Measurement最新文献

TranP-B-site: A Transformer Enhanced Method for prediction of binding sites of Protein-protein interactions

IF 5.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Measurement

Pub Date : 2025-03-15 DOI: 10.1016/j.measurement.2025.117227

Sharzil Haris Khan , Hilal Tayara , Kil To Chong

Protein-protein interactions (PPIs) govern essential biological processes, relying on specific binding sites for molecular machinery in cells. Identifying these binding sites is crucial, with computational methods emerging as efficient alternatives to labor-intensive experimental approaches. While various techniques leverage sequential and structural information of amino acids, the limited availability of protein structural data in databases makes sequential-based models more practical. The proposed model, named TranP-B-site, employs a convolutional neural network on the transformer model’s embeddings of the sequential information of the amino acids to predict the binding sites of PPIs. First, two types of features are extracted for each amino acid in a protein sequence: one-hot encoding representing the low-level features and transformer model-based embeddings, which contain information about the entire protein sequence. These one-hot encodings and amino acid embeddings are concatenated to form two matrices. Then, two local feature sets are created by employing a windowing technique across the acquired matrices. The amino acid–based local feature set is fed into a CNN architecture, while the one-hot encoding-based local features are fed into a neural network. Finally, classification is performed on the concatenated output of the CNN and neural network using a sub-neural network. The proposed model demonstrates an improvement of 3% in MCC and 7% in accuracy compared to the previous state-of-the-art sequence-based model for independent dataset. Additionally, a new test dataset was curated from recently published protein sequences in the PDB database, and the proposed model outperformed other state-of-the-art models.

{"title":"TranP-B-site: A Transformer Enhanced Method for prediction of binding sites of Protein-protein interactions","authors":"Sharzil Haris Khan , Hilal Tayara , Kil To Chong","doi":"10.1016/j.measurement.2025.117227","DOIUrl":"10.1016/j.measurement.2025.117227","url":null,"abstract":"<div><div>Protein-protein interactions (PPIs) govern essential biological processes, relying on specific binding sites for molecular machinery in cells. Identifying these binding sites is crucial, with computational methods emerging as efficient alternatives to labor-intensive experimental approaches. While various techniques leverage sequential and structural information of amino acids, the limited availability of protein structural data in databases makes sequential-based models more practical. The proposed model, named TranP-B-site, employs a convolutional neural network on the transformer model’s embeddings of the sequential information of the amino acids to predict the binding sites of PPIs. First, two types of features are extracted for each amino acid in a protein sequence: one-hot encoding representing the low-level features and transformer model-based embeddings, which contain information about the entire protein sequence. These one-hot encodings and amino acid embeddings are concatenated to form two matrices. Then, two local feature sets are created by employing a windowing technique across the acquired matrices. The amino acid–based local feature set is fed into a CNN architecture, while the one-hot encoding-based local features are fed into a neural network. Finally, classification is performed on the concatenated output of the CNN and neural network using a sub-neural network. The proposed model demonstrates an improvement of 3% in MCC and 7% in accuracy compared to the previous state-of-the-art sequence-based model for independent dataset. Additionally, a new test dataset was curated from recently published protein sequences in the PDB database, and the proposed model outperformed other state-of-the-art models.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"251 ","pages":"Article 117227"},"PeriodicalIF":5.2,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143636543","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}

引用次数: 0

Deep Learning-Driven MRI analysis for accurate diagnosis and grading of lumbar spinal stenosis

IF 5.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Measurement

Pub Date : 2025-03-14 DOI: 10.1016/j.measurement.2025.117294

Hasan Genç , Ebubekir Seyyarer , Faruk Ayata

In recent years, deep neural networks (DNN) have emerged as an important solution due to the increasing complexity of healthcare data. Machine learning (ML) algorithms provide effective and powerful analytical methods that can uncover hidden patterns and important information from large healthcare data sets that cannot be detected in a reasonable time frame using traditional methods. Deep learning (DL) techniques have shown promise in areas such as pattern recognition and diagnosis in healthcare systems. This study aims to contribute to easier interpretation of medical data by applying different DL algorithms to MRI images of the lumbar spine collected between 2020and 2023 in a private clinic. In this context, Convolutional Neural Network (CNN) variations, EfficientNET models and methods such as k-fold cross-validation for more acceptable results, early stopping to save time and Genetic Algorithm (GA) to optimize hyperparameters are preferred. As a result of the study, success rates between 61% and 83.25% are achieved with CNN and between 86.25% and 91.56% with EfficientNET. Overall, this study aims to support medical professionals by mitigating some of the challenges in diagnosis and classification caused by image complexity when interpreting medical data.

{"title":"Deep Learning-Driven MRI analysis for accurate diagnosis and grading of lumbar spinal stenosis","authors":"Hasan Genç , Ebubekir Seyyarer , Faruk Ayata","doi":"10.1016/j.measurement.2025.117294","DOIUrl":"10.1016/j.measurement.2025.117294","url":null,"abstract":"<div><div>In recent years, deep neural networks (DNN) have emerged as an important solution due to the increasing complexity of healthcare data. Machine learning (ML) algorithms provide effective and powerful analytical methods that can uncover hidden patterns and important information from large healthcare data sets that cannot be detected in a reasonable time frame using traditional methods. Deep learning (DL) techniques have shown promise in areas such as pattern recognition and diagnosis in healthcare systems. This study aims to contribute to easier interpretation of medical data by applying different DL algorithms to MRI images of the lumbar spine collected between 2020and 2023 in a private clinic. In this context, Convolutional Neural Network (CNN) variations, EfficientNET models and methods such as k-fold cross-validation for more acceptable results, early stopping to save time and Genetic Algorithm (GA) to optimize hyperparameters are preferred. As a result of the study, success rates between 61% and 83.25% are achieved with CNN and between 86.25% and 91.56% with EfficientNET. Overall, this study aims to support medical professionals by mitigating some of the challenges in diagnosis and classification caused by image complexity when interpreting medical data.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"251 ","pages":"Article 117294"},"PeriodicalIF":5.2,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143629482","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}

引用次数: 0

The nexus of smart transportation: Self-powered and self-sensing node for autonomous rail rapid transit

IF 5.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Measurement

Pub Date : 2025-03-14 DOI: 10.1016/j.measurement.2025.117303

Fujian Liang , Yuchen Gong , Jiaoyi Wu , Zutao Zhang , Dabing Luo , Rui Zou

Smart transportation conforms to the developing trend, autonomous rail rapid transit (ART) draws attention as a new form of public transportation. In this paper, a self-powered and self-sensing node (SSN) is proposed to detect the running state of vehicles while providing electrical energy, which can be used as a link in intelligent transportation. The self-powered part stabilizes the system’s response using a zero-pressure angle mechanism and a flywheel. Establish dynamic and kinematic models to study the system response, electrical performance, and neural network model. This paper innovatively studies the enhanced flywheel and its influence on the system, and the benefit of the enhanced flywheel set system proposed is 41.6% higher than traditional flywheel. Experiments show that the energy conversion efficiency of the SSN can reach 75%, and it only takes 60 s to charge one 1.5F supercapacitor fully. In the self-sensing part, the characteristic signals are collected and encoded to generate data sets to train and test the neural network model. The results show that the detection accuracy of the SSN reaches 99.7%, indicates that it can effectively obtain the information we need. This SSN has positive implications for driving the development of ART in smart transportation.

{"title":"The nexus of smart transportation: Self-powered and self-sensing node for autonomous rail rapid transit","authors":"Fujian Liang , Yuchen Gong , Jiaoyi Wu , Zutao Zhang , Dabing Luo , Rui Zou","doi":"10.1016/j.measurement.2025.117303","DOIUrl":"10.1016/j.measurement.2025.117303","url":null,"abstract":"<div><div>Smart transportation conforms to the developing trend, autonomous rail rapid transit (ART) draws attention as a new form of public transportation. In this paper, a self-powered and self-sensing node (SSN) is proposed to detect the running state of vehicles while providing electrical energy, which can be used as a link in intelligent transportation. The self-powered part stabilizes the system’s response using a zero-pressure angle mechanism and a flywheel. Establish dynamic and kinematic models to study the system response, electrical performance, and neural network model. This paper innovatively studies the enhanced flywheel and its influence on the system, and the benefit of the enhanced flywheel set system proposed is 41.6% higher than traditional flywheel. Experiments show that the energy conversion efficiency of the SSN can reach 75%, and it only takes 60 s to charge one 1.5F supercapacitor fully. In the self-sensing part, the characteristic signals are collected and encoded to generate data sets to train and test the neural network model. The results show that the detection accuracy of the SSN reaches 99.7%, indicates that it can effectively obtain the information we need. This SSN has positive implications for driving the development of ART in smart transportation.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"251 ","pages":"Article 117303"},"PeriodicalIF":5.2,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143636622","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}

引用次数: 0

Short-term electrical load curve forecasting with MEWMA-CP monitoring techniques

IF 5.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Measurement

Pub Date : 2025-03-14 DOI: 10.1016/j.measurement.2025.117207

Yue Jin , Cheng Mingchang , Liu Liu

Load forecasting is an essential component in the power sector for effective demand-side management. A decline in forecasting accuracy can significantly compromise the efficacy of planning and management strategies, particularly in the face of substantial changes to the underlying model structure. To mitigate this challenge, rigorous model monitoring is imperative to ensure the electrical system

^{^{'}}

s reliable operation. Based on radial basis function neural network (RBF-NN) and least square support vector machine regression (LS-SVMR), an innovative prediction framework for multivariate exponential weighted moving average with cautious parameter learning (MEWMA-CP) control scheme is proposed in this paper. Central to this framework is the continuous monitoring and analysis of the residual sequence for daily electrical load data. This detailed examination allows us to meticulously track the distributions of key model features. When a significant deviation in data distribution is detected, indicating a shift from historical patterns, the proposed MEWMA-CP control scheme is activated. This scheme serves as an early warning system, triggering alerts that necessitate timely updates to the forecasting model. The MEWMA-CP control scheme is a groundbreaking addition to load forecasting methodologies, designed to ensure that the model remains current and accurate, providing a solid foundation for policy formulation and the strategic planning of future installed power capacities. The adaptability of our method to update model parameters in response to detected data distribution shifts is a distinguishing feature that sets it apart from conventional approaches. Empirical evidence from our experimental validation demonstrates the method’s capability to promptly detect changes in data distribution and dynamically update the model parameters, thereby achieving more precise and reliable prediction outcomes.

{"title":"Short-term electrical load curve forecasting with MEWMA-CP monitoring techniques","authors":"Yue Jin , Cheng Mingchang , Liu Liu","doi":"10.1016/j.measurement.2025.117207","DOIUrl":"10.1016/j.measurement.2025.117207","url":null,"abstract":"<div><div>Load forecasting is an essential component in the power sector for effective demand-side management. A decline in forecasting accuracy can significantly compromise the efficacy of planning and management strategies, particularly in the face of substantial changes to the underlying model structure. To mitigate this challenge, rigorous model monitoring is imperative to ensure the electrical system<span><math><msup><mrow></mrow><mrow><msup><mrow></mrow><mrow><mo>′</mo></mrow></msup></mrow></msup></math></span>s reliable operation. Based on radial basis function neural network (RBF-NN) and least square support vector machine regression (LS-SVMR), an innovative prediction framework for multivariate exponential weighted moving average with cautious parameter learning (MEWMA-CP) control scheme is proposed in this paper. Central to this framework is the continuous monitoring and analysis of the residual sequence for daily electrical load data. This detailed examination allows us to meticulously track the distributions of key model features. When a significant deviation in data distribution is detected, indicating a shift from historical patterns, the proposed MEWMA-CP control scheme is activated. This scheme serves as an early warning system, triggering alerts that necessitate timely updates to the forecasting model. The MEWMA-CP control scheme is a groundbreaking addition to load forecasting methodologies, designed to ensure that the model remains current and accurate, providing a solid foundation for policy formulation and the strategic planning of future installed power capacities. The adaptability of our method to update model parameters in response to detected data distribution shifts is a distinguishing feature that sets it apart from conventional approaches. Empirical evidence from our experimental validation demonstrates the method’s capability to promptly detect changes in data distribution and dynamically update the model parameters, thereby achieving more precise and reliable prediction outcomes.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"251 ","pages":"Article 117207"},"PeriodicalIF":5.2,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143636540","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}

引用次数: 0

Variable reluctance generator assisted intelligent monitoring and diagnosis of wind turbine spherical roller bearings

IF 5.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Measurement

Pub Date : 2025-03-14 DOI: 10.1016/j.measurement.2025.117264

Qiyi Dai , Chen Zheng , Song Wang , Tenghao Ma , Yun Kong , Shuai Gao , Qinkai Han

The development of intelligent spherical roller bearings (ISRBs) with self-powered, sensing, and diagnostic capabilities is crucial for enhancing wind turbine platform operation and maintenance. This study introduces a finite-number roller-based variable reluctance generator (FR-VRG) as a promising approach for ISRB construction. In the FR-VRG, the limited number of bearing rollers creates a gap between adjacent rollers, allowing each roller to periodically pass through a magnetic circuit consisting of a coil, iron core, and permanent magnet. This movement causes a variable reluctance effect, which induces current in the coil, achieving electromechanical energy conversion. Since the coil and permanent magnet are fixed and do not rotate, they have minimal impact on the rotating parts of the bearing. Key design parameters, including coil turns, coil-to-roller distance, and iron core material, were tested and analyzed for their effect on the FR-VRG’s self-power performance. We applied the fast Fourier transform and deep learning methods to classify typical bearing faults, and the system achieved an accuracy of 94.05%. The FR-VRG’s power generation mechanism was verified through theoretical and simulation analyses. Additionally, the self-sensing and diagnosis capability of the ISRB with the FR-VRG was verified on a wind turbine test setup, where sensing tests were conducted at variable speeds. The proposed FR-VRG provides an effective alternative for constructing intelligent wind turbine operation and maintenance systems.

{"title":"Variable reluctance generator assisted intelligent monitoring and diagnosis of wind turbine spherical roller bearings","authors":"Qiyi Dai , Chen Zheng , Song Wang , Tenghao Ma , Yun Kong , Shuai Gao , Qinkai Han","doi":"10.1016/j.measurement.2025.117264","DOIUrl":"10.1016/j.measurement.2025.117264","url":null,"abstract":"<div><div>The development of intelligent spherical roller bearings (ISRBs) with self-powered, sensing, and diagnostic capabilities is crucial for enhancing wind turbine platform operation and maintenance. This study introduces a finite-number roller-based variable reluctance generator (FR-VRG) as a promising approach for ISRB construction. In the FR-VRG, the limited number of bearing rollers creates a gap between adjacent rollers, allowing each roller to periodically pass through a magnetic circuit consisting of a coil, iron core, and permanent magnet. This movement causes a variable reluctance effect, which induces current in the coil, achieving electromechanical energy conversion. Since the coil and permanent magnet are fixed and do not rotate, they haveminimal impact ontherotating parts of the bearing. Key design parameters, including coil turns, coil-to-roller distance, and iron core material, were tested and analyzedfor their effect on the FR-VRG’s self-power performance. We applied the fast Fourier transform and deep learning methods to classify typical bearing faults, andthe system achieved an accuracy of 94.05%. The FR-VRG’s power generation mechanism was verified through theoretical and simulation analyses. Additionally, the self-sensing and diagnosis capability of the ISRB with the FR-VRG was verified on a wind turbine test setup, where sensing tests were conducted at variable speeds. The proposed FR-VRG provides an effective alternative for constructing intelligent wind turbine operation and maintenance systems.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"251 ","pages":"Article 117264"},"PeriodicalIF":5.2,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143636621","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}

引用次数: 0

Modeling wireless power transfer in marine environment via integrated electromagnetic field and circuit analysis

IF 5.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Measurement

Pub Date : 2025-03-14 DOI: 10.1016/j.measurement.2025.117224

Shimin Wang, Wangqiang Niu, Xianwen Zhou

In the marine environment, wireless power transfer faces significant eddy current effects due to the high electrical conductivity of seawater, making traditional modeling in the air environment inapplicable. In order to understand the effect of seawater on wireless power transfer, a circuit model whose key electric parameters are determined from electromagnetic field theory is proposed for series–parallel topological wireless power transfer in seawater. Firstly, the complex mutual inductance and complex self-inductance of the circuit model are calculated from in depth analysis of electromagnetic fields model of wireless power transfer under seawater. Subsequently, these parameters are incorporated into an equivalent circuit model, which contributes to more accurate circuit calculations and ensures the completeness and accuracy of the model. To validate the proposed model, a seawater wireless power transfer system with a 22.5 cm coil outer diameter and a 460 kHz resonant frequency is designed, and implemented. Its complex mutual inductance, complex self-inductance, load voltages and transfer efficiencies are calculated and then measured experimentally. Three methods were used to verify the complex mutual inductance and complex self-inductance: LCR method, open circuit method on the secondary side and simulation. While the load voltage and transmission efficiency are verified experimentally. The obtained theoretical calculations, electromagnetic simulations and experimental results are in good agreement. Through integration of electromagnetic field analysis and circuit analysis, the modeling of wireless power transfer is transformed from the traditional dependence on external excitation sources to a more autonomous and endogenous approach.

{"title":"Modeling wireless power transfer in marine environment via integrated electromagnetic field and circuit analysis","authors":"Shimin Wang, Wangqiang Niu, Xianwen Zhou","doi":"10.1016/j.measurement.2025.117224","DOIUrl":"10.1016/j.measurement.2025.117224","url":null,"abstract":"<div><div>In the marine environment, wireless power transfer faces significant eddy current effects due to the high electrical conductivity of seawater, making traditional modeling in the air environment inapplicable. In order to understand the effect of seawater on wireless power transfer, a circuit model whose key electric parameters are determined from electromagnetic field theory is proposed for series–parallel topological wireless power transfer in seawater. Firstly, the complex mutual inductance and complex self-inductance of the circuit model are calculated from in depth analysis of electromagnetic fields model of wireless power transfer under seawater. Subsequently, these parameters are incorporated into an equivalent circuit model, which contributes to more accurate circuit calculations and ensures the completeness and accuracy of the model. To validate the proposed model, a seawater wireless power transfer system with a 22.5 cm coil outer diameter and a 460 kHz resonant frequency is designed, and implemented. Its complex mutual inductance, complex self-inductance, load voltages and transfer efficiencies are calculated and then measured experimentally. Three methods were used to verify the complex mutual inductance and complex self-inductance: LCR method, open circuit method on the secondary side and simulation. While the load voltage and transmission efficiency are verified experimentally. The obtained theoretical calculations, electromagnetic simulations and experimental results are in good agreement. Through integration of electromagnetic field analysis and circuit analysis, the modeling of wireless power transfer is transformed from the traditional dependence on external excitation sources to a more autonomous and endogenous approach.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"251 ","pages":"Article 117224"},"PeriodicalIF":5.2,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143629157","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}

引用次数: 0

Laser head integrated chromatic confocal system for coaxial measurement of deposited clads

IF 5.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Measurement

Pub Date : 2025-03-13 DOI: 10.1016/j.measurement.2025.117290

Adrian Zakrzewski, Piotr Koruba, Jakub Mazur, Jacek Reiner

This paper presents the results of a coaxial measurement of the height of a cladding structure using an optical system integrated with a laser head for laser metal deposition. The developed system was designed based on numerical analyses. An analysis of the interaction of the components of the system’s optical path on its functional parameters was carried out. An algorithm based on the lognormal model was proposed to process the acquired spectral data. In addition, the factors having a significant impact on the obtained values of the functional parameters were analyzed, i.e. the inhomogeneity of the material surface and the low repeatability of the positioning of the robot arm. The metrological evaluation of the system in terms of measurement range, trueness, linearity, precision, accuracy and resolution was presented. Finally, the developed system was validated by comparing the measured heights of deposited clads with those obtained by a laser triangulator system.

引用次数: 0

Cycle slip and data gap processing based on the geometry-free, geometry-based, and geometry-fixed methods for different receiver types

IF 5.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Measurement

Pub Date : 2025-03-13 DOI: 10.1016/j.measurement.2025.117253

Xiaohan Wang , Zhetao Zhang , Jinwen Zeng , Yong Wang

GNSS precise positioning is based on carrier phase measurements, such as precise point positioning (PPP). However, cycle slips and data gaps in measurements are frequent, which can seriously affect the positioning accuracy. How to appropriately handle the geometric term is an inevitable issue for repairing cycle slips and data gaps. While existing methods have been proposed, there remains a notable research gap in comprehensively understanding how different geometric models interact with various receiver types, particularly under complex conditions such as ionospheric activity and long data gaps. Focusing on the cycle slip and data gap for the different receiver types, this paper systematically and comprehensively studies the geometry-free (GF), geometry-based (GB), and geometry-fixed (GFix) methods through theoretical analysis, designed experiments, and field tests for the first time. In the designed experiments, the minimal detectable cycle slips (MDCs) of these three methods are determined, and their detection capabilities for multiple cycle slips and insensitive cycle slips are discussed. In the field tests, the three methods are used with high-end receiver, low-cost board, and smart phone to investigate their applicability under different conditions. The results show that the accuracy of the GF and GFix methods can reach 1 cycle under good observation conditions with short sampling intervals, but if data gaps occur (e.g., 60 s) the performance of both methods degrades due to atmospheric delays. In addition, they are sensitive to measurement noise and are particularly suited to high-end receivers. The MDC of the GB method is 4 cycles due to the excessive parameters to be estimated. However, the GB method has great potential if constraints and enough redundant measurements are added. This method reduces the impact of measurement noise by least squares, it is recommended for processing data from low-cost boards. For smart phones, due to the complexity of the cycle slips, several methods can be combined for processing. Compared with the results without cycle slip processing, these three methods can improve the 3D root mean square error by 91.3 %, 92.5 %, and 92.0 % respectively with low-cost boards.

全球导航卫星系统的精确定位基于载波相位测量，如精确点定位（PPP）。然而，测量中经常出现周期滑动和数据间隙，这会严重影响定位精度。如何适当处理几何项是修复周期滑移和数据间隙不可避免的问题。虽然已经提出了现有的方法，但在全面了解不同几何模型如何与各种接收机类型相互作用方面，尤其是在电离层活动和长数据间隙等复杂条件下，仍然存在明显的研究差距。本文以不同接收机类型的周期滑移和数据间隙为重点，通过理论分析、设计实验和现场测试，首次系统全面地研究了无几何模型（GF）、基于几何模型（GB）和固定几何模型（GFix）方法。在设计实验中，确定了这三种方法的最小可检测周期滑移 (MDC)，并讨论了它们对多周期滑移和不敏感周期滑移的检测能力。在现场测试中，三种方法分别与高端接收器、低成本电路板和智能手机配合使用，以考察它们在不同条件下的适用性。结果表明，在短采样间隔的良好观测条件下，GF 和 GFix 方法的精度可达 1 个周期，但如果出现数据间隙（如 60 秒），这两种方法的性能会因大气延迟而下降。此外，这两种方法对测量噪声比较敏感，特别适用于高端接收机。由于需要估计的参数过多，GB 方法的 MDC 为 4 个周期。不过，如果增加限制条件和足够的冗余测量，GB 方法还是有很大潜力的。这种方法通过最小二乘法减少了测量噪声的影响，建议用于处理来自低成本电路板的数据。对于智能手机，由于周期滑动的复杂性，可以结合几种方法进行处理。与未进行周期滑动处理的结果相比，这三种方法可将低成本电路板的三维均方根误差分别提高 91.3%、92.5% 和 92.0%。

{"title":"Cycle slip and data gap processing based on the geometry-free, geometry-based, and geometry-fixed methods for different receiver types","authors":"Xiaohan Wang , Zhetao Zhang , Jinwen Zeng , Yong Wang","doi":"10.1016/j.measurement.2025.117253","DOIUrl":"10.1016/j.measurement.2025.117253","url":null,"abstract":"<div><div>GNSS precise positioning is based on carrier phase measurements, such as precise point positioning (PPP). However, cycle slips and data gaps in measurements are frequent, which can seriously affect the positioning accuracy. How to appropriately handle the geometric term is an inevitable issue for repairing cycle slips and data gaps. While existing methods have been proposed, there remains a notable research gap in comprehensively understanding how different geometric models interact with various receiver types, particularly under complex conditions such as ionospheric activity and long data gaps. Focusing on the cycle slip and data gap for the different receiver types, this paper systematically and comprehensively studies the geometry-free (GF), geometry-based (GB), and geometry-fixed (GFix) methods through theoretical analysis, designed experiments, and field tests for the first time. In the designed experiments, the minimal detectable cycle slips (MDCs) of these three methods are determined, and their detection capabilities for multiple cycle slips and insensitive cycle slips are discussed. In the field tests, the three methods are used with high-end receiver, low-cost board, and smart phone to investigate their applicability under different conditions. The results show that the accuracy of the GF and GFix methods can reach 1 cycle under good observation conditions with short sampling intervals, but if data gaps occur (e.g., 60 s) the performance of both methods degrades due to atmospheric delays. In addition, they are sensitive to measurement noise and are particularly suited to high-end receivers. The MDC of the GB method is 4 cycles due to the excessive parameters to be estimated. However, the GB method has great potential if constraints and enough redundant measurements are added. This method reduces the impact of measurement noise by least squares, it is recommended for processing data from low-cost boards. For smart phones, due to the complexity of the cycle slips, several methods can be combined for processing. Compared with the results without cycle slip processing, these three methods can improve the 3D root mean square error by 91.3 %, 92.5 %, and 92.0 % respectively with low-cost boards.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"251 ","pages":"Article 117253"},"PeriodicalIF":5.2,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143637220","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}

引用次数: 0

ECL-Tear: Lightweight detection method for multiple types of belt tears

IF 5.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Measurement

Pub Date : 2025-03-13 DOI: 10.1016/j.measurement.2025.117269

Xiaopan Wang, Shuting Wan, Zhonghang Li, Xiaoxiao Chen, Bolin Zhang, Yilong Wang

Belt tearing can disrupt coal transmission systems and compromise power supply stability. Current detection methods primarily focus on identifying longitudinal tears, which lack the capability for multiple tear types and resilience to harsh environments. This paper proposes the ECL-Tear lightweight target detection algorithm to address these limitations. The algorithm integrates Efficient Multi-Scale Convolution (EIEM) into the YOLOv11 backbone network, replacing standard convolution with multi-scale convolution to enhance edge information capture. In the neck network, Coord Attention-High-level Screening-Feature Pyramid Networks (CA-HSFPN) reduce parameters via adaptive pooling and replace channel attention with coordinate attention for precise weight adjustment of tear locations. The detection head is upgraded to a Lightweight Shared Detail-enhanced Convolutional Detection Head (LSDECD), which uses shared and distributed feedback convolutional layers to lower computational complexity and dynamically generate anchor sizes for diverse image dimensions and tear types. A Multidimensional Augmentation Strategy (MAS) expands 370 field-collected images to 1214 for training. Experimental results demonstrate that ECL-Tear achieves 94 % and 59 % on mAP50 and mAP50-90, respectively, with a 3.7 MB weight file, 1.587 × 10⁶ parameters, and an FPS of 190.2, outperforming other YOLO algorithms. This approach significantly improves belt tear detection accuracy and speed, offering critical support for coal conveyor system fault detection.

{"title":"ECL-Tear: Lightweight detection method for multiple types of belt tears","authors":"Xiaopan Wang, Shuting Wan, Zhonghang Li, Xiaoxiao Chen, Bolin Zhang, Yilong Wang","doi":"10.1016/j.measurement.2025.117269","DOIUrl":"10.1016/j.measurement.2025.117269","url":null,"abstract":"<div><div>Belt tearing can disrupt coal transmission systems and compromise power supply stability. Current detection methods primarily focus on identifying longitudinal tears, which lack the capability for multiple tear types and resilience to harsh environments. This paper proposes the ECL-Tear lightweight target detection algorithm to address these limitations. The algorithm integrates Efficient Multi-Scale Convolution (EIEM) into the YOLOv11 backbone network, replacing standard convolution with multi-scale convolution to enhance edge information capture. In the neck network, Coord Attention-High-level Screening-Feature Pyramid Networks (CA-HSFPN) reduce parameters via adaptive pooling and replace channel attention with coordinate attention for precise weight adjustment of tear locations. The detection head is upgraded to a Lightweight Shared Detail-enhanced Convolutional Detection Head (LSDECD), which uses shared and distributed feedback convolutional layers to lower computational complexity and dynamically generate anchor sizes for diverse image dimensions and tear types. A Multidimensional Augmentation Strategy (MAS) expands 370 field-collected images to 1214 for training. Experimental results demonstrate that ECL-Tear achieves 94 % and 59 % on mAP50 and mAP50-90, respectively, with a 3.7 MB weight file, 1.587 × 10⁶ parameters, and an FPS of 190.2, outperforming other YOLO algorithms. This approach significantly improves belt tear detection accuracy and speed, offering critical support for coal conveyor system fault detection.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"251 ","pages":"Article 117269"},"PeriodicalIF":5.2,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143636544","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}

引用次数: 0

Asymmetric-dot-pattern fusion fault identification of motor-driven belt transmission system in industrial robots

IF 5.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Measurement

Pub Date : 2025-03-13 DOI: 10.1016/j.measurement.2025.117267

Hongbo Wang , Yuting Qiao , Yaguo Lei , Naipeng Li , Yanxin Zhang , Junyi Cao

The motor-driven belt transmission component is one of the most important parts in industrial robots on smart manufacturing production line. The complex motion and progressive wear may reduce their reliability and potentially lead to significant operational losses. Meanwhile, it is difficult to extract effective features from vibration signal for fault diagnosis due to the inherent buffering characteristics of the belts. However, the current signals can compensate the loss of some fault information with their sensitivity to the abnormal change of transmission torque. Therefore, an asymmetric-dot-pattern (aSDP) vibration and current fusion diagnosis strategy is proposed to accurately identify various fault types of motor-driven belt transmission. The current and vibration signals are fused into a single aSDP image based on empirical mode components in the same frequency band. In order to characterize the features from different aSDP images, the similarity between the aSDP images of unknown and template faults is calculated by the fusion of perceptual and difference hash. Furthermore, a weighted similarity mechanism is proposed to address the inconsistent classification of the similarity feature in different bands. Motor-driven belt transmission experiments are conducted on an industrial robot to validate the proposed current and vibration fusion methods under different conditions. Experiment results show the average fault identification accuracy of the proposed method is 98.70%. It demonstrates that the proposed method is capable of fusing current and vibration signals effectively for diagnosing faults of motor-driven transmission with flexible components and is preferable of the superior performance when compared to existing methods.

{"title":"Asymmetric-dot-pattern fusion fault identification of motor-driven belt transmission system in industrial robots","authors":"Hongbo Wang , Yuting Qiao , Yaguo Lei , Naipeng Li , Yanxin Zhang , Junyi Cao","doi":"10.1016/j.measurement.2025.117267","DOIUrl":"10.1016/j.measurement.2025.117267","url":null,"abstract":"<div><div>The motor-driven belt transmission component is one of the most important parts in industrial robots on smart manufacturing production line. The complex motion and progressive wear may reduce their reliability and potentially lead to significant operational losses. Meanwhile, it is difficult to extract effective features from vibration signal for fault diagnosis due to the inherent buffering characteristics of the belts. However, the current signals can compensate the loss of some fault information with their sensitivity to the abnormal change of transmission torque. Therefore, an asymmetric-dot-pattern (aSDP) vibration and current fusion diagnosis strategy is proposed to accurately identify various fault types of motor-driven belt transmission. The current and vibration signals are fused into a single aSDP image based on empirical mode components in the same frequency band. In order to characterize the features from different aSDP images, the similarity between the aSDP images of unknown and template faults is calculated by the fusion of perceptual and difference hash. Furthermore, a weighted similarity mechanism is proposed to address the inconsistent classification of the similarity feature in different bands. Motor-driven belt transmission experiments are conducted on an industrial robot to validate the proposed current and vibration fusion methods under different conditions. Experiment results show the average fault identification accuracy of the proposed method is 98.70%. It demonstrates that the proposed method is capable of fusing current and vibration signals effectively for diagnosing faults of motor-driven transmission with flexible components and is preferable of the superior performance when compared to existing methods.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"251 ","pages":"Article 117267"},"PeriodicalIF":5.2,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143636547","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}

引用次数: 0