Measurement最新文献

{"title":"CrackAdaptNet: End-to-end domain adaptation for crack detection and quantification","authors":"Hancheng Zhang ,&nbsp;Yuanyuan Hu ,&nbsp;Jing Hu ,&nbsp;Jiao Jin ,&nbsp;Pengfei Liu","doi":"10.1016/j.measurement.2025.117716","DOIUrl":"10.1016/j.measurement.2025.117716","url":null,"abstract":"<div><div>Crack detection and quantification are essential for ensuring the maintenance and safety of infrastructure, as cracks serve as early indicators of structural degradation. This paper introduces CrackAdaptNet, an end-to-end domain adaptation and semantic segmentation framework designed to address the complexities of crack detection in diverse engineering environments. Unlike existing approaches that face challenges in generalizing to practical applications, CrackAdaptNet utilizes extensive annotated vertical datasets to enhance detection accuracy in oblique imagery from uncontrolled settings. The framework comprises three core components: the Alignment Generator (AG), Segmentation Generator (SG), and Alignment-Segmentation Discriminator (ASD). AG mitigates the domain gap between controlled datasets and field-collected imagery. SG performs precise crack segmentation using Generative Adversarial Networks, while ASD assesses both alignment and segmentation quality. Experimental results indicate that CrackAdaptNet surpasses state-of-the-art models such as Mask2Former, K-Net, and SegFormer, achieving notable improvements in segmentation performance. Specifically, CrackAdaptNet achieves an IoU improvement of over 36% and an F1-score increase of more than 40% compared to these methods, demonstrating its superior generalization capability. Furthermore, field experiments conducted on Qingshuiting West Road in Nanjing, China, reveal strong correlations between model predictions and manual measurements. These results demonstrate the framework’s ability to minimize false positives and enhance the reliability of crack detection across diverse environments. CrackAdaptNet provides a robust solution for the monitoring and assessment of infrastructure conditions.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117716"},"PeriodicalIF":5.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070848","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 experiment study of a novel micro seawater solenoid valve for energy conversion device of marine animal telemetry tag","authors":"Jianjun Wang,&nbsp;Xiaobin Zheng","doi":"10.1016/j.measurement.2025.117848","DOIUrl":"10.1016/j.measurement.2025.117848","url":null,"abstract":"<div><div>The marine animal telemetry tag is an important ocean environment measurement tool, especially for polar ocean observation. A novel micro seawater solenoid valve is proposed to control the seawater pressure energy conversion device of the telemetry tag. The conversion device is used to replace the lithium battery of the tag to increase its energy supply. Under nearly 1000 m underwater, the solenoid valve and its electromagnet are immersed in high-pressure seawater. To tackle the problems of high pressure, corrosiveness and electrical conductivity of seawater and meanwhile minimize the power consumption and the size, several new designs have been developed, including flexible pressure balancing membranes, the fluid hydrostatic transmission between the spool and the armature, and the dual duty cycle pulse width modulation (DDC-PWM) control circuit. The prototype of the solenoid valve was built and tested. The experiment results show that the micro solenoid valve worked normally in high-pressure water and meanwhile achieved micro size. Furthermore, the experiment results also indicate that the water pressure had almost no influence on the energy consumption of the valve and the valve’s energy consumption is reduced to one-ninth under control of DDC-PWM circuit. Under control of the micro solenoid valve, the energy conversion device achieved expected efficiency and can greatly increase the energy supply of the tag, which extends the tag’s working life and enhance its environmental monitoring capability. Because of micro size and low energy consumption, the valve is applicable for various underwater instruments and has remarkable advantages in deep water.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117848"},"PeriodicalIF":5.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070220","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":"Progress in electrical property measurements of micro-nano materials for smart wearable sensors","authors":"Ning Cao ,&nbsp;Yupu Liu ,&nbsp;Feiling Shen ,&nbsp;Chao Wu ,&nbsp;Duanqin Zhang","doi":"10.1016/j.measurement.2025.117863","DOIUrl":"10.1016/j.measurement.2025.117863","url":null,"abstract":"<div><div>Advancing electrical measurement methods for the interior key micro-nano materials can promote the overall performance and parameter optimization of smart wearable sensors. In order to systematically illustrate different electrical measurement methods and principles, electrical property measurements of micro-nano materials for smart wearable sensors can be summarized comprehensively from the perspective of integrated smart wearable sensor and all-in-one smart wearable sensor. Three key indexes including cyclic stability, sensitivity and volt-ampere characteristic are employed to carry out the detailed summary analysis. Firstly, the cyclic stability measurements of smart wearable sensor materials are reviewed based on the sensing ranges and cyclic stretching times. The effects of preparation methods and materials on cyclic stability have been proved. The bending voltage measurement, long-distance resistance measurement and constant velocity resistance measurement possess the low strain, large measuring range and good stability, respectively. Secondly, the sensitivity measurements of smart wearable sensor materials are reviewed. The characteristics of measurement methods are compared from different material processing effects and material structures. The constant velocity material measurement has a high accuracy effect, but the high strain measurement possesses a wide monitoring range. Furthermore, volt-ampere characteristic measurements of materials have been summarized to demonstrate that the linear mass measurement and high range strain measurement possess the high-precision results. Finally, the conclusion and development prospects of smart wearable sensor are discussed, and the further research directions of measurement technology are proposed in future.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117863"},"PeriodicalIF":5.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069275","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":"Federated learning framework for Wi-Fi-based cross-environment human action recognition","authors":"Sai Zhang ,&nbsp;Haoge Jia ,&nbsp;Ting Jiang ,&nbsp;Sheng Wu ,&nbsp;Xue Ding ,&nbsp;Yi Zhong","doi":"10.1016/j.measurement.2025.117821","DOIUrl":"10.1016/j.measurement.2025.117821","url":null,"abstract":"<div><div>Human action recognition (HAR) based on Wi-Fi plays a critical support in the Internet of Things (IoT). Recently, Wi-Fi-based HAR using deep learning models achieves remarkable performance. However, existing HAR models have poor generalization capacity, where the multipath effects and the recognition tasks diversity in different environments would affect the model performance at a great level. This article proposes a cross-environment HAR system based on the federated learning named WiFed-CHAR. This system collaboratively learns the action feature from source environments and generate a feature extraction knowledge base on the cloud. In addition, a HAR module assignment and optimization strategy is proposed to guide the new environment to inherit the most suitable feature extraction knowledge from knowledge base and achieve high performance even with limited data. Extensive experiments are conducted to validate the effectiveness of WiFed-CHAR. When given one sample/action, the HAR of new environments reaches 80.14%, surpassing other competitive baselines.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117821"},"PeriodicalIF":5.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069268","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":"Deep learning for automated defect recognition in tungsten inert gas welds of stainless steel 304","authors":"Aman Nohwal,&nbsp;Nitin Patel,&nbsp;Sivanandam Aravindan,&nbsp;Sunil Jha","doi":"10.1016/j.measurement.2025.117850","DOIUrl":"10.1016/j.measurement.2025.117850","url":null,"abstract":"<div><div>Identifying weld defects is crucial for ensuring the integrity of welded structures. Traditional visual inspections are subjective and prone to errors, while the integration of machine learning (ML) and artificial intelligence (AI) offers significant improvements in automated, accurate weld defect detection. For better accuracy, speed, and consistency in quality control, this study aims at how deep learning algorithms can be used to automatically find defects in SS304 TIG welds. Using visible spectrum camera images, AI-driven models can accurately identify defects in welding in real time, reducing the need for manual checking and reducing the chance of mistakes made by humans. This deep learning method improves weld quality assurance, making it easier to check the integrity of SS304 TIG welds in a more accurate and cost-effective way. The finding demonstrates significant improvements. A model with fewer epochs achieved an F1-score of 86% and an accuracy of 95%, while a model with more epochs attained an F1-score of 88% and an accuracy of 96%. The models demonstrated exceptional efficacy in predicting errors like inadequate shielding gas, with an F1-score of 65%. A fully connected layer model improved the F1-score by 39.2% and test accuracy by 37.7%, exhibiting remarkable efficacy in detecting the burn-through defect, attaining an F1-score of 0.89. The results of this study show that AI and ML models using advanced regularisation and deep learning techniques are a better and more reliable way to find weld defects. This makes TIG welding better and more reliable.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117850"},"PeriodicalIF":5.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069272","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":"Measurement of the bulk material distribution length on a conveyor belt surface guided on a three-roller idler housing","authors":"Leopold Hrabovsky ,&nbsp;Gabriel Fedorko ,&nbsp;Vieroslav Molnar","doi":"10.1016/j.measurement.2025.117849","DOIUrl":"10.1016/j.measurement.2025.117849","url":null,"abstract":"<div><div>Belt transport is an effective and one of the most widespread methods of transporting bulk materials in various industrial sectors. Properly designed and operated belt conveyors significantly increase productivity, reduce operating costs and minimise the risk of accidents. To ensure the efficient and reliable transport of bulk materials by belt conveyors, it is essential to know the length of their distribution on the surface of the conveyor belt, especially at inclinations exceeding normal operating conditions. Determining the length of material distribution is key to optimising conveyor design, efficient operation, and preventing operational failures such as material backsliding. The paper verifies an original method of measuring the bulk material length distribution on a conveyor belt’s surface, guided on a three-roller idler housing. The measurements were carried out because the ISO 5048 standard does not provide instructions for determining the volume of transported material for a belt conveyor, the inclination angle d [deg] of which exceeds the dynamic angle of discharge Q [deg]. The measurement was carried out for various conveyor angles of inclination, the conveyor belt width and the height of the partitions for two different types of bulk materials (wheat, river gravel). The experiments were carried out at a conveyor inclination significantly exceeding a permissible angle of inclination, which caused the material to slide back on a conventional conveyor belt. Transverse partitions were installed on the conveyor belt to eliminate this effect and were fixed at regular intervals. The volume of transported material dose spread on the surface of the conveyor belt retained by a transverse partition of a known height can be analytically calculated according to the formulas given in this article. Due to the practical impossibility of carrying out measurements in actual operating conditions, a laboratory device was designed, which represents a section of a belt conveyor with a support system and a conveyor belt with partitions. The device allows simulating 3 different middle roller lengths from 300 to 500 mm. During the measurements, the angle of inclination of the conveyor longitudinal axis can be further changed to 20 to 70 degrees and the height of the transverse partition to 0 to 100 mm. The experimental results confirmed the functionality of the proposed method and were validated by theoretical calculations. The difference between the experiments and the theoretical calculation is for the measured material “food wheat” in the range of 7.2 % to 12.6 % and for the material “river gravel” in the range of 2.8 % to 14.1 %. The designed laboratory device thus provides a reliable platform for experimental measurement and analysis of bulk material length distribution on the conveyor belt’s surface guided on the three-roller idler housing.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117849"},"PeriodicalIF":5.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070847","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":"Distributed fiber-optic sensing for mining-induced abutment pressure measurement: Sensor design and experiment study","authors":"Jinghao Zhang ,&nbsp;Qiang Yuan ,&nbsp;Deyi Jiang ,&nbsp;Yiwei Ren ,&nbsp;Fengqi Qiu ,&nbsp;Dingding Zhang ,&nbsp;Yi Cui","doi":"10.1016/j.measurement.2025.117839","DOIUrl":"10.1016/j.measurement.2025.117839","url":null,"abstract":"<div><div>Monitoring stress changes in mining areas during mining activities is essential for early warning and prevention of dynamic disasters. This paper presents a distributed fiber-optic abutment pressure sensor (DFAPS) based on the Brillouin distributed fiber sensing principle. The performance of the DFAPS was evaluated through theoretical analysis, laboratory experiments, and numerical simulations. The results confirm a strong linear relationship between the strain of the DFAPS and applied pressure, with an optimal sensitivity coefficient of 48.23 με/kPa. The DFAPS was utilized in the physical model test for measuring the distribution of stope abutment pressure in the mining area. The test results demonstrate high consistency between the abutment pressure distribution patterns reflected by DFAPS and resistance pressure sensor, with a relative error of less than 4.65 %. The proposed DFAPS offers large-scale distributed measurement, high precision, and high sensitivity, which provides a novel approach for abutment stress monitoring in mining environments.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117839"},"PeriodicalIF":5.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070851","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 non-contact torque measurement method for ultrasonic micromotors based on Tunnel Magnetoresistance angle sensor","authors":"Yiwei Zhang ,&nbsp;Yu Chen ,&nbsp;Wentao Zhang ,&nbsp;Tianyu Yang ,&nbsp;Xiaoshi Li ,&nbsp;Lingyi Li ,&nbsp;Pingyi Jia ,&nbsp;Meirong Zhao ,&nbsp;Yelong Zheng","doi":"10.1016/j.measurement.2025.117712","DOIUrl":"10.1016/j.measurement.2025.117712","url":null,"abstract":"<div><div>Ultrasonic micromotors are extensively utilized in microsystems; however, measuring torque in these motors presents a significant challenge due to the small size of the motors, which are on the millimeter scale. This paper introduces a torque measurement method for micromotors utilizing the Tunnel Magnetoresistance (TMR) sensor. The output torque is accurately computed through the measurement of angular acceleration and rotational inertia. Angular acceleration is derived from the angular velocity and angle measured by the TMR sensor, while rotational inertia is determined by the rotor’s mass and dimensions. This method offers several advantages, such as non-contact measurement, low uncertainty, rapid response, and high accuracy. In particular, by performing high-precision encoder calibration, temperature coefficient calibration, and Kalman filtering on the TMR sensor, the error compensation rate for angle measurement was 87 %, significantly improving the accuracy and precision of the TMR sensor. The experimental results indicate that within the normal operating temperature range, there is a good linear relationship between the motor’s torque and the applied voltage. Furthermore, experiments on drive frequency and starting torque reveal that the motor’s starting torque reaches its maximum near the resonant frequency, providing an efficient method for rapid estimation of the resonant frequency. Uncertainty evaluation confirms that the relative combined standard uncertainty of the system is 3.43%. These results demonstrate the effectiveness and reliability of the proposed torque measurement method for ultrasonic micromotors, providing a promising solution for precise motor control and performance optimization in microsystems.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117712"},"PeriodicalIF":5.2,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143947144","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 survey on machine learning approaches for vital sign monitoring using radar","authors":"Mohammad Hossein Shirazi,&nbsp;Sira Yongchareon,&nbsp;Anuradha Singh,&nbsp;Jing Ma","doi":"10.1016/j.measurement.2025.117707","DOIUrl":"10.1016/j.measurement.2025.117707","url":null,"abstract":"<div><div>The integration of machine learning methodologies with radar-based vital sign monitoring represents a significant advancement in non-contact healthcare surveillance systems. This systematic literature review synthesizes and critically analyzes research from 2020 to 2025, addressing substantive theoretical and methodological gaps in extant literature. Our comprehensive taxonomic classification of machine learning paradigms employed in this domain elucidates the progressive refinement from conventional algorithmic approaches to sophisticated deep learning architectures, with particular emphasis on hybrid neural network configurations optimized for physiological signal extraction in non-stationary environments. Methodologically, this survey contributes a rigorous evaluation framework comprising standardized assessment protocols, quantifiable performance metrics, and cross-validation methodologies—elements conspicuously absent in previous reviews. Empirical analysis demonstrates substantial correlations between dataset demographic characteristics and algorithmic generalizability, with heterogeneous participant cohorts yielding markedly enhanced performance across cardiac, respiratory, and hemodynamic parameter estimation tasks. The review delineates four distinct developmental phases in the field’s chronological evolution and provides analytical insight into persistent technical challenges: motion artifact compensation, multi-subject disambiguation, and the translation of laboratory efficacy to clinical utility. This comprehensive examination of computational approaches for radar-based vital sign monitoring establishes a theoretical foundation and methodological framework to guide future research towards physiologically robust and clinically viable implementations.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117707"},"PeriodicalIF":5.2,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070850","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":"Smart aggregate-enabled dual spatial domain health monitoring of concrete beams under loading conditions","authors":"Weihang Gao ,&nbsp;Minghui Zhang ,&nbsp;Ziqian Yang ,&nbsp;Caiyan Zhang","doi":"10.1016/j.measurement.2025.117831","DOIUrl":"10.1016/j.measurement.2025.117831","url":null,"abstract":"<div><div>Concrete beams are fundamental components in civil engineering, often subjected to various loads throughout their service life. Monitoring the health states of concrete beams under loading conditions is crucial for ensuring structural integrity and longevity. To the best of our knowledge, few studies have simultaneously investigated both global and local monitoring of concrete beams under external loads using smart aggregate (SA)-enabled active sensing technology. This paper proposes an SA-enabled dual spatial domain damage evaluation (SA-DSDDE) method to comprehensively investigate the damage evolution process of concrete beams under loading conditions. Specifically, the proposed SA-DSDDE method includes two primary damage evaluation functions: local spatial domain damage evaluation (LSDDE) and global spatial domain damage evaluation (GSDDE). The LSDDE function employs a parallel sensing mode of the embedded SA array to collect detection signals, utilizing the Hilbert-Huang transform (HHT) to define a sensitive index for assessing damage in the local monitoring zone. In contrast, the GSDDE function utilizes a cross sensing mode of the embedded SA array, alongside empirical mode decomposition (EMD), to construct a detection signal characteristic matrix and apply singular value decomposition (SVD) to establish a sensitive index for describing damage in the global monitoring zone. To validate the effectiveness of the proposed method, four-point loading tests of a concrete beam with embedded SA sensors are conducted. The results demonstrate that the proposed method can effectively reveal the damage evolution process of the monitored concrete beam under loading conditions both from local and global perspectives, displaying enormous engineering application prospects.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117831"},"PeriodicalIF":5.2,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070853","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}