yan","doi":"10.1109/TIM.2025.3580860","DOIUrl":"https://doi.org/10.1109/TIM.2025.3580860","url":null,"abstract":"Extended dispersion entropy-based Lempel–Ziv complexity (EDELZC) can measure the irregularity or chaos of single-channel time series, which is one of the ideal tools for extracting fault features from rotating machinery. However, EDELZC is only suitable for single-scale and single-channel time-series analysis, which affects the effective extraction of fault features. To solve this problem, the multivariate embedding and variable-step multiscale techniques are integrated, and the multivariate variable-step multiscale EDELZC (MvVSMEDELZC) is developed, which achieves the characterization of multichannel feature information at different time scales. Moreover, in order to improve the recognition accuracy, the crayfish optimization algorithm (COA) is applied to optimize the parameters of the kernel extreme learning machine (KELM), and a new fault diagnosis method is proposed in combination with MvVSMEDELZC. The simulated signal experiments verify the ability of MvVSMEDELZC to detect dynamic changes in complex signals. The practical rotating machinery fault diagnosis experiments show that compared with other methods, the proposed fault diagnosis method offers superior accuracy and efficiency in identifying the condition of bearings and gears, which indicates its superior performance in properties in diagnosing rotating machinery faults.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.6,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Test Optimization Selection for Fault Detection and Isolation Under Multivariable and Multifault Scenarios 多变量多故障场景下故障检测与隔离的试验优化选择

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-06-19 DOI: 10.1109/TIM.2025.3579828

Xiuli Wang;Dongdong Xie;Defeng He;Yang Li;Hongtian Chen;Haowei Wang

{"title":"Test Optimization Selection for Fault Detection and Isolation Under Multivariable and Multifault Scenarios","authors":"Xiuli Wang;Dongdong Xie;Defeng He;Yang Li;Hongtian Chen;Haowei Wang","doi":"10.1109/TIM.2025.3579828","DOIUrl":"https://doi.org/10.1109/TIM.2025.3579828","url":null,"abstract":"Test optimization selection (TOS) is a crucial technology in testability design, playing a key role in intelligent manufacturing by enhancing product maintainability and reliability while reducing life-cycle costs. As intelligent manufacturing systems demand higher reliability and efficiency, effective TOS methods are essential for ensuring real-time fault diagnosis and predictive maintenance. However, existing TOS methods inadequately account for correlations between test outcomes in metrics modeling and offer limited solutions to the low fault isolation rate (FIR) caused by multiple faults. An innovative TOS approach is developed by considering fault detection rate (FDR) and FIR metrics via the D-vine copula and Bhattacharyya coefficient method, along with an improved binary particle swarm optimization (DVBC-IBPSO) method to minimize the number of required test points. First, the D-vine copula method is introduced to model test metrics, effectively capturing strong correlations between test outcomes. Second, considering the ambiguity group problem induced by multiple faults, a DVBC combined method is developed to quantify the similarity between fault distributions and model the FIR metric. Third, leveraging the constructed test metrics models, an IBPSO algorithm is employed by incorporating a newly designed objective function that selects the most cost-effective test points while ensuring FDR and FIR remain within acceptable thresholds. The proposed method enhances the reliability and efficiency of intelligent manufacturing systems by optimizing fault diagnosis processes and improving overall system health management. Its validity is established through experimental studies on one commonly used critical circuit in industrial systems.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.6,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144481904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bionic Seal Whisker Triboelectric Sensor for Underwater Multiobject Wake Perception 水下多目标尾迹感知仿生海豹须摩擦电传感器

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-06-19 DOI: 10.1109/TIM.2025.3580836

Jianhua Liu;Siyuan Wang;Yuanzheng Li;Ziyue Xi;Hao Jin;Peng Xu;Minyi Xu

{"title":"Bionic Seal Whisker Triboelectric Sensor for Underwater Multiobject Wake Perception","authors":"Jianhua Liu;Siyuan Wang;Yuanzheng Li;Ziyue Xi;Hao Jin;Peng Xu;Minyi Xu","doi":"10.1109/TIM.2025.3580836","DOIUrl":"https://doi.org/10.1109/TIM.2025.3580836","url":null,"abstract":"Existing underwater flow field sensing techniques encounter significant challenges in complex and variable flow environments. Seals possess a highly sensitive whisker sensing system that enables them to perform tasks such as predation and environment sensing. Drawing inspiration from the hydrodynamic tactile function of seal whiskers, this article introduces a bionic whisker triboelectric sensor (BWTS) that integrates whisker-based sensing mechanisms with triboelectric nanogenerator technology. The BWTS features a wavy bionic whisker and a flexible bionic follicle structure embedded with four sensing units. It is verified through simulation and experimental analysis that the BWTS can effectively capture the wake field characteristics of stationary and moving underwater objects under different flow field parameters. The BWTS demonstrates high reliability, achieving correlation coefficients of 0.98–0.99 for the geometrical and kinematic parameters of underwater objects. The error is less than 10%. Additionally, its strong directional recognition and flow field feature sensing capabilities have been validated. As a noncontact underwater flow field sensing technology, BWTS will provide an innovative approach to enhance the sensing capability of underwater vehicles.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-10"},"PeriodicalIF":5.6,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144500956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multifault Feature Wasserstein Generative Adversarial Networks for Fault Diagnosis in Unbalanced Data 多故障特征Wasserstein生成对抗网络在非平衡数据中的故障诊断

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-06-18 DOI: 10.1109/TIM.2025.3580880

Weibo Ren;Zhijian Wang;Zhongxin Chen;Shun Zhao;Lei Dong;Yanfeng Li;Xin Fan

{"title":"Multifault Feature Wasserstein Generative Adversarial Networks for Fault Diagnosis in Unbalanced Data","authors":"Weibo Ren;Zhijian Wang;Zhongxin Chen;Shun Zhao;Lei Dong;Yanfeng Li;Xin Fan","doi":"10.1109/TIM.2025.3580880","DOIUrl":"https://doi.org/10.1109/TIM.2025.3580880","url":null,"abstract":"Due to the limitation of industrial conditions in production, raw sensor data are always shown as an unbalanced dataset, characterized by abundant normal operational data and scarce fault instances. This unbalance can degrade the performance of conventional fault diagnosis methods, leading to reduced accuracy and unstable model training. To address this challenge in bearing fault diagnosis, this article proposes a multifault feature Wasserstein generative adversarial network (MFF-WGAN) to enhance diagnostic precision. First, the framework employs a multiencoder denoising autoencoder (DAE) architecture to mitigate noise interference in raw sensor data. Subsequently, the proposed MFF-WGAN integrates label information into its adversarial loss function to enable simultaneous generation of diverse fault categories, while incorporating interclass feature discrepancies to refine sample quality. Finally, the developed multifault feature Wasserstein generation adversarial network is tested on the Case Western Reserve University bearing dataset and the laboratory bearing dataset. Computational results show that the proposed method can generate high-quality bearing samples with multiple faults effectively, which can obtain a higher diagnosis accuracy of 99.01% and 97.71% compared with the existing methods.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-9"},"PeriodicalIF":5.6,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Joint Distribution Alignment via Mutual Information for Cross-Device Fault Diagnosis 基于互信息的跨设备故障诊断联合分布对齐

IF 5.6 2区工程技术

IEEE Transactions on Instrumentation and Measurement Pub Date : 2025-06-18 DOI: 10.1109/TIM.2025.3580817

Lexuan Shao;Ningyun Lu;Bin Jiang;Jianhua Lv;Silvio Simani

{"title":"Joint Distribution Alignment via Mutual Information for Cross-Device Fault Diagnosis","authors":"Lexuan Shao;Ningyun Lu;Bin Jiang;Jianhua Lv;Silvio Simani","doi":"10.1109/TIM.2025.3580817","DOIUrl":"https://doi.org/10.1109/TIM.2025.3580817","url":null,"abstract":"Current data-driven fault diagnosis methods suffer from poor transferability. It is challenging to apply a model effective on one device directly to another. Many methods now employ domain adaptation algorithms to align their fault distributions for model transferability. However, most methods focus only on aligning either marginal or pseudo-labels-based conditional distributions, ignoring cases where both label and conditional distributions change, along with the unreliable nature of pseudo-labels. This oversight can lead to transfer failures. To tackle this, this article introduces an information theory-based joint distribution alignment model. The algorithm starts by maximizing mutual information between predicted categories and input samples for conditional alignment without pseudo-label involvement. Simultaneously, the model introduces virtual adversarial training with a penalty term to improve the robustness of prediction results. When label distribution changes, the model uses entropy values to assign data in categories unique to the target domain to “outliers,” thus preventing misalignment of these data. In experiments, this algorithm outperformed other domain adaptation-based methods.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144519414","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0