Measurement最新文献

{"title":"Machine learning driven 3D point cloud displacement reconstruction and structural safety evaluation of retaining structures","authors":"Xulin Zhou ,&nbsp;Qiankun Zhu ,&nbsp;Qiong Zhang ,&nbsp;Yongfeng Du","doi":"10.1016/j.measurement.2025.118540","DOIUrl":"10.1016/j.measurement.2025.118540","url":null,"abstract":"<div><div>Image-based 3D reconstruction algorithms make it possible to obtain 3D point clouds of retaining structures across different time periods. These point clouds can be used to efficiently derive the full-field displacement of the structures. However, due to environmental influences and limitations in algorithmic accuracy, the generated point clouds may contain a high density of outliers within the full-field displacement data.</div><div>To address the issues of outliers and inaccuracies in displacement measurements, this study employs the Improved-PatchmatchNet algorithm, the Improved-ICP algorithm, and the M3C2 algorithm to obtain full-field displacement. Subsequently, machine learning methods are applied to reconstruct point cloud displacement and correct the full-field displacement. Through algorithm improvement and a series of experiments, Support Vector Regression (SVR) is considered the most suitable method for reconstructing displacement data from 3D point clouds. In addition, extensive experiments were conducted to investigate the impact of different kernel functions and parameter settings on displacement accuracy after data reconstruction. The proposed method was validated using a PBGM based evaluation framework, and the results show that the error was less than 1 cm, with an average error of less than 3.27 %. In the field tests, long-term displacement monitoring conducted over 29 months successfully captured structural displacements caused by tunnel shield construction and seismic events. Finally, the safety and reliability of post-earthquake retaining structures were assessed using engineering experience method and PDEM method, revealing that the safety level of the structures is classified as level 1, with a reliability greater than 0.9663, consistent with post-earthquake survey results.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"256 ","pages":"Article 118540"},"PeriodicalIF":5.2,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704240","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":"Research on the detection technology of goniometric accuracy of space-based binary stars","authors":"Rui Zhu,&nbsp;Nan Liu,&nbsp;Qiang Fu,&nbsp;Haodong Shi,&nbsp;Liyong Wang,&nbsp;Yingchao Li,&nbsp;Huilin Jiang","doi":"10.1016/j.measurement.2025.118490","DOIUrl":"10.1016/j.measurement.2025.118490","url":null,"abstract":"<div><div>Precise measurement of angular positions in space-based observations is essential for improving the accuracy of target localization and identification. This paper presents an in-depth investigation into the accuracy of space-based binary star goniometry and introduces a polarization imaging technique based on a split focal plane. Leveraging binocular triangulation principles, we establish a theoretical model to evaluate the angular measurement performance of binary star systems. To validate the effectiveness of the proposed split-focal-plane polarization imaging method in enhancing goniometric accuracy, we construct experimental platforms under varying environmental conditions. Objective evaluation methods are employed to compare the angular accuracy of single-star polarization imaging versus single-star visible-light imaging, as well as binary-star polarization imaging versus binary-star visible-light imaging, in both daytime and evening scenarios. Experimental results show that, compared to traditional visible-light imaging, the split-focal-plane polarization imaging technique significantly enhances goniometric accuracy and improves both the probability of spatial target recognition and the precision of localization. This research offers valuable theoretical insight and practical relevance for space science and related applications.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"256 ","pages":"Article 118490"},"PeriodicalIF":5.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144724523","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":"Implementing digital technology in landscape architecture: cityscape image segmentation via deep learning","authors":"Nana Tang ,&nbsp;Hui Zhang","doi":"10.1016/j.measurement.2025.118553","DOIUrl":"10.1016/j.measurement.2025.118553","url":null,"abstract":"<div><div>Digital technology plays a crucial role in urban park landscape design by enhancing design efficiency, precision, and recall through precise data analysis, simulation, and optimization, while also aiming to improve ecological sustainability and user experience. Specifically, cityscape image segmentation, as a key digital technology, enables the precise identification and segmentation of various elements within urban street scenes, providing detailed site analysis and landscape simulation. This assists designers in making informed decisions when planning and optimizing urban layouts, resulting in aesthetically pleasing and functional environments. Therefore, we present the YOLACT-Premium model for cityscape segmentation, which includes the Enhanced Asymmetric Shuffle Network (EASNet) and the Twin-route Representation Learning Module (TRLM). EASNet enhances feature extraction capabilities, while TRLM improves the efficient fusion of multi-resolution spatial and semantic information, generating high-quality segmentation masks. Our primary experimental evaluations were conducted on a composite dataset amalgamating images from the Cityscapes benchmark and diverse field-collected urban scenes, with further robustness validation performed on the BDD100K dataset. Results demonstrate that YOLACT-Premium achieves a mean Average Precision (mAP) @0.5:0.95 of 52.05 % and a [email protected] of 75.58 %. Inference speed was benchmarked at 18.09 FPS using FP32 precision on an NVIDIA GeForce RTX 3050 GPU (8 GB VRAM) with a 640*640 input resolution and a batch size of 1. Specifically, in comparative experiments employing standard COCO evaluation protocols for object scale, wherein ’small’ objects have an area &lt;322 pixels, ’medium’ between 322–962 pixels, and ’large’ &gt;962 pixels, YOLACT-Premium demonstrates superior performance across these categories, achieving [email protected] values of 24.05 % (small), 48.11 % (medium), and 56.00 % (large objects), respectively. These findings indicate the model’s robust capability to handle a wide range of object sizes and its suitability for applications requiring a balance of high precision, recall, and near real-time processing speed on typical desktop-grade hardware.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"257 ","pages":"Article 118553"},"PeriodicalIF":5.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738396","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":"Investigating dynamic evolution of pore structures during long term water flooding via in-situ CT scanning: A case study of the Beibu-Gulf Basin in the South China Sea","authors":"Jingjing Guo,&nbsp;Henghao Wang,&nbsp;Haitao Wang","doi":"10.1016/j.measurement.2025.118556","DOIUrl":"10.1016/j.measurement.2025.118556","url":null,"abstract":"<div><div>Long term water flooding (LTWF) can alter the micro-porous structure of oil reservoirs, thereby affecting the water flooding efficiency. Based on the core samples collected from the Beibu-Gulf Basin in the South China Sea, the online in situ CT scanning and digital rock techniques were adopted to elucidate the impacts of long-term water flooding on microscopic pore structures. Dynamic prediction models of pore radius, throat radius, porosity and permeability changing with the volume of injected water were established. The results show that in reservoirs with permeabilities ranging from medium to high, the average pore and throat radii increase after water flooding, resulting in better pore connectivity and more regular pore shape. For low permeability reservoirs, the overall permeability and average throat radius decrease ascribe to the blockage of smaller throats by migrating tiny particles. The average pore radius, throat radius and pore shape factor of the core samples satisfy exponential relationships with the volume of injected water.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"256 ","pages":"Article 118556"},"PeriodicalIF":5.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721643","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":"Terahertz frequency-domain characterization of UHMW-PE ballistic armor plates","authors":"Can Candan ,&nbsp;Kayrahan Kocyigit ,&nbsp;Mehmet Tiken ,&nbsp;Asaf Behzat Sahin ,&nbsp;Hakan Altan ,&nbsp;Halil Berberoglu","doi":"10.1016/j.measurement.2025.118555","DOIUrl":"10.1016/j.measurement.2025.118555","url":null,"abstract":"<div><div>Ultra-high molecular weight polyethylene (UHMW-PE) fiber-based ballistic armor plates are analyzed in the terahertz (THz) frequency region to better understand their structural properties. Various thickness plates are produced by hot pressing 5, 10 and 15 layer four-ply cross-weaved UHMW-PE fiber sheets whose refractive index and absorption characteristics are then examined for three different frequencies using time-domain imaging techniques. The obtained transmission images reveal significant structural information, including surface texture and potential defects, such as air bubbles or voids. It is found that with an increasing number of layers in each plate there is an increase in the refractive index approaching the value of the UHMW-PE fiber sheet. The change in the effective refractive index is attributed to inhomogeneities such as bunching up of the fibers as well as voids because of the manufacturing processes with a larger inhomogeneity in the 5-layer plates as compared to the 10- and 15-layer plates. Furthermore, a significant change in refractive index is observed for different orientations of the armor plate with respect to the input beam polarization due to the presence of periodic surface ridge formations. A detailed analysis of the extinction coefficient with respect to the refractive index shows groupings in the range of values for different thickness plates which can serve as an indicator of the inhomogeneities inside the structures. The purely frequency domain analysis performed here suggests that such methods in the THz region can offer a new, rapid way for non-destructive analysis of ballistic armor plates.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"257 ","pages":"Article 118555"},"PeriodicalIF":5.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738395","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 robust autocorrelation-based strategy for early gear fault feature extraction under strong Gaussian noise and random impulsive interference","authors":"Jingchao Zhang ,&nbsp;Ge Sun ,&nbsp;Yupeng Zhang ,&nbsp;Shaoqun Zhang ,&nbsp;Chen Li ,&nbsp;Guoqian Jiang ,&nbsp;Yingwei Li","doi":"10.1016/j.measurement.2025.118552","DOIUrl":"10.1016/j.measurement.2025.118552","url":null,"abstract":"<div><div>Gearbox fault diagnosis is often hindered by the presence of strong Gaussian white noise and random impulsive noise, which tend to mask weak modulation components associated with early-stage faults. To overcome this challenge, this study proposes a novel demodulation-based signal analysis method, termed LEARCgram, specifically designed to extract cyclic fault features under complex noise conditions. The proposed method introduces the logarithmic envelope autocorrelation average power spectrum (LEAPS), which effectively enhances periodic fault-related components while suppressing non-Gaussian interference. Furthermore, a new indicator called the relative cyclic frequency index (<em>RCFI</em>) is developed to evaluate the periodicity strength of each frequency band, thereby enabling the selection of the optimal demodulation band in a data-driven and fault-targeted manner. By integrating the advantages of logarithmic envelope transformation, autocorrelation analysis, and spectral averaging, LEARCgram improves the signal-to-noise ratio and enhances the detectability of subtle fault signatures. The method is validated using both simulated gear fault signals and experimental vibration data collected from industrial gearboxes. Comparative results demonstrate that LEARCgram outperforms conventional methods in isolating fault-related harmonics and exhibits superior robustness against noise and impulsive interference, making it a promising tool for early and reliable fault diagnosis in rotating machinery.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"256 ","pages":"Article 118552"},"PeriodicalIF":5.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721638","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":"Microalgae density assessment using quantum dots-based optical sensing technique","authors":"Hua Xiao ,&nbsp;Feng Li ,&nbsp;Qiannan Jiang ,&nbsp;Haiyun Chen ,&nbsp;Mingxin Liu ,&nbsp;Caiming Sun ,&nbsp;Wensong Wang","doi":"10.1016/j.measurement.2025.118489","DOIUrl":"10.1016/j.measurement.2025.118489","url":null,"abstract":"<div><div>Monitoring microalgae density is crucial for optimizing growth conditions and ensuring productivity in cultivation systems. To offer a more efficient, accurate, and adaptable method for microalgae density assessment, this study introduces (a) an optical sensing technique that employs quantum-dot light-emitting diodes (QD-LEDs) and a high-sensitivity PIN photodiode, and (b) a calibration method based on dynamical numerical calculation. The proposed method leverages green, orange, and red QDs with diverse luminescence properties, combined with deep ultraviolet (DUV), ultraviolet (UV), and blue-light LEDs as excitation sources, offering multiple measurement options. Initially, the method evaluates microalgae densities for species such as <em>Euchlorocystis marina</em> and <em>Isochrysis galbana</em> using a standard QD-LED. Subsequently, a photocurrent-based calibration model is introduced to calibrate measurements obtained under non-standard QD-LED conditions. Compared to manual counting, our approach achieved a maximum accuracy of 0.99 and an average accuracy exceeding 0.90 across various LED chips, driving voltages, measurement angles, and QD species. With its high feasibility and tunable color options, this method holds significant potential for smart illumination-sensing systems in marine microorganism monitoring.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"256 ","pages":"Article 118489"},"PeriodicalIF":5.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721753","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":"Vibration and stability in dry rough milling AZ31B magnesium alloy using end mills with different edge geometry","authors":"Ireneusz Zagórski ,&nbsp;Andrzej Weremczuk ,&nbsp;Monika Kulisz ,&nbsp;Agnieszka Skoczylas","doi":"10.1016/j.measurement.2025.118523","DOIUrl":"10.1016/j.measurement.2025.118523","url":null,"abstract":"<div><div>Modern milling methods should ensure high quality and stability of machining processes. Increased manufacturing demands require the use of advanced machining methods. The aim is to use milling as both a preliminary (rough) and finishing operation, eliminating e.g. the grinding process. Vibrations generated during machining are an integral part of the process, however, they should be minimized. Therefore, the current research focuses on the vibrations analysis during magnesium alloy rough milling. This alloy is often used in various industries and the application and use of magnesium alloys is considered innovative. The main objective of the research was an assessment of vibration and stability during dry end milling processes and to study the influence of machining technological parameters and end mill geometry. The basis of the research carried out is the recording and analysis of the vibration acceleration signal in the time domain. In the research were used end mills with different edge geometry (different rake and helix angles). A frequency domain analysis of selected vibration signals was also performed (Fast Fourier Transform spectral analysis). Vibration acceleration parameters such as maximum, peak-to-peak value, root mean square and Composite Multiscale Entropy were also determined. It was noticed that for certain milling parameters, increasing the rake angle causes a greater degree of disturbance of the measured acceleration signal. In the vast majority of cases observed, the maximum does not exceed 1 m/s², which may indicate a very good stability of the implemented process, despite the use of effective, high values of machining parameters.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"256 ","pages":"Article 118523"},"PeriodicalIF":5.2,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144714220","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":"An ensemble deep learning method for predicting cadmium content in eggs using hyperspectral imaging","authors":"Kunshan Yao ,&nbsp;Yibo Zhang ,&nbsp;Jun Sun ,&nbsp;Yexin Xu ,&nbsp;Xingrui Jia ,&nbsp;Yujie Wei ,&nbsp;Bing Zhang ,&nbsp;Xiaojiao Du ,&nbsp;Yan Li","doi":"10.1016/j.measurement.2025.118524","DOIUrl":"10.1016/j.measurement.2025.118524","url":null,"abstract":"<div><div>The purpose of this research was to investigate the feasibility of applying hyperspectral imaging (HSI) technique for the determination of heavy metal cadmium (Cd) in eggs. An ensemble deep learning algorithm fusing deep learning and ensemble learning was proposed to achieve end-to-end prediction. Firstly, discrete wavelet transform (DWT) algorithm was used to decompose the raw spectra to obtain scale information. Then, one-dimensional convolutional neural network (1DCNN) sub-models were established based on the wavelet coefficients of each scale. Finally, the sub-model space was optimized using a filtering strategy to construct ensemble deep learning model. The results showed that the ensemble deep learning model had stronger stability and higher prediction accuracy than conventional hyperspectral analysis methods, with R²_p of 0.91, RMSEP of 0.0285 mg/kg and RPD of 3.40. The proposed combination of HSI with ensemble deep learning model has great potential for in-situ and non-destructive detection of heavy metals in eggs.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"256 ","pages":"Article 118524"},"PeriodicalIF":5.6,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721755","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":"Real-time weight estimation of Zucchini using laser-based 3D matrix and deep learning","authors":"Mojtaba Taheri ,&nbsp;Mohammad Amin Nematollahi ,&nbsp;Alimohammad Shirzadifar ,&nbsp;Mahmoud Omid","doi":"10.1016/j.measurement.2025.118542","DOIUrl":"10.1016/j.measurement.2025.118542","url":null,"abstract":"<div><div>Accurate and efficient weight-based grading systems are essential for maintaining quality standards and improving productivity in modern agriculture. However, traditional methods are often manual, time-consuming, and prone to inaccuracies. This study presents a machine vision-based system for automated Zucchini weight estimation using a cost-effective laser-assisted 3D imaging method combined with deep learning. A red line laser, aligned perpendicular to a moving conveyor, captures video frames of Zucchinis. Height deviations from the laser profile are analyzed to generate a 3D matrix for each Zucchini. These data are resized, augmented, and used via transfer learning as inputs for pre-trained deep learning models, VGG16, ResNet101, and MobileNetV2. The study also compares this laser-based volumetric approach with traditional RGB image-based estimation. Among the models, MobileNetV2 using 3D matrix input achieved the highest accuracy, with an R² of 0.96 ± 0.03, root mean squared error of 19.01 ± 6.29  g, and mean absolute percentage error of 7.04 ± 2.63 %. The 3D matrix-based approach significantly outperformed the image-only method in accuracy and processing speed. Nevertheless, limitations such as sensitivity to ambient light, surface moisture, and the need for controlled imaging conditions must be considered for real-world deployment. This research introduces a scalable, low-cost solution for real-time weight grading of Zucchinis, with the potential for adaptation to other irregularly shaped horticultural crops. Furthermore, the system architecture can be extended to assess other practical applications of postharvest traits, such as ripeness, surface damage, or frostbite. Future work will focus on validating the system across diverse environmental conditions and expanding its functionality for broader use in precision agriculture.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"256 ","pages":"Article 118542"},"PeriodicalIF":5.6,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721642","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}