Yunjun Yu;Zhibin Zheng;Hongwei Tao;Jianhua Teng;Yunfeng Xin;Xiaozheng Xiang;Huao Zhou;Jiawen Hu
{"title":"A Real-Time Bent Cable Detection Method for Fatigue Testing in Fast Drag Chain Machines","authors":"Yunjun Yu;Zhibin Zheng;Hongwei Tao;Jianhua Teng;Yunfeng Xin;Xiaozheng Xiang;Huao Zhou;Jiawen Hu","doi":"10.1109/TIM.2025.3557102","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557102","url":null,"abstract":"Bending cables can cause irreversible damage to the tracks and rails of fast drag chain machines. To swiftly and precisely identify bent cables within these machines, an intelligent detection method based on improved YOLOv8n for bent cables is proposed. This method can simultaneously achieve clear detection and bend detection of cables. The YOLOv8n backbone network is augmented with a global attention mechanism (GAM) to adjust the importance weights of each channel, enabling more effective capture of key features and enhancing the feature maps’ expressive capacity. A P2 small-object detection layer is incorporated in the detection head to improve the model’s capability to detect minute curved areas. Moreover, the Wise_IoU (W_IoU) loss function is adopted in place of the traditional C_IoU loss function to minimize the impact of low-quality samples on model performance during training, thereby optimizing the training process and enhancing model accuracy. The refined YOLOv8n model demonstrated a mean average precision (mAP) of 92.1% in detecting bent cables, with a detection time of 2.1 ms, leading to a 0.8-ms reduction in detection time compared to the original YOLOv8n model. These improvements make the model particularly well-suited for rapid detection in fast drag chain machines. The detection method has already been applied in practice and helps avoid over 3 track damages within a quarter.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852445","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":"Enhanced Heterodyne Grating Interferometer for Simultaneously Measuring Tri-Axial Linear Motions","authors":"Xingyou Chen;Peng Huang;Limin Zhu;Zhiwei Zhu","doi":"10.1109/TIM.2025.3557115","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557115","url":null,"abstract":"A novel heterodyne grating interferometer (HTGI) with a rotationally symmetric optical configuration is proposed to achieve the simultaneous measurement of tri-axial linear motions with a large Z-axis range and a large Z-axis rotation tolerance. In this design, the ±1st-order diffracted beams from one incident beam were purposely rotated around the central axis by an angle of 180° to interfere with them from the other incident beam. In this configuration, all beams can shift identical distances along the same direction to maintain interference, when the grating has large Z-axis motions and rotations. Experimental testing demonstrates high linearities comparable with commercial capacitive sensors, and sub-nanometric resolutions by identifying 0.25 nm motions via the spectrum analysis for all the tri-axial measurements. Moreover, a greatly extended Z-axis range of 7.6 mm and a Z-axis rotation tolerance of 0.75° were achieved, well demonstrating the superiority of the proposed design.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-9"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860872","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":"Dynamic Performance Evaluation of High-Valued Complex Systems Based on Belief Rule Base","authors":"Can Li;Zhichao Feng;Zhijie Zhou;Yongjia Gao","doi":"10.1109/TIM.2025.3554856","DOIUrl":"https://doi.org/10.1109/TIM.2025.3554856","url":null,"abstract":"This study presents a novel dynamic method for evaluating the performance of high-valued complex systems (HVCSs). It aims to address the following three problems in performance evaluation (PE) of this type of system, including limited observation data of system states, uncertainty in expert knowledge, and high real-time requirement. To address these challenges, we expand the discernment frame of the belief rule base (BRB) to the power set (BRB-P), enhancing its capacity to handle limited data and uncertain expert knowledge. The belief rules are integrated using the evidential reasoning (ER) algorithm, ensuring the interpretability of the framework. Simultaneously, we introduce a new optimization model to enhance the real-time performance of the framework and mitigate the explosion of belief rule combinations when dealing with multiple input features. Furthermore, we develop a utility-based framework reduction method to adaptively adjust the discernment framework of BRB-P. This enables the structure and parameters of the framework to be dynamically trained using real-time observation data. An experimental illustration is presented to demonstrate the effectiveness of the proposed framework.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143839910","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}
Martim F. Fernandes;Ian P. Bordin;José Alexandre de França
{"title":"Development of a Low-Cost Ozone Monitoring Module for Continuous Partial Discharge Detection in Hydrogenerators","authors":"Martim F. Fernandes;Ian P. Bordin;José Alexandre de França","doi":"10.1109/TIM.2025.3557129","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557129","url":null,"abstract":"Partial discharge (PD) measurement is a well-established predictive maintenance tool for high-voltage rotating machines, allowing the condition of the insulation to be assessed not only during machine outages, but also continuously monitored during regular operation, enabling a more efficient planning of major overhauls or possible repairs. Some types of PDs are known to produce ozone in air-cooled machines, but online ozone monitoring has not been widely available commercially for this application, perhaps with one exception which uses a complex system of tubes and valves to direct air samples to a measuring chamber, based on ultraviolet (UV) absorption. Advances in electrochemical sensors, however, have allowed for more reliable measurements at very low cost. In this article, we describe the development and prototype of an ozone monitoring module with embedded signal processing for specific application in rotating machines, using simultaneous temperature and humidity measurements to reduce the typical errors induced by the variations of these parameters. Prototypes were manufactured and installed in two 311 MVA hydrogenerators and the data collected indicates that continuous ozone monitoring can detect potential problems that may not be identified with traditional PD monitoring.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-7"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856329","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":"PRNet: Low-Light Image Enhancement Based on Fourier Transform","authors":"Jiayu Zhang;Xiaohua Wang;Yingjian Li;Wenjie Wang","doi":"10.1109/TIM.2025.3557114","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557114","url":null,"abstract":"Low-light image enhancement (LLIE) techniques constitute a significant approach for enhancing image brightness effectively while preserving image details. In this article, PRNet is proposed, which is a novel lightweight LLIE network that leverages the Fourier transform, performing LLIE in two stages. In the first stage, a pixel enhancement network (PENet) enhances the brightness of the low-light image (LLI) through a dense skip-connection structure. This structure incorporates a custom-designed Fourier-based brightness enhancement block (FBEB). In the second stage, a refinement and restoration network (RRNet) processes the output from the first stage, further restoring image details. Detailed refinement is achieved using a dual-branch UNet structure, incorporating a bidirectional frequency-domain cross-attention solver (BFDCS) to optimize image quality. To thoroughly assess the performance of the proposed PRNet, nine well-established benchmark datasets were employed for detailed quantitative and qualitative evaluations. The experimental results show that PRNet achieves high-quality image enhancement at significantly reduced computational complexity.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-14"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143865327","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 Hybrid-Model-Flux-Observer-Based Horizon-Adaptive Sliding Integration Fault Diagnosis Method for Sensorless Vector Controlled Voltage Source Inverter","authors":"Naizhe Diao;Xiaoqing Zhang;Ruizhen Zhang;Yingwei Zhang;Xiaoqiang Guo;Yupeng Wei","doi":"10.1109/TIM.2025.3557119","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557119","url":null,"abstract":"In this article, a horizon-adaptive sliding integration fault diagnosis (HSIFD) method based on a hybrid model flux observer is proposed for a single switch open-circuit (OC) fault in the sensorless vector control (SVC) fed voltage source inverter (VSI). It can achieve the diagnosis and location of the OC fault of the power switch quickly in real-time within the frequency regulation range. First, the compensation voltage is obtained in-loop by the deviation between the voltage model flux observer and the current model flux observer. Aiming at the problem that model-based methods rely heavily on precise mathematical models and parameter accuracy, a conversion method from time domain integration to phase angle domain integration is proposed to indirectly observe the periodic characteristics of compensation voltages. Then, the second-order equal phase angle moving mean (SoEPAMM) method is proposed to reduce the data storage and improve diagnosis timeliness. Simulations and experiments show the accuracy and superiority of the HSIFD method in the SVC framework. The proposed method can be implemented in-loop for practical applications since the storage and operation volumes are greatly reduced. Moreover, a comparison with other models shows that the proposed method is robust to the variation of model parameters, speed, and load.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143839858","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":"AI-Based Generative Model for Computer-Based X-Ray Inspection Training System","authors":"Junyoung Kim;Gihyun Kwon;Dohoon Ryu;Jong Chul Ye","doi":"10.1109/TIM.2025.3554859","DOIUrl":"https://doi.org/10.1109/TIM.2025.3554859","url":null,"abstract":"X-ray baggage inspection systems have proven to be indispensable tools for swiftly and efficiently examining passengers’ belongings and inspecting goods during import-export processes at locations, such as airports and seaports. The ability to visualize the contents of bags without opening them streamlines the inspection process, enabling rapid assessments. The reliance on human judgment for interpreting X-ray images requires systematic training program, given the disparities between the actual shapes of items and their representations in X-ray images. In addition, the surge in travel demand and logistics movements necessitates a substantial number of highly trained inspectors. Computer-based training (CBT) systems offer a convenient solution for training inspectors, but current X-ray inspection CBT systems have limitations in data diversity and provide only restricted information, constraining the effectiveness of training. To address this, here we propose a novel AI-based data augmentation scheme for X-ray inspection CBT systems. Specifically, this article focuses on the AI generative model component, which is composed of three parts. First, we employ a latent diffusion model (LDM) to generate high-quality, diverse illicit item X-ray images. Second, by incorporating a novel neural support optimization from frontal and side-view images, a tuned voxel grid is obtained, enabling the creation of 3-D images that offer varied perspectives of items. Finally, the generated images undergo transformations, such as metal material emphasis, organic material emphasis, negative images, and variations in brightness to enhance detection capabilities, making it easier to identify items that were challenging to detect in conventional pseudo-color images. Inspector training with real X-ray data followed by training with generated X-ray data resulted in an increase in inspection accuracy and decrease in inspection time, confirming the effectiveness of training using generated images.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-13"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143809020","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":"Systematic Error Reduction of i-TOF LiDARs Using Flexible Trapezoidal Waveforms","authors":"Xuan Ma;Hui Lin;Shangquan Wu;Xiaoguang Liu","doi":"10.1109/TIM.2025.3552461","DOIUrl":"https://doi.org/10.1109/TIM.2025.3552461","url":null,"abstract":"Compared with common 3-D measurements technologies, indirect time-of-flight (i-TOF) systems offers significant advantages in volume, cost, power consumption, accuracy, range, and angular resolution. As such, they have found widespread applications in intelligent recognition, simultaneous localization and mapping (SLAM), and augmented reality (AR). However, due to the interference of systematic and random errors, current i-TOF systems achieve ranging accuracy only within several tens of millimeters. This severely limits their applications in high-precision scenarios, such as facial recognition payments, advanced manufacturing, and intelligent healthcare. In this work, we highlight that the most significant factor affecting accuracy among all errors is a systematic error known as wiggling. It is a high-dimensional complex function that nonlinearly couples with other systematic and random errors, making it difficult to independently separate, characterize, and compensate for. In light of this, we develop a methodology for ranging simulation and systematic error optimization based on adjustable trapezoidal functions derived from actual drive light waveform shaping. To demonstrate the effectiveness of the proposed theory and methodology, we perform measurement on an i-ToF system. Through global optimization of the frequency, duty ratio (DR), and rising/falling edge ratio (RFER) of the optical waveform, the total systematic error can be reduced from ±19 to ±4.5 mm under the conditions of a 5.6% RFER, a 33.2%, and a frequency of 100 MHz. By developing drive circuits that are optimized for the best DR and RFER, the systematic error is expected to be further reduced to the submillimeter level.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-17"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143826486","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 Cloud-Edge Collaborative Learning-Based Electrical Impedance Tomography Method","authors":"Qinghe Dong;Xichan Wang;Qian He;Chuanpei Xu","doi":"10.1109/TIM.2025.3557103","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557103","url":null,"abstract":"Deep learning-based electrical impedance tomography (EIT) technology encounters significant challenges including insufficient image clarity and boundary blurring. To address these issues, we propose a multiscale attention residual model (MSARM) that integrates multiscale feature fusion with a parameter-free attention mechanism and trains the network using a hybrid <inline-formula> <tex-math>$L1$ </tex-math></inline-formula>–<inline-formula> <tex-math>$L2$ </tex-math></inline-formula> loss function to improve the accuracy of image reconstruction. Experiments conducted on a simulated dataset demonstrate that the proposed method achieves a 1.87% improvement in the correlation coefficient (CC) metric and a significant 17.42% reduction in relative error (RE) compared to the prevailing multiscale U-Net model. Furthermore, phantom experiments have validated the effectiveness and generalization capability of the proposed method. However, deep learning-based EIT faces practical deployment challenges such as high latency, data loss, and privacy breaches. In response, we introduce a novel cloud-edge collaborative EIT system architecture, comprising two-level cloud servers, edge computing nodes, and terminal devices. Experimental results indicate that, compared to the traditional cloud-only service architecture, this architecture reduces the data transmission time by approximately 50% and maintains data integrity during network fluctuations. The proposed EIT system architecture not only improves the real-time and quality of image reconstruction but also provides a viable solution for EIT clinical application and remote monitoring.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-9"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848807","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-Source Multi-Target Domain Adaptation Based on Evidence Theory","authors":"Linqing Huang;Jinfu Fan;Shilin Wang;Alan Wee-Chung Liew","doi":"10.1109/TIM.2025.3557120","DOIUrl":"https://doi.org/10.1109/TIM.2025.3557120","url":null,"abstract":"Domain adaptation usually confronts the multiple-source and multiple-target domain issue. In such cases, the reduction of distribution discrepancy across domains and the combination of information in diverse domains are two major subproblems. Here, we propose a new method called multi-source multi-target domain adaptation based on evidence theory (MMET) to improve the accuracy. In MMET, we first develop a joint first- and second-order statistical distribution alignment approach to reduce distribution discrepancy. For a certain target domain, the other target domains are merged with it to yield multiple new target domains. Then, patterns in this target domain will obtain multiple domain-invariant feature representations by pairwise aligning the distributions of the source domain and each new target domain. For a query pattern in this target domain, it will obtain multiple soft classification results after employing the new distribution alignment approach. In order to integrate useful information in different target domains, the weighted average fusion (WAF) rule is used to locally combine the soft classification results, and multiple pieces of WAF results will be produced because of multiple source domains. For integration of information in different source domains, evidence theory (ET) is employed to globally combine these WAF results. MMET was compared with a variety of advanced methods, and the experimental results show that MMET can significantly improve the accuracy in each target domain.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-17"},"PeriodicalIF":5.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852442","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}