IEEE Transactions on Instrumentation and Measurement最新文献

{"title":"Application of a Multimodal Deep Learning Model Based on Recursive Fusion Feature Map With Transformer–TCN for Complex Fault Diagnosis of Flying Wing UAV Actuators","authors":"Wenqi Zhang;Zhenbao Liu;Zhen Jia;Xiao Wang;Weijun Yan;Kai Wang","doi":"10.1109/TIM.2025.3561438","DOIUrl":"https://doi.org/10.1109/TIM.2025.3561438","url":null,"abstract":"This present article proposes a multimodal deep learning model based on recursive feature fusion map (RFFM) and Transformer-temporal convolutional network (TCN), to solve the problem of fault diagnosis of flying wing unmanned aerial vehicle (UAV) actuators under complex working conditions. The challenges of data scarcity, high-dimensional nonlinear dynamic characteristics, and the difficulty of effectively fusing multimodal features are particularly relevant in this context. The recursive fusion feature map is used to extract high-order features from multimodal time-series signals (position, velocity, acceleration, torque, current, and voltage), and the Transformer is used to capture the long-term dependencies of the signals, while the TCN is employed to model short-term dynamic characteristics. This enables accurate classification and health assessment of the flying wing UAV actuator under normal, single fault (wear/jamming, dynamic lag, and signal failure), and compound fault modes. In the simulation experiment, the six-modal time-series signal generated for the seven states was analyzed. The experimental findings demonstrated that the proposed model attained a classification accuracy of 98.6% on the balanced dataset and 94.7% on the unbalanced dataset, with an <inline-formula> <tex-math>$F1$ </tex-math></inline-formula>-score exceeding 0.92 for each category. Concurrently, the model’s resilience to complex fault modes was substantiated through a comparison of residual signals and an examination of time-frequency diagrams. A comparison of the model with traditional methods such as support vector machine (SVM), random forest (RF), and long short-term memory (LSTM) reveals significant advantages in key indicators such as average area under curve (AUC) value, diagnostic accuracy, and classification stability (average AUC value exceeds 0.97). The research results demonstrate the effectiveness and applicability of this method in the complex fault diagnosis of flying wing UAV actuators and have important engineering application value and potential for promotion.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-17"},"PeriodicalIF":5.6,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073348","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":"Motor Bearing Fault Diagnosis Based on LMSWT With Improved Multiscale Convolutional Neural Network","authors":"Yuhang Fan;Zhaoyang Fu;Huan Li;Yue Yang","doi":"10.1109/TIM.2025.3565707","DOIUrl":"https://doi.org/10.1109/TIM.2025.3565707","url":null,"abstract":"Motor bearing fault diagnosis is essential to guarantee production efficiency and safety. Deep learning methods have shown strong performance in diagnosing bearing faults. In this article, an intelligent fault diagnosis method based on the maximum local maximum synchrosqueezing wavelet transform and improved multiscale convolutional neural network (LMSWT-SE-MSCNN) is presented. Local maximum synchrosqueezing wavelet transform (LMSWT) enhances time-frequency energy concentration, addressing the issues of energy dispersion and noise interference in traditional synchrosqueezing wavelet transform (SWT). Multiscale convolutional neural network based on senet attention mechanism (SE-MSCNN) fuses the multiscale information and then uses the channel attention mechanism to extract more effective fault features. The superiority and effectiveness of the method are demonstrated by experimental results on three datasets [Case Western Reserve University (CWRU), PU, Huazhong University of Science and Technology (HUST)] with added high-intensity noise.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144124031","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":"OCT Fingerprint Presentation Attack Detection Based on Dual-Branch Reconstruction Differences","authors":"Haixia Wang;Kun Xiao;Chengfang Zhu;Ronghua Liang;Yilong Zhang;Peng Chen;Yipeng Liu;Rui Yan","doi":"10.1109/TIM.2025.3565107","DOIUrl":"https://doi.org/10.1109/TIM.2025.3565107","url":null,"abstract":"The emergence of optical coherence tomography (OCT) as a noninvasive imaging technique has advanced research in automated fingerprint recognition systems (AFRSs). Several methods leveraging OCT for fingerprint presentation attack detection (PAD) have been proposed, offering promising solutions to enhance the security and reliability of biometric authentication systems. Effectively detecting unknown presentation attacks (PAs), however, remains a challenging issue. A reconstruction-based strategy that requires only bonafide data for training could be a solution to address the issue of data dependency. It detects unknown PAs by computing differences between the input image and the reconstructed image. Two key challenges are, nevertheless, presented in reconstruction-based PAD: style differences introduced during reconstruction and inadequate reconstruction performance when dealing with PA samples, which affect detection performance. In order to tackle these issues, this study proposed a novel dual-branch reconstruction differences-based PAD (RePAD) method for fingerprints captured by OCT. The method consists of two distinct branches: the Recovery branch and the Equality branch. The Recovery branch is specifically designed to enhance the network’s ability to reconstruct any inputs into bonafide-like images. A simulated anomaly module is further introduced to generate abnormal images for participation in network training without any preknowledge of PAs. Meanwhile, the Equality branch and the style difference loss function work together to eliminate any potential bias introduced by variations in image style. The antispoofing score is then calculated based on the reconstruction differences of two branches in terms of B-scan wise and instance wise. This architecture can effectively expand the decision boundary for PAD by enabling more robust differentiation between bonafides and PAs. The proposed method was evaluated using the ZJUT-EIFD public dataset. The results demonstrate that the proposed approach achieves the best performance in terms of both B-scan-wise and instance-wise PAD. Comparative analysis and ablation experiments reveal that the dual-branch structure effectively enhances the reconstruction ability and mitigates style differences caused by reconstruction.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-14"},"PeriodicalIF":5.6,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072884","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":"Design and Validation of a Novel Human–Machine Interface System Based on Multisource Data Fusion","authors":"Lizhi Pan;Chaofan Wang;Zihao Li;Jianchang Zhao;Chi Zhang;Jianmin Li","doi":"10.1109/TIM.2025.3565342","DOIUrl":"https://doi.org/10.1109/TIM.2025.3565342","url":null,"abstract":"Conventional human-machine interface (HMI) systems generally take surface electromyography (sEMG) as the only signal source, which often faces the problem of multichannel crosstalk. To enhance HMI performance, this study introduces a novel three-degree-of-freedom (3-DOF) HMI system for surgical robot control, which integrates sEMG signals and inertial measurement unit (IMU) signals. A cost-effective wearable HMI hardware system is designed to address the high price and poor portability of existing commercial equipment, which also has a higher signal-to-noise ratio (SNR) of 35.9 dB. Based on the proposed simultaneous and proportional control (SPC) strategy, ten subjects were recruited to conduct an online experiment involving four upper limb postures to assess the real-time performance of the HMI system. In addition, six able-bodied participants participated in a validation experiment to statistically verify and rigorously evaluate the implemented HMI system. The experimental results demonstrate that our HMI system can accurately decode the angles of the wrist and metacarpophalangeal (MCP) joints in both single-DOF and 3-DOF movements, achieving stable control and robust online performance. Furthermore, the proposed HMI system was applied to a flexible endoscopic robot to realize remote SPC, and the results indicate that it can perform well in the practical application. The current study proves the feasibility and practicability of multisource data fusion for HMI, providing a new direction.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-16"},"PeriodicalIF":5.6,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073420","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 Novel Wind Turbine Pitch Bearing Fault Diagnosis Using Signal Encoding and Attention Mechanism Dual-Channel Parallel Fusion Network","authors":"Chen Chang;Jiuyuan Huo;Tian Xie;Yuyu Meng","doi":"10.1109/TIM.2025.3565253","DOIUrl":"https://doi.org/10.1109/TIM.2025.3565253","url":null,"abstract":"As the core component of wind turbine (WT) pitch system, pitch bearing plays an important role in the continuous safe and stable operation of WTs. However, pitch bearing fault diagnosis (PBFD) has problems such as poor diagnostic performance and low accuracy caused by strong random noise interference, small samples and variable operating conditions. For this reason, this article presents a wind turbine pitch bearing fault diagnosis approach continuous wavelet transform (CWT)-position matrix transform (PMT)-attention mechanism dual-channel parallel fusion network (ADCPFN) using signal encoding and attention mechanism dual-channel parallel fusion network. First, the CWT and PMT are utilized to encode the signals caused by vibration into time–frequency diagrams and position matrix diagrams, respectively, so as to boost the signal’s feature information by expanding the data’s visualization dimension. Second, the ADCPFN is constructed using both global and sliding window attention mechanisms to capture both global and local features in the signal-coded image data. The dual-channel parallel network structure enables the model to adequately learn various levels of feature information to suppress the interference of strong random noise on the identification of the health state of the pitch bearing. Finally, in order to verify the advantages and efficacy of the suggested approach, case studies of bearing fault diagnosis toward small samples and variable operating conditions under strong random noise were carried out, and application tests were carried out with real pitch bearing vibration data. The findings demonstrate that the presented approach performs better and has greater diagnostic accuracy when compared to the current mainstream approaches.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-15"},"PeriodicalIF":5.6,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929680","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":"Multi-Incremental Learning-Based Predictive Modeling for Unknown Distributed Parameter Systems Under Larger Working Region","authors":"Tianyue Wang;Han-Xiong Li","doi":"10.1109/TIM.2025.3563052","DOIUrl":"https://doi.org/10.1109/TIM.2025.3563052","url":null,"abstract":"Distributed parameter systems (DPS) are broadly present in numerous industrial manufacturing systems. Accurate modeling of DPS is critical for subsequent process monitoring and optimization. However, conventional modeling methods often ignore the larger working region in complex DPS. Besides, the inherent time-varying dynamic behavior of the system also brings challenges to spatiotemporal modeling. In this article, a new multi-incremental learning-based predictive modeling approach is proposed to solve the above concerns. First, the larger global working region is adaptively decomposed into multiple subspaces to extract local dynamics hierarchically. Then, a spatiotemporal forgetting-based incremental modeling method is further designed to cope with time-varying dynamics of local subspace. Finally, the global dynamic model is ensembled via multiple locally weighted incremental models to enhance modeling performance. Experiments on an industrial curing system demonstrated the effectiveness and superiority of the proposed modeling approach.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-8"},"PeriodicalIF":5.6,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902645","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":"Discovering Invariance From Variations: Invariant-Specific Bi-Graph Neural Network for Multisource Transfer Learning With Application to Industrial Soft Sensor","authors":"Jiayi Ren;Chunhui Zhao","doi":"10.1109/TIM.2025.3565340","DOIUrl":"https://doi.org/10.1109/TIM.2025.3565340","url":null,"abstract":"Conventional transfer learning offers a feasible solution to address distribution discrepancy by extracting and transferable knowledge from source domains to the target domain. Integrating information from multiple source domains while mitigating the negative transfer caused by distribution discrepancy poses a significant challenge. Instead of aligning the data distribution among different domains, it is observed that enduring invariance lies in the relation among variables. In this article, an invariant-specific Bi-graph neural network (IS-BiGNN) model is proposed to address the aforementioned issue by designing an invariant relation alignment scheme. It is built upon the subsequent observations: 1) despite discrepancy among multidomains, we propose a novel concept wherein the invariant intervariable relation is put forth as the invariant characteristic within each domain and 2) the mentioned relation can be extracted through the learning of graph representations among the variables. To address the existence of both cross-domain invariant and varying relation among variables, a Bi-graph network architecture is designed. The invariant graph network extracts cross-domain transferable relations, whereas the specific graph network captures domain-specific relation among variables. Invariant relation alignment and specific information filtering modules are developed to implement the extraction of invariant relation collaboratively, facilitating knowledge transfer from multiple source domains to the target domain. Furthermore, with theoretical support, the proposed method provides a tighter generalization error bound. The effectiveness of IS-BiGNN is verified by soft sensor as the downstream task on industrial processes.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.6,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929795","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":"Localization for Energy Interconnection Systems With Uncertainties via Maximum Entropy Adaptive Dynamic Programming","authors":"Tianbiao Wang;Huaguang Zhang;Xiyue Guo;Dazhong Ma","doi":"10.1109/TIM.2025.3565241","DOIUrl":"https://doi.org/10.1109/TIM.2025.3565241","url":null,"abstract":"This article addresses the critical challenge of high localization error in long-distance energy interconnection systems (EISs), where conventional methods face significant limitations due to the increased uncertainties of time-dependent information. A novel localization framework is proposed based on the maximum entropy adaptive dynamic programming (MEADP) algorithm to tackle this challenge. This framework transforms the long-distance localization problem into a consistency issue concerning the attenuation of negative pressure waves (NPWs), thereby reducing reliance on time-based information. To address measurement noise, a hybrid data fusion algorithm driven by both model and data is developed to reduce the variance of predicted NPWs using a Kalman filter. At the core of the framework lies the MEADP algorithm, which incorporates entropy regularization in the policy improvement to encourage exploration and prevent convergence to suboptimal solutions. Moreover, the algorithm employs a policy network based on the <inline-formula> <tex-math>$beta $ </tex-math></inline-formula>-distribution, enabling dynamic adjustment of action probabilities to adhere to physical constraints and maintain feasible operational limits. Finally, the proposed framework is validated through experiments with pipelines exceeding 350 km in length.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-9"},"PeriodicalIF":5.6,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924952","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":"Feasibility Study on Using Atomic Gravimeters for Detecting Urban Underground Spaces","authors":"Zhong-Kun Qiao;Peng Yuan;Ruo Hu;Lin-Ling Li;Kan-Xing Weng;Hai-Xiang Yang;Zong-Yu Zhang;Jia-Jun Zhang;Dong Zhu;Xue-Min Wu;Xiao-Long Wang;Bin Wu;Qiang Lin","doi":"10.1109/TIM.2025.3565251","DOIUrl":"https://doi.org/10.1109/TIM.2025.3565251","url":null,"abstract":"Microgravity measurement offers several benefits: it is highly efficient, cost-effective, resistant to interference, and nondestructive. This technique is especially valuable for exploring urban underground spaces and identifying issues such as surface collapses, underground cavities, karst formations, and other geological anomalies. The atomic gravimeter (AG), which is based on atom interferometry, provides high precision, and continuous measurement without drift. It is suitable for detecting urban underground spaces and for long-term monitoring of geological high-risk areas. This study demonstrates the potential of an independently developed AG by Zhejiang University of Technology (ZJUT) for microgravity measurements. It also examines the potential of AG as a local reference for relative gravimeters by performing cross-bridge microgravity profile measurements and validating the results with theoretical model simulations. The estimated sensitivity of the AG without the vibration isolation platform is approximately <inline-formula> <tex-math>$135.1~mu $ </tex-math></inline-formula>Gal/Hz1/2, achieving a resolution of about <inline-formula> <tex-math>$3~mu $ </tex-math></inline-formula>Gal (<inline-formula> <tex-math>$1~mu $ </tex-math></inline-formula>Gal <inline-formula> <tex-math>$=10^{-8}$ </tex-math></inline-formula> m/s2) with an integration time of 2000 s. Additionally, this study conducted cross-bridge experiments with two spring gravimeters, CG-6 and Burris, to assess their effectiveness for detecting urban underground features and to evaluate the accuracy of these conventional instruments. Due to issues like zero drift in the relative gravimeters, the comparison with AG measurements showed external coincidence accuracies of <inline-formula> <tex-math>$8.5~pm ~8.8~mu $ </tex-math></inline-formula>Gal for the CG-6 and <inline-formula> <tex-math>$7.1~pm ~7.9~mu $ </tex-math></inline-formula>Gal for the Burris. Overall, AGs demonstrate superior detection accuracy and offer significant potential for applications in urban underground space detection.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073459","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":"Ripe Stage Detection and Optimal Ripe Hours Prediction of a Banana Using Modified Fractional Order Colpitts Oscillator","authors":"Agniv Tapadar;Dibakar Roy;Avhishek Adhikary","doi":"10.1109/TIM.2025.3565248","DOIUrl":"https://doi.org/10.1109/TIM.2025.3565248","url":null,"abstract":"Accurate assessment of ripe-stages and reliable prediction of ripe hours of banana will ensure efficient supply chain management, extended shelf-lives, reduction of food waste, and optimal nutrients to the consumers. Bioimpedance spectroscopy (BIS) is an accurate and intrinsic method to track banana ripeness but not suitable for a commercial portable meter. This work presents a compact and reliable solution to this challenge by designing a modified fractional-order Colpitts oscillator (FOCO) as a novel electronic sensor to ripeness detection. When a banana sample is connected to the proposed circuit its frequency output indicates the ripe stage of the banana: “Green,” “Ripe,” “Overripe,” and “Decay.” In addition to that, the proposed sensor includes another novel feature; it uses a time-series model to predict “hours to Ripe” and “hours to Overripe” for a banana in Green stage, from the same FOCO output. The model is trained with 540 banana sample data and validated with 180 test data. The work reports 94.4% <inline-formula> <tex-math>${F}1$ </tex-math></inline-formula> score in ripe stage identification and 82.5% <inline-formula> <tex-math>${F}1$ </tex-math></inline-formula> score in the ripe hour prediction.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-9"},"PeriodicalIF":5.6,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943916","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}