Pub Date : 2024-07-03DOI: 10.1088/1361-6501/ad5ea2
Yaochi Tang, Yi Ting Chen
Currently, robots on the market have varying operational requirements due to their different functions. The care robots are primarily used to serve people under care. Therefore, reducing the amount of noise they make while moving is important. This study measured their noise in an anechoic room. This study found that the most noise is produced when they move forward and backward at full speed. The robot’s vibration signal was measured and compared with the noise source to propose the most effective way to reduce the noise. Due to the robot's small internal space, methods for noise reduction are limited. The care robot’s development must adopt quick customizable 3D printing technologies, produce sound absorption/insulation materials independently, determine the best sound absorption/insulation material and structural configuration, use impedance tubes to measure the sound absorption coefficient and sound insulation performance, and select the appropriate materials and implement them into the robot for actual tests. These results indicate that the noise value of the main contributing frequency can be reduced by 15dB at most. Furthermore, this study also used an acoustic simulation analysis to calculate and simulate the vibration and noise of the care robot. The vibration and noise signals during the robot's operation were measured and compared to provide a reference for manufacturers in design. Finally, experimental materials were added to the simulation and compared with the noise reduction results. The results show similar trends. Therefore, the model developed in this study may provide a fast, low-cost, and feasible method for the noise reduction of care robots.
目前,市场上的机器人因功能不同而有不同的操作要求。护理机器人主要用于为需要护理的人提供服务。因此,降低它们在移动过程中产生的噪音非常重要。这项研究在消声室中测量了它们的噪音。研究发现,机器人全速前进和后退时产生的噪音最大。我们测量了机器人的振动信号,并将其与噪声源进行了比较,从而提出了减少噪声的最有效方法。由于机器人内部空间狭小,降低噪音的方法有限。护理机器人的开发必须采用可快速定制的 3D 打印技术,自主生产吸音/隔音材料,确定最佳吸音/隔音材料和结构配置,使用阻抗管测量吸音系数和隔音性能,并选择合适的材料将其应用到机器人中进行实际测试。这些结果表明,主要贡献频率的噪声值最多可降低 15dB。此外,本研究还采用了声学模拟分析方法来计算和模拟护理机器人的振动和噪声。对机器人运行时的振动和噪音信号进行了测量和比较,为制造商的设计提供参考。最后,在模拟中加入了实验材料,并与降噪结果进行了比较。结果显示出相似的趋势。因此,本研究开发的模型可为护理机器人降噪提供一种快速、低成本且可行的方法。
{"title":"Study on the Noise Reduction Mechanism and Application of the Noise Simulation Analysis of Care Robots","authors":"Yaochi Tang, Yi Ting Chen","doi":"10.1088/1361-6501/ad5ea2","DOIUrl":"https://doi.org/10.1088/1361-6501/ad5ea2","url":null,"abstract":"\u0000 Currently, robots on the market have varying operational requirements due to their different functions. The care robots are primarily used to serve people under care. Therefore, reducing the amount of noise they make while moving is important. This study measured their noise in an anechoic room. This study found that the most noise is produced when they move forward and backward at full speed. The robot’s vibration signal was measured and compared with the noise source to propose the most effective way to reduce the noise. Due to the robot's small internal space, methods for noise reduction are limited. The care robot’s development must adopt quick customizable 3D printing technologies, produce sound absorption/insulation materials independently, determine the best sound absorption/insulation material and structural configuration, use impedance tubes to measure the sound absorption coefficient and sound insulation performance, and select the appropriate materials and implement them into the robot for actual tests. These results indicate that the noise value of the main contributing frequency can be reduced by 15dB at most. Furthermore, this study also used an acoustic simulation analysis to calculate and simulate the vibration and noise of the care robot. The vibration and noise signals during the robot's operation were measured and compared to provide a reference for manufacturers in design. Finally, experimental materials were added to the simulation and compared with the noise reduction results. The results show similar trends. Therefore, the model developed in this study may provide a fast, low-cost, and feasible method for the noise reduction of care robots.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141684223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-03DOI: 10.1088/1361-6501/ad5ea4
Huimin Zhao, Peixi Li, Aibin Guo, Wu Deng
Due to the limited amount of failure data in rolling bearing faults, traditional fault diagnosis models encounter challenges such as low diagnostic accuracy and efficiency when dealing with imbalanced data. Additionally, many fault diagnosis models are overly complex and demand high computational resources. To address these issues, a lightweight bearing fault diagnosis method based on Cross-Scale Learnable Transformer (CSLT) is proposed for imbalanced data. For difficult-to-classify samples, a learnable generalized focal loss function is defined. The learnable parameters are employed to increase its flexibility, it better addresses the issue of bearing fault diagnosis under imbalanced data conditions. Then, a multi-head broadcasted self-attention mechanism is designed by capturing critical local features of the signal through one-dimensional convolution operations, which not only improves feature extraction capability but also reduces computational complexity. Finally, a dynamic label prediction pruning module is developed to trim redundant labels, which helps in lightening the model and enhancing both feature extraction and diagnostic efficiency. The experimental results demonstrate that the proposed diagnosis method exhibits superior diagnostic precision and efficiency by comparing with other methods.
{"title":"Lightweight Bearing Fault Diagnosis Method Based on Cross-Scale Learning Transformer under Imbalanced Data","authors":"Huimin Zhao, Peixi Li, Aibin Guo, Wu Deng","doi":"10.1088/1361-6501/ad5ea4","DOIUrl":"https://doi.org/10.1088/1361-6501/ad5ea4","url":null,"abstract":"\u0000 Due to the limited amount of failure data in rolling bearing faults, traditional fault diagnosis models encounter challenges such as low diagnostic accuracy and efficiency when dealing with imbalanced data. Additionally, many fault diagnosis models are overly complex and demand high computational resources. To address these issues, a lightweight bearing fault diagnosis method based on Cross-Scale Learnable Transformer (CSLT) is proposed for imbalanced data. For difficult-to-classify samples, a learnable generalized focal loss function is defined. The learnable parameters are employed to increase its flexibility, it better addresses the issue of bearing fault diagnosis under imbalanced data conditions. Then, a multi-head broadcasted self-attention mechanism is designed by capturing critical local features of the signal through one-dimensional convolution operations, which not only improves feature extraction capability but also reduces computational complexity. Finally, a dynamic label prediction pruning module is developed to trim redundant labels, which helps in lightening the model and enhancing both feature extraction and diagnostic efficiency. The experimental results demonstrate that the proposed diagnosis method exhibits superior diagnostic precision and efficiency by comparing with other methods.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141681315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-03DOI: 10.1088/1361-6501/ad5ea1
D. Gauder, Johannes Gölz, Alexander Bott, Martin Stein, Gisela Lanza
Micro gears play an increasingly important role in various industrial applications, and the minimization of their deviations is challenging for metrology and manufacturing. A promising method is the focus variation technology, which enables areal measurements of micro gears. Practice-related standards are used to determine measurement uncertainties by comparison with calibration values. In this work, the external micro gear standard of the Physikalisch-Technische Bundesanstalt (PTB) is used to evaluate experimental measurement uncertainties of a focus variation coordinate measurement system for the first time. The traceable standard with modules between 0.1 and 1 mm is calibrated using micro tactile coordinate measurements. Optical and tactile measurements are then compared. As a result, small expanded measurement uncertainties of less than 4 µm are achieved.
{"title":"Experimental uncertainty evaluation by measuring a micro gear standard using focus variation","authors":"D. Gauder, Johannes Gölz, Alexander Bott, Martin Stein, Gisela Lanza","doi":"10.1088/1361-6501/ad5ea1","DOIUrl":"https://doi.org/10.1088/1361-6501/ad5ea1","url":null,"abstract":"\u0000 Micro gears play an increasingly important role in various industrial applications, and the minimization of their deviations is challenging for metrology and manufacturing. A promising method is the focus variation technology, which enables areal measurements of micro gears. Practice-related standards are used to determine measurement uncertainties by comparison with calibration values. In this work, the external micro gear standard of the Physikalisch-Technische Bundesanstalt (PTB) is used to evaluate experimental measurement uncertainties of a focus variation coordinate measurement system for the first time. The traceable standard with modules between 0.1 and 1 mm is calibrated using micro tactile coordinate measurements. Optical and tactile measurements are then compared. As a result, small expanded measurement uncertainties of less than 4 µm are achieved.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141682899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The misalignment error between the gear theoretical coordinate system and actual gear coordinate system is illustrated, as well as its influence on the measurement of tooth surface deviation is discussed. On the analysis of the tooth convex and concave surface error measurement process, the measured points in the theoretical coordinate system are transformed from the actual measured points in the actual coordinate system. Then, an eight tooth-surface fitting method is utilized to calculate the misalignment error and the compensation method is given. Finally, actual measurements of three different spiral bevel gears are analyzed, and the misalignment error are calculated. Using the proposed compensation method, both the eccentricity and tilt are compensated to some extent. And the machining suggestions of each spiral bevel gear are also given according to its compensated tooth surface error distribution.
{"title":"Compensation method of the spiral bevel gear tooth surface error based on eight tooth-surface fitting","authors":"Lihua Zhou, Suping Fang, Yongsheng Liu, Yuan Li, Ryohei Takeda, Tetsuya Taguchi","doi":"10.1088/1361-6501/ad5ea8","DOIUrl":"https://doi.org/10.1088/1361-6501/ad5ea8","url":null,"abstract":"\u0000 The misalignment error between the gear theoretical coordinate system and actual gear coordinate system is illustrated, as well as its influence on the measurement of tooth surface deviation is discussed. On the analysis of the tooth convex and concave surface error measurement process, the measured points in the theoretical coordinate system are transformed from the actual measured points in the actual coordinate system. Then, an eight tooth-surface fitting method is utilized to calculate the misalignment error and the compensation method is given. Finally, actual measurements of three different spiral bevel gears are analyzed, and the misalignment error are calculated. Using the proposed compensation method, both the eccentricity and tilt are compensated to some extent. And the machining suggestions of each spiral bevel gear are also given according to its compensated tooth surface error distribution.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141682008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-03DOI: 10.1088/1361-6501/ad5e9f
L. Ribotta, A. Delvallée, E. Cara, Roberto Bellotti, Andrea Giura, Ivan De Carlo, Fretto Matteo, Knulst Walter, R. Koops, Bruno Torre, Z. Saghi, Luca Boarino
Silicon nanowires (NWs) with a cylindrical form are fabricated by means of nanospheres lithography and metal-assisted chemical etching to obtain high aspect ratio nanostructures (diameter of about 100 nm and length of more than 15 µm) on cm2 area. The nanodimensional characterization of individual NWs is performed by using several techniques, because dimensions at the nanoscale strictly relate to functional performances. In this study, we report the results of an interlaboratory comparison between measurements from a metrological atomic force microscope (AFM) and research AFMs located in different national metrology institutes (NMIs) across Europe and in a university. The purpose of this study is to characterize two measurands: (i) sidewall roughness (Ra, Rq, Rz, Rsk, Rku parameters), extracted from the top profile measured along the nanowire length, and (ii) diameter of the nanowires measured as top-height. To this goal, the nanowires are spread horizontally on a silicon substrate, which has several areas labelled with a pattern of crosses and letters facilitating the measurement of the same NW, in order to study the reproducibility due to different instruments. Measurements show a good agreement between the different NMIs, with a combined standard uncertainty of top-height diameter less than 3%, and with a combined standard uncertainty of roughness parameters well within 5% for Ra and Rq values.
{"title":"AFM interlaboratory comparison for nanodimensional metrology on silicon nanowires","authors":"L. Ribotta, A. Delvallée, E. Cara, Roberto Bellotti, Andrea Giura, Ivan De Carlo, Fretto Matteo, Knulst Walter, R. Koops, Bruno Torre, Z. Saghi, Luca Boarino","doi":"10.1088/1361-6501/ad5e9f","DOIUrl":"https://doi.org/10.1088/1361-6501/ad5e9f","url":null,"abstract":"\u0000 Silicon nanowires (NWs) with a cylindrical form are fabricated by means of nanospheres lithography and metal-assisted chemical etching to obtain high aspect ratio nanostructures (diameter of about 100 nm and length of more than 15 µm) on cm2 area. The nanodimensional characterization of individual NWs is performed by using several techniques, because dimensions at the nanoscale strictly relate to functional performances. In this study, we report the results of an interlaboratory comparison between measurements from a metrological atomic force microscope (AFM) and research AFMs located in different national metrology institutes (NMIs) across Europe and in a university. The purpose of this study is to characterize two measurands: (i) sidewall roughness (Ra, Rq, Rz, Rsk, Rku parameters), extracted from the top profile measured along the nanowire length, and (ii) diameter of the nanowires measured as top-height. To this goal, the nanowires are spread horizontally on a silicon substrate, which has several areas labelled with a pattern of crosses and letters facilitating the measurement of the same NW, in order to study the reproducibility due to different instruments. Measurements show a good agreement between the different NMIs, with a combined standard uncertainty of top-height diameter less than 3%, and with a combined standard uncertainty of roughness parameters well within 5% for Ra and Rq values.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141680966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-02DOI: 10.1088/1361-6501/ad5dea
M. R. Rahim, MD Mofazzal Hossain, Mohd Firdaus Hassan
Despite their sensitivity potential, diaphragm-type fiber Bragg grating accelerometers with inertia mass are often too complex and large, limiting their suitability for measuring small structures. Designing a suitable accelerometer for small structures, where its weight must be less than one-tenth of the measured structure, is challenging. This paper introduces a compact, simplified, and fabricable non-inertia mass FBG accelerometer (FBGA-SD), featuring a longer FBG tunnel and a through-hole for monitoring. The proposed FBGA-SD is 16 × 16 × 10 mm, weighing 4 grams. Numerical and experimental results show good agreement, though amplitude sensitivity differs by 50%. The experimental sensitivity is 9.64 × 10-2 pm/g, while transient response analysis gives 4.79 × 10-2 pm/g, valid for 10-100 Hz excitation frequencies and up to 10.5 m/s² base acceleration.
{"title":"Development and Comprehensive Investigation of a Lightweight FBG Accelerometer for Small Structure Acceleration Measurements","authors":"M. R. Rahim, MD Mofazzal Hossain, Mohd Firdaus Hassan","doi":"10.1088/1361-6501/ad5dea","DOIUrl":"https://doi.org/10.1088/1361-6501/ad5dea","url":null,"abstract":"\u0000 Despite their sensitivity potential, diaphragm-type fiber Bragg grating accelerometers with inertia mass are often too complex and large, limiting their suitability for measuring small structures. Designing a suitable accelerometer for small structures, where its weight must be less than one-tenth of the measured structure, is challenging. This paper introduces a compact, simplified, and fabricable non-inertia mass FBG accelerometer (FBGA-SD), featuring a longer FBG tunnel and a through-hole for monitoring. The proposed FBGA-SD is 16 × 16 × 10 mm, weighing 4 grams. Numerical and experimental results show good agreement, though amplitude sensitivity differs by 50%. The experimental sensitivity is 9.64 × 10-2 pm/g, while transient response analysis gives 4.79 × 10-2 pm/g, valid for 10-100 Hz excitation frequencies and up to 10.5 m/s² base acceleration.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141686237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-02DOI: 10.1088/1361-6501/ad5dd9
Huilin Wu, Chuanzhi Sun, Yongmeng Liu, Limin Zou, Jiubin Tan
Aiming at the problem of small measurement range and difficult measurement of traditional contact sensor method in the rotating state of aero-engine blades, this paper proposes a novel deformation measurement method for rotating blade based on image correlation matching and mismatch correction. Firstly, a Particle Swarm Optimization-Iterative Local Search (PSO-ILS) image intelligent matching algorithm is proposed, which effectively balances global search and local optimization, and the image matching displacement accuracy reaches 10-3pixel. Secondly, a mismatch point detection method based on multi-scale local Root Mean Square (RMS) is proposed, and the high-precision detection of mismatch points is realized by considering the influence of local structure. Finally, through the hierarchical refinement of the sub-pixel level mismatch point correction method, the mismatch point is corrected in the two iterative stages of global search and local optimization. The corrected mismatch point response value K is reduced by 99% compared with that before correction, which further improves the accuracy of deformation field calculation. In the experiment, the deformation of the rotating blade of 4500 RPM is measured, which proves that the image intelligent matching algorithm and the deformation field calculation method proposed in this paper can provide new methods and technical support for the accurate measurement of the blade surface deformation.
针对传统接触式传感器方法在航空发动机叶片旋转状态下测量范围小、测量困难的问题,本文提出了一种基于图像相关匹配和错配校正的新型叶片旋转变形测量方法。首先,提出了粒子群优化-迭代局部搜索(PSO-ILS)图像智能匹配算法,有效兼顾了全局搜索和局部优化,图像匹配位移精度达到 10-3pixel。其次,提出了基于多尺度局部均方根(RMS)的不匹配点检测方法,通过考虑局部结构的影响实现了对不匹配点的高精度检测。最后,通过对子像素级错配点校正方法的分层细化,在全局搜索和局部优化两个迭代阶段对错配点进行校正。修正后的错配点响应值 K 比修正前降低了 99%,进一步提高了形变场计算的精度。在实验中,对转速为 4500 RPM 的叶片进行了变形测量,证明本文提出的图像智能匹配算法和变形场计算方法可以为叶片表面变形的精确测量提供新的方法和技术支持。
{"title":"A Novel Deformation Measurement Method for Rotating Blade Based on PSO-ILS Image Correlation Matching and Mismatch Correction","authors":"Huilin Wu, Chuanzhi Sun, Yongmeng Liu, Limin Zou, Jiubin Tan","doi":"10.1088/1361-6501/ad5dd9","DOIUrl":"https://doi.org/10.1088/1361-6501/ad5dd9","url":null,"abstract":"\u0000 Aiming at the problem of small measurement range and difficult measurement of traditional contact sensor method in the rotating state of aero-engine blades, this paper proposes a novel deformation measurement method for rotating blade based on image correlation matching and mismatch correction. Firstly, a Particle Swarm Optimization-Iterative Local Search (PSO-ILS) image intelligent matching algorithm is proposed, which effectively balances global search and local optimization, and the image matching displacement accuracy reaches 10-3pixel. Secondly, a mismatch point detection method based on multi-scale local Root Mean Square (RMS) is proposed, and the high-precision detection of mismatch points is realized by considering the influence of local structure. Finally, through the hierarchical refinement of the sub-pixel level mismatch point correction method, the mismatch point is corrected in the two iterative stages of global search and local optimization. The corrected mismatch point response value K is reduced by 99% compared with that before correction, which further improves the accuracy of deformation field calculation. In the experiment, the deformation of the rotating blade of 4500 RPM is measured, which proves that the image intelligent matching algorithm and the deformation field calculation method proposed in this paper can provide new methods and technical support for the accurate measurement of the blade surface deformation.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141684579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To solve the problems of easy miss and false detection on rail surface defects caused by small size, dense target, and high similarity between features and background, this paper proposed an improved detection algorithm in complex background. First, the conventional convolution of YOLOv5 backbone network is replaced with omni-dimensional dynamic convolution (ODConv), which improves the feature extraction capability of the network without increasing the computational cost; second, to improve the model's performance in detecting tiny objects, a two-layer context augmentation module(CAM) is introduced into the path aggregation network(PAN) structure; finally, the traditional non-maximum suppression(NMS) algorithm is replaced by the Soft-NMS algorithm in the network post-processing to reduce the false-alarm and miss-rate. The experimental results on the Railway Track Fault Detection public dataset show that the OD-YOLO (OD stands for ODConv) and C-PAN(CAM module is introduced into PAN) structures could achieve better performance in the same type of improved algorithms; compared with the baseline algorithm YOLOv5, the ODCS-YOLO (OD stands for ODConv, C stands for CAM, and S stands for Soft-NMS) algorithm improves the precision by 12.4%, the recall by 3.6%, the map50 by 8.6% and the GFLOPs is reduced by 0.6. Compared with seven classical object detection algorithms, the ODCS-YOLO algorithm achieves the highest detection accuracy, which makes it able to meet the real-time detection requirements of rail surface defects in real working conditions. The ODCS-YOLO model provides certain technical support for the defects detection and a new method for the detection of dense small objects.
{"title":"ODCS-YOLO detection algorithm for rail surface defects based on Omni-Dimensional Dynamic Convolution and Context Augmentation Module","authors":"wenqi gao, Wenjuan Gu, yanchao yin, tiangui li, penglin dong","doi":"10.1088/1361-6501/ad5dd5","DOIUrl":"https://doi.org/10.1088/1361-6501/ad5dd5","url":null,"abstract":"\u0000 To solve the problems of easy miss and false detection on rail surface defects caused by small size, dense target, and high similarity between features and background, this paper proposed an improved detection algorithm in complex background. First, the conventional convolution of YOLOv5 backbone network is replaced with omni-dimensional dynamic convolution (ODConv), which improves the feature extraction capability of the network without increasing the computational cost; second, to improve the model's performance in detecting tiny objects, a two-layer context augmentation module(CAM) is introduced into the path aggregation network(PAN) structure; finally, the traditional non-maximum suppression(NMS) algorithm is replaced by the Soft-NMS algorithm in the network post-processing to reduce the false-alarm and miss-rate. The experimental results on the Railway Track Fault Detection public dataset show that the OD-YOLO (OD stands for ODConv) and C-PAN(CAM module is introduced into PAN) structures could achieve better performance in the same type of improved algorithms; compared with the baseline algorithm YOLOv5, the ODCS-YOLO (OD stands for ODConv, C stands for CAM, and S stands for Soft-NMS) algorithm improves the precision by 12.4%, the recall by 3.6%, the map50 by 8.6% and the GFLOPs is reduced by 0.6. Compared with seven classical object detection algorithms, the ODCS-YOLO algorithm achieves the highest detection accuracy, which makes it able to meet the real-time detection requirements of rail surface defects in real working conditions. The ODCS-YOLO model provides certain technical support for the defects detection and a new method for the detection of dense small objects.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141685010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-02DOI: 10.1088/1361-6501/ad5de1
Ligang Wu, Le Chen, Jialong Li, Jianhua Shi, Jiafu Wan
Due to the large size of the coal and the high mining output, lump coal is one of the hidden risks of mining conveyor damage. Typically, lump coal can cause jamming and even damage to the conveyor belt during the coal mining and transportation process. This study proposes a novel real-time detection method for lump coal on a conveyor belt. The Space-to-Depth Conv (SPD-Conv) module is introduced into the feature extraction network to extract the features of the mine's low-resolution lump coal. To enhance the feature extraction capability of the model, the Normalization-based Attention Module (NAM) is combined to adjust weight sparsity. After loss function optimization using the Wise-IoU v3 (WIoU v3) module, the SPD-Conv-NAM-WIoU v3 YOLOv8 (SNW YOLO v8) model is proposed. The experimental results show that the SNW YOLOv8 model outperforms the widely used model (YOLOv8) in terms of precision and recall by 15.82% and 11.71%, respectively. Significantly, the real-time detection speed of the SNW YOLOv8 model is increased to 192.93 f/s. Compared to normal models, the SNW YOLO v8 model overcomes the disadvantages of normal models, such as being overweight, and the parameters of SNW YOLO v8 are reduced to only 6.04 million with a small model volume of 12.3 MB. Meanwhile, the floating point of SNW YOLOv8 is significantly reduced. Consequently, it demonstrates excellent lump coal detection performance, which may open up a new window for coal mining optimization.
{"title":"SNW YOLOv8: Improving the YOLOv8 Network for Real-Time Monitoring of Lump Coal","authors":"Ligang Wu, Le Chen, Jialong Li, Jianhua Shi, Jiafu Wan","doi":"10.1088/1361-6501/ad5de1","DOIUrl":"https://doi.org/10.1088/1361-6501/ad5de1","url":null,"abstract":"\u0000 Due to the large size of the coal and the high mining output, lump coal is one of the hidden risks of mining conveyor damage. Typically, lump coal can cause jamming and even damage to the conveyor belt during the coal mining and transportation process. This study proposes a novel real-time detection method for lump coal on a conveyor belt. The Space-to-Depth Conv (SPD-Conv) module is introduced into the feature extraction network to extract the features of the mine's low-resolution lump coal. To enhance the feature extraction capability of the model, the Normalization-based Attention Module (NAM) is combined to adjust weight sparsity. After loss function optimization using the Wise-IoU v3 (WIoU v3) module, the SPD-Conv-NAM-WIoU v3 YOLOv8 (SNW YOLO v8) model is proposed. The experimental results show that the SNW YOLOv8 model outperforms the widely used model (YOLOv8) in terms of precision and recall by 15.82% and 11.71%, respectively. Significantly, the real-time detection speed of the SNW YOLOv8 model is increased to 192.93 f/s. Compared to normal models, the SNW YOLO v8 model overcomes the disadvantages of normal models, such as being overweight, and the parameters of SNW YOLO v8 are reduced to only 6.04 million with a small model volume of 12.3 MB. Meanwhile, the floating point of SNW YOLOv8 is significantly reduced. Consequently, it demonstrates excellent lump coal detection performance, which may open up a new window for coal mining optimization.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141686463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-02DOI: 10.1088/1361-6501/ad5ddf
Yifan Lin, Qifeng Xu, Jun Li, Nan Xie, Yang Yang
An optical voltage sensor with an arbitrary-electrical-field-direction-modulation mode is proposed to increase the half-wave voltage without bringing additional stress and birefringence. The mode is realized by heterogeneous electrodes arranged in a center-symmetric way, and generate an electrical field with a direction at an arbitrary angle to the light propagation direction. The finite element method and coupling wave theory are used to design and optimize the electrodes and field distribution. The experimental results show that heterogeneous electrodes and arbitrary electric field direction modulation mode is able to effectively regulate the Sensor's half-wave voltage and sensitivity, without degrading the accuracy and linearity. Compared to solid voltage divider method, this modulation mode almost do not generate additional temperature drift or measurement errors caused by birefringence, but have more simple structure, less drift and higher precision.
{"title":"Half-Wave Voltage Controllable Optical Voltage Sensor with Arbitrary Electric Field Direction Modulation","authors":"Yifan Lin, Qifeng Xu, Jun Li, Nan Xie, Yang Yang","doi":"10.1088/1361-6501/ad5ddf","DOIUrl":"https://doi.org/10.1088/1361-6501/ad5ddf","url":null,"abstract":"\u0000 An optical voltage sensor with an arbitrary-electrical-field-direction-modulation mode is proposed to increase the half-wave voltage without bringing additional stress and birefringence. The mode is realized by heterogeneous electrodes arranged in a center-symmetric way, and generate an electrical field with a direction at an arbitrary angle to the light propagation direction. The finite element method and coupling wave theory are used to design and optimize the electrodes and field distribution. The experimental results show that heterogeneous electrodes and arbitrary electric field direction modulation mode is able to effectively regulate the Sensor's half-wave voltage and sensitivity, without degrading the accuracy and linearity. Compared to solid voltage divider method, this modulation mode almost do not generate additional temperature drift or measurement errors caused by birefringence, but have more simple structure, less drift and higher precision.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141685038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}