Measurement最新文献

{"title":"An improved dual-channel CNN-BILSTM fusion attention model for fault diagnosis of aero-engine bearings","authors":"Delin Huang ,&nbsp;Xiangdong Su ,&nbsp;Jinghui Yang ,&nbsp;Shichang Du ,&nbsp;Dexian Wang ,&nbsp;Qiuyu Ran","doi":"10.1016/j.measurement.2025.117761","DOIUrl":"10.1016/j.measurement.2025.117761","url":null,"abstract":"<div><div>Accurate fault diagnosis of aero-engine bearings is vital for ensuring flight safety. Existing methods still struggle with extracted features lacking multi-dimensional representation, insufficient fault information, and ineffective feature fusion under complex conditions (e.g., varying rotational speeds) and multi-source signal inputs. As such, an improved two-channel fault diagnosis model for rolling bearings is proposed, integrating a convolutional neural network and bidirectional long short-term memory (CNN–BILSTM) architecture, enhanced by multiple improved attention mechanisms.First, the raw vibration signals were directly used as time-domain inputs and processed to obtain their frequency-domain counterparts, forming a dual-channel input to the customized and optimized CNN-BILSTM feature extraction network. Then, a one-dimensional convolutional block attention module (1DECBAM) is inserted after each of the two CNNs to retain initial features while enhancing key ones critical for fault diagnosis. Moreover, the proposed Hybrid Interaction-Fusion Attention (HIFAttn) framework incorporates a Time-Frequency Interactive Attention Mechanism (T-FIAttn) and a Local-Global Adaptive Attention Module (L-GAAM) to perform multimodal feature fusion. Specifically, the T-FIAttn is employed to capture latent feature relationships across both time and frequency domains. In addition, the L-GAAM was appended after the BILSTM layers in each channel to dynamically capture essential features. Experimental results on two aero-engine datasets demonstrate that the proposed model achieves accuracies of 99.32% and 99.94%, respectively, surpassing current state-of-the-art methods.The model also demonstrates excellent stability and robustness, even under high-noise conditions.These results indicate that the proposed model achieves high accuracy and strong generalization, making it well-suited for aero-engine bearing fault diagnosis.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117761"},"PeriodicalIF":5.2,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143921959","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 early fault online detection model of rolling bearing based on deep attention convolutional autoencoder and multi-decision fusion under variable operation conditions","authors":"Wenchang Zhu ,&nbsp;Qiuhua Miao ,&nbsp;Yudong Cao ,&nbsp;Peng Huang ,&nbsp;Hongwei Fan","doi":"10.1016/j.measurement.2025.117752","DOIUrl":"10.1016/j.measurement.2025.117752","url":null,"abstract":"<div><div>A method based on model pre-training, fine-tuned transfer learning, and multi-decision fusion is proposed to achieve high-precision online early fault detection of rolling bearing under complex and variable operation conditions. Firstly, a novel attention mechanism is designed by combining the improved multi-head attention mechanism with rotary position embedding, and the Deep Attention Convolutional Autoencoder (DACAE) is constructed to extract bearing feature. Secondly, a self-supervised pre-training and fine-tuning strategy is used to features transfer, and combining data reconstruction error screening and enhancement algorithm to complete model optimization. Finally, various online detection results of algorithms are integrated, and multi decision voting mechanism is used to complete the detection task. Different bearing datasets are carried out, and the results show that the proposed method can effectively identify the early fault of rolling bearings, and reduce the false alarm rate under different working conditions, which has high robustness and reliability in the industry.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117752"},"PeriodicalIF":5.2,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143912725","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":"Tightly coupled GNSS RTK-LiDAR-inertial system for consistent urban navigation","authors":"Jiahui Liu ,&nbsp;Feng Qin ,&nbsp;Cheng Chi ,&nbsp;Xin Zhang ,&nbsp;Zihao Zhang ,&nbsp;Yulong Sun ,&nbsp;Xingqun Zhan","doi":"10.1016/j.measurement.2025.117671","DOIUrl":"10.1016/j.measurement.2025.117671","url":null,"abstract":"<div><div>LiDAR-Inertial Odometry (LIO) has emerged as a viable solution for local navigation, especially when GNSS signals are affected by interference and outages. The recent availability of solid state LiDAR with non-repetitive scanning patterns has further enhanced the appeal of solid state LIO (sLIO). However, most state-of-the-art LIO methods rely on absolute constraints by associating newly scanned features to a globally maintained map, making it difficult to effectively integrate GNSS information into a consistent tightly coupled fusion system. In this paper, we introduce a coarse-to-fine LiDAR registration strategy that achieves a consistent estimator by combining both absolute scan-to-map and relative keyframe map constraints, thus transforming the system into a partially dead-reckoning framework. Then, a tightly coupled GNSS RTK-solid state LiDAR-Inertial Navigation System (GsLINS) is proposed through keyframe-based factor graph optimization at the measurement level, with global attitude initialization and pose estimation. The proposed coarse-to-fine strategy proves to be consistent in state estimation and achieves superior accuracy in comparison to other methods. The tightly coupled GsLINS system is validated through various field experiments in diverse urban environments and large-scale scenarios, demonstrating precise and robust navigation performance.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117671"},"PeriodicalIF":5.2,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143921731","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":"Enhancing machinery reliability in lunar bases: Optimized machine learning for bearing fault classification in DC power distribution networks","authors":"Muhammad Zain Yousaf ,&nbsp;Josep M. Guerrero ,&nbsp;Muhammad Tariq Sadiq ,&nbsp;Umar Farooq","doi":"10.1016/j.measurement.2025.117737","DOIUrl":"10.1016/j.measurement.2025.117737","url":null,"abstract":"<div><div>In space missions and extraterrestrial habitats, ensuring the reliability of power systems is critical, particularly for DC distribution networks supporting lunar bases and space stations. These systems rely on rotating machinery such as motors and pumps, making the integrity of rolling bearings essential. There is a significant gap in robust fault detection and classification for such machinery under harsh, variable conditions similar to those in space. Existing machine learning (ML) methods often struggle to capture complex multi-channel patterns in sensor data due to overfitting, hyperparameter sensitivity, and high computational demands. This study proposes an ML-driven framework for fault classification in rolling bearings under extreme conditions, taking into account varying dataset sizes. Using three datasets, the proposed approach employs multi-variate variational mode decomposition (MVMD) and Hilbert-Huang Transform (HHT) to capture fault signatures and extract relevant features. To address overfitting and account for monotonic fault progression, this framework fuses four feature selection methods —Laplacian Score (LS), Minimum Redundancy Maximum Relevance (mRMR), ReliefF, and Mutual Information (mutInf)—with Spearman’s rank correlation. The performance of ML classifiers (Neural Networks, Support Vector Machines, Naïve Bayes, K-Nearest Neighbors, Decision Trees, and Ensemble Methods) is optimized by adjusting hyperparameters using Bayesian Optimization (BO), Asynchronous Successive Halving (ASHA), and Random Search (RS), all in parallel settings to improve computational efficiency. These optimizers also help ML architectures to adapt according to available datasets of diverse types. Key quantitative results show that the ASHA-optimized ML model performs well with larger datasets, providing an overall accuracy of 99.94% with the reduced computational load. Meanwhile, BO and RS attained accuracies of 99.90% and 98.0%, which proved effective for scarce datasets. This innovative framework integrates signal decomposition, feature selection, and optimization techniques, creating an efficient predictive maintenance tool. It improves fault classification, boosting the reliability of machinery in extraterrestrial environments and enhancing the safety and sustainability of long-term space missions.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117737"},"PeriodicalIF":5.2,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143921683","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":"Kriging-based surface error measurement method with human-factor resilience using articulated arm coordinate measuring machine","authors":"Zhen Sun ,&nbsp;Tao Wu ,&nbsp;Guochao Li ,&nbsp;Xinshan Liao ,&nbsp;Honggen Zhou ,&nbsp;Qiulin Hou","doi":"10.1016/j.measurement.2025.117754","DOIUrl":"10.1016/j.measurement.2025.117754","url":null,"abstract":"<div><div>Articulated arm coordinate measuring machine (AACMM) has been widely utilized in complex surface measurements due to its flexibility and portability. However, the handheld operation of AACMM makes it highly susceptible to human factors, particularly in the measurement of thin-walled surfaces deformation, often resulting in significant measurement errors. This paper proposes a Kriging-based surface error measurement method to address the impact of human factors on the measurement accuracy of AACMM. By employing a surface profile deviation calculation method based on maximum deviation, the deformation of thin-walled surfaces is quantitatively evaluated. The Hammersley method is used to generate a small number of sample points to construct a Kriging model, which predicts deformation errors and their uncertainty distribution. Two sampling rules are designed: Rule 1 selects points with the highest uncertainty in predicted deformation errors to avoid local convergence; Rule 2 targets extreme points of maximum uncertainty in the predicted error distribution. This approach enables focused sampling in areas with larger deformation errors, thereby improving both measurement accuracy and efficiency. Experimental results demonstrate that the proposed method significantly enhances the reliability of thin-walled surfaces deformation measurements and exhibits strong resilience to coordinate deviations caused by handheld operations, providing an effective solution for practical applications.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117754"},"PeriodicalIF":5.2,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143921983","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":"Prediction of human-induced structural vibration based on multi-view and markerless human gait capture and BiLSTM network","authors":"Huiqi Liang ,&nbsp;Wenbo Xie ,&nbsp;Yijing Lu ,&nbsp;Peizi Wei ,&nbsp;Zhiqiang Zhang","doi":"10.1016/j.measurement.2025.117734","DOIUrl":"10.1016/j.measurement.2025.117734","url":null,"abstract":"<div><div>Human-induced structural vibration assessment is important to evaluate the vibration serviceability of a structure. Existing test methods are mostly invasive, using wearable sensors for the direct measurement of pedestrian vertical loads in vibration test. However, invasive acquisition of a nonspecific tester is impractical for the purpose of monitoring and prediction of structural vibration. Moreover, there is a lack of practical tests considering the pedestrian gait evolution and trajectory, essential for accurate vibration prediction. For this purpose, this paper presents a non-invasive method for reconstructing pedestrian gait based on multiple camera views. Combining the Skinned Multi-Person Linear Model (SMPL) human body model with a Bidirectional Long Short-Term Memory (BiLSTM) network, a mapping network for “gait-walking force” was trained. The method achieves non-invasive and non-contact prediction of human walking loads. Experimental validation on a 7.5 m × 5 m test platform confirmed the method’s precision in predicting both walking loads and structural vibrations.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117734"},"PeriodicalIF":5.2,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143921963","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-feature-based parallel DarkNet53-GhostNet-SqueezeNet for supercapacitor remaining useful life classification prediction method","authors":"Quan Lu,&nbsp;Wenju Ju,&nbsp;Linfei Yin","doi":"10.1016/j.measurement.2025.117731","DOIUrl":"10.1016/j.measurement.2025.117731","url":null,"abstract":"<div><div>Because of the complexity of the internal structure of supercapacitors, the aging information of supercapacitors is difficult to be captured fully. And the regression prediction methods for remaining useful life (RUL) exhibit errors. Instead, the classification divides several supercapacitor RULs into a life interval, which can avoid the loss caused by the regression prediction error. This study proposes a multi-feature-based parallel DarkNet53-GhostNet-SqueezeNet (PDGS) for a supercapacitor RUL classification prediction method. Classification methods are employed for the first time in predicting the supercapacitor RUL. To fully capture the features in the data and improve classification accuracy, this study selects three CNNs from multiple configured neural networks for feature extraction. The features of the three CNNs are then integrated and mapped by the fully connected layers to get more precise classification outcomes. PDGS accuracy is 13.66% higher than the best comparison result.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117731"},"PeriodicalIF":5.2,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906807","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 cell microinjection method based on multi-tasking network","authors":"Xiangyu Guo ,&nbsp;Youchao Zhang ,&nbsp;Fanghao Wang ,&nbsp;Minxuan Cao ,&nbsp;Qingyao Shu ,&nbsp;Huanyu Jiang ,&nbsp;Alois Knoll ,&nbsp;Mingchuan Zhou","doi":"10.1016/j.measurement.2025.117465","DOIUrl":"10.1016/j.measurement.2025.117465","url":null,"abstract":"<div><div>Cell injection is a fundamental technology for cell research with very important applications in biological breeding. The intelligent control of cell deformation is important to improve cell survival rate. In this article, we propose an enhanced robot-assisted cell injection method based on a deep-learning network. An attention-based multi-task perception network (AMP-Net) is proposed for cell segmentation and needle detection in robot-assisted cell injection. Based on the information extracted from the network, three metrics to describe the cell deformation are defined, total cell deformation <span><math><msub><mrow><mi>T</mi></mrow><mrow><mi>C</mi><mi>D</mi></mrow></msub></math></span>, axial cell deformation <span><math><msub><mrow><mi>A</mi></mrow><mrow><mi>C</mi><mi>D</mi></mrow></msub></math></span>, and lateral cell deformation <span><math><msub><mrow><mi>L</mi></mrow><mrow><mi>C</mi><mi>D</mi></mrow></msub></math></span>, and the puncture force is estimated by the point contact model. Finally, the cell puncture speed is automatically adjusted based on cell deformation and puncture force. The experimental result shows that the survival rate of the tested cell is 46.67% based on the proposed method, which increases 14.42% compared with the manual injection method.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117465"},"PeriodicalIF":5.2,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143921685","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 new approach for monitoring mining surface 3D deformation using UAV-LiDAR point cloud data","authors":"Xiao Wang ,&nbsp;Xilin Zhan ,&nbsp;Dawei Zhou","doi":"10.1016/j.measurement.2025.117745","DOIUrl":"10.1016/j.measurement.2025.117745","url":null,"abstract":"<div><div>This study introduces a method that leverages Unmanned Aerial Vehicle – Light Detection and Ranging (UAV-LiDAR) point cloud to monitor the three-dimensional surface deformation of a mining face accurately. The method incorporates Progressive TIN Densification (PTD) filtering to distinguish between ground and non-ground points within the UAV-LiDAR dataset. It then uses various techniques to pinpoint feature points, which are aligned using Iterative Closest Point (ICP) registration algorithm to determine corresponding points and calculate the resulting deformation of the surface caused by mining activities. By applying this deformation extraction method, two sets of UAV-LiDAR point cloud data collected at different times over the Wangjiata Coal Mine in Inner Mongolia were analyzed to evaluate three-dimensional surface deformation. Results indicate that the surface movement in the x-direction ranged from −0.69 m to 0.64 m, in the y-direction from −0.58 m to 0.53 m, and in the z-direction from −2.79 m to 0.2 m. Additionally, the refined three-dimensional deformation model demonstrated interpolation accuracies of 40 mm, 43 mm, and 74 mm in the x, y, and z directions, respectively and the external coincidence accuracy is 51 mm, 48 mm, and 55 mm respectively. This method effectively harnesses the potential of the collected point cloud data, offering a viable solution for extracting three-dimensional deformations of mining faces through UAV-LiDAR monitoring, with promising application prospects.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117745"},"PeriodicalIF":5.2,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924072","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":"Determination of physical activity energy expenditure to evaluate occupational health perception of underground mine workers","authors":"Vikram Sakinala,&nbsp;P.S. Paul","doi":"10.1016/j.measurement.2025.117760","DOIUrl":"10.1016/j.measurement.2025.117760","url":null,"abstract":"<div><div>Miner fatigue is a critical hazard in underground mining. Factors such as age, Body Mass Index (BMI), lifestyle, aerobic strength, and Physical Activity Energy Expenditure (PAEE) of miners significantly influence fatigue intensity. Therefore, this study investigated underground miner’s fatigue by analyzing the difference between PAEE at the maximum volume of oxygen consumed (VO2 max) and the peak PAEE required during a work shift. The results showed that 55.81 % of miners with very low aerobic capacity had only 45–590 kcal of energy remaining after completing an effective working shift. A Pearson correlation revealed a strong negative association (R = −0.79, p = 0.01) between fatigue and Remaining Aerobic Energy Potential (RAEP). Later, Structural Equation Modelling (SEM) was used to explore the relationships between key personal factors (age, BMI, lifestyle) and perceived health, mediated by PAEE at VO2 max, RAEP, and fatigue. The SEM analysis demonstrated that BMI and lifestyle had significant indirect effects on perceived health through PAEE at VO2 max, RAEP, and fatigue. These findings provide valuable insights for mine management in developing fatigue management strategies to enhance the health and well-being of miners.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"253 ","pages":"Article 117760"},"PeriodicalIF":5.2,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143912722","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}