首页 > 最新文献

Measurement Science and Technology最新文献

英文 中文
Sonar image intelligent processing in seabed pipeline detection: review and application 海底管道探测中的声纳图像智能处理:回顾与应用
IF 2.4 3区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-01-08 DOI: 10.1088/1361-6501/ad1919
Bo Shi, Tianyu Cao, Qiqi Ge, Yuan Lin, Zitao Wang
Subsea pipelines rely primarily on imaging sonar for detection and identification. We analyze the imaging principles of side scan sonar, multi-beam sonar, synthetic aperture sonar, seafloor penetrating sonar and forward-looking sonar. We discuss their effectiveness in detecting seabed pipelines, as well as their limitations in image recognition capabilities. As intelligent algorithms have become increasingly important in the field of image processing, we review the sonar image intelligent detection and recognition algorithms in the past six years and summarize the internal principles and application effects of classic algorithms such as Scale-Invariant Feature Transform, K-means algorithm, and constant false-alarm rate that currently show good application prospects. Simultaneously, we review the particular strengths exhibited by these algorithms, such as contour feature extraction, image segmentation and clustering, target recognition under background noise, etc. The research on intelligent processing of sonar images opens up a new way to solve the difficult problem of the seabed targets detection and recognition.
海底管道主要依靠成像声纳进行探测和识别。我们分析了侧扫声纳、多波束声纳、合成孔径声纳、海底穿透声纳和前视声纳的成像原理。我们讨论了它们在探测海底管道方面的有效性,以及在图像识别能力方面的局限性。随着智能算法在图像处理领域越来越重要,我们回顾了近六年来的声纳图像智能检测和识别算法,总结了目前具有良好应用前景的尺度不变特征变换、K-means 算法、恒误报率等经典算法的内部原理和应用效果。同时,我们回顾了这些算法在轮廓特征提取、图像分割与聚类、背景噪声下的目标识别等方面所表现出的特殊优势。声纳图像智能处理研究为解决海底目标检测与识别这一难题开辟了新途径。
{"title":"Sonar image intelligent processing in seabed pipeline detection: review and application","authors":"Bo Shi, Tianyu Cao, Qiqi Ge, Yuan Lin, Zitao Wang","doi":"10.1088/1361-6501/ad1919","DOIUrl":"https://doi.org/10.1088/1361-6501/ad1919","url":null,"abstract":"Subsea pipelines rely primarily on imaging sonar for detection and identification. We analyze the imaging principles of side scan sonar, multi-beam sonar, synthetic aperture sonar, seafloor penetrating sonar and forward-looking sonar. We discuss their effectiveness in detecting seabed pipelines, as well as their limitations in image recognition capabilities. As intelligent algorithms have become increasingly important in the field of image processing, we review the sonar image intelligent detection and recognition algorithms in the past six years and summarize the internal principles and application effects of classic algorithms such as Scale-Invariant Feature Transform, K-means algorithm, and constant false-alarm rate that currently show good application prospects. Simultaneously, we review the particular strengths exhibited by these algorithms, such as contour feature extraction, image segmentation and clustering, target recognition under background noise, etc. The research on intelligent processing of sonar images opens up a new way to solve the difficult problem of the seabed targets detection and recognition.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":"59 15","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139447705","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}
引用次数: 0
Traceable Frequency Measurements with Counters 使用计数器进行可溯源频率测量
IF 2.4 3区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-01-08 DOI: 10.1088/1361-6501/ad1c4a
Dirk Piester, E. Staliuniene, Andreas Bauch
Received signals from Global Navigation Satellite Systems (GNSS) are nowadays widely used by industry laboratories for ensuring metrological traceability for their respective range of calibration services in the field of time and frequency. Usually, a local frequency standard is steered by continuous GNSS signal reception providing at its output stable and accurate reference signals for the laboratory measurement equipment, in general for synthesizers and counters. Reception of GNSS signals is surely an adequate and practical tool for the purpose, however further steps are needed to establish traceability in a strict metrological sense. Based on already available guidelines and publications, this paper is a contribution to the discussion how metrological traceability to internationally accepted standards can be established in a calibration laboratory. We restrict the discussion to equipment in common use which may not necessarily be of the highest sophistication. In this spirit, we develop a detailed scheme for an uncertainty budget comprising all links of the traceability chain from the device under test to the SI second, the scale-unit of Coordinated Universal Time. Then we go through and apply this scheme step by step to a demonstration setup for frequency measurements with a counter with varying operational parameters. In this framework, a novel approach to distinguish between components of statistical measurement uncertainty is introduced. Furthermore, the limiting uncertainty contributions are discussed and based on a suitable set of parameters an expression for the best measurement capability is given. With this scheme at hand a user may develop an uncertainty budget adapted to his own setup, especially if acceptance from a national accreditation body is sought.
全球导航卫星系统(GNSS)的接收信号如今被工业实验室广泛用于确保其各自时间和频率领域校准服务范围的计量溯源性。通常,本地频率标准由连续的全球导航卫星系统信号接收引导,其输出为实验室测量设备(一般为合成器和计数器)提供稳定准确的参考信号。接收全球导航卫星系统信号无疑是实现这一目的的适当而实用的工具,但还需要采取进一步措施,以建立严格计量意义上的可追溯性。本文以现有的指南和出版物为基础,讨论如何在校准实验室建立国际公认标准的计量溯源性。我们的讨论仅限于常见的设备,这些设备不一定是最先进的。本着这一精神,我们制定了不确定度预算的详细方案,包括从被测设备到协调世界时的标度单位 SI 秒的溯源链的所有环节。然后,我们逐步将这一方案应用于使用具有不同运行参数的计数器进行频率测量的演示装置。在此框架下,我们引入了一种新方法来区分统计测量不确定性的组成部分。此外,还讨论了极限不确定性的贡献,并根据一组合适的参数给出了最佳测量能力的表达式。有了这个方案,用户就可以根据自己的设置制定不确定性预算,尤其是在寻求国家认证机构认可的情况下。
{"title":"Traceable Frequency Measurements with Counters","authors":"Dirk Piester, E. Staliuniene, Andreas Bauch","doi":"10.1088/1361-6501/ad1c4a","DOIUrl":"https://doi.org/10.1088/1361-6501/ad1c4a","url":null,"abstract":"\u0000 Received signals from Global Navigation Satellite Systems (GNSS) are nowadays widely used by industry laboratories for ensuring metrological traceability for their respective range of calibration services in the field of time and frequency. Usually, a local frequency standard is steered by continuous GNSS signal reception providing at its output stable and accurate reference signals for the laboratory measurement equipment, in general for synthesizers and counters. Reception of GNSS signals is surely an adequate and practical tool for the purpose, however further steps are needed to establish traceability in a strict metrological sense. Based on already available guidelines and publications, this paper is a contribution to the discussion how metrological traceability to internationally accepted standards can be established in a calibration laboratory. We restrict the discussion to equipment in common use which may not necessarily be of the highest sophistication. In this spirit, we develop a detailed scheme for an uncertainty budget comprising all links of the traceability chain from the device under test to the SI second, the scale-unit of Coordinated Universal Time. Then we go through and apply this scheme step by step to a demonstration setup for frequency measurements with a counter with varying operational parameters. In this framework, a novel approach to distinguish between components of statistical measurement uncertainty is introduced. Furthermore, the limiting uncertainty contributions are discussed and based on a suitable set of parameters an expression for the best measurement capability is given. With this scheme at hand a user may develop an uncertainty budget adapted to his own setup, especially if acceptance from a national accreditation body is sought.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":"33 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139445247","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}
引用次数: 0
Non-ferromagnetic thin metal micron-sized defect detection system based on coherent accumulation-difference method 基于相干累积差分法的非铁磁性薄金属微米级缺陷检测系统
IF 2.4 3区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-01-08 DOI: 10.1088/1361-6501/ad1c46
Bingkun Wei, Chen Chen, Runcong Liu, Jinling Yang, Xiaodong Wang
Copper and aluminum foils serve as predominant materials in fluid collectors, and defects within them can significantly impact the electrochemical performance of cells. However, existing methods for detecting defects within non-ferromagnetic thin metals, such as copper and aluminum foils, have several limitations. This study aims to address the need for detecting micrometer-scale defects on 0.1 mm copper foils, aligning with industrial field requirements. We devised an inspection device based on the induced magnetic field detection principle and explored the impact of copper foil undulations on micrometer-scale defect detection using COMSOL modeling. Subsequently, we introduced a coherent cumulative-differential algorithm to effectively mitigate the influences of circuit noise and sampling heave noise on defect signals. Consequently, the signal-to-noise ratios of 100- and 200-micron defect signals were significantly improved by 157% and 234%, respectively. This approach shows promise for detecting micrometer-scale defects in non-ferromagnetic thin metals and lays a robust foundation for future defect identification and inversion endeavors.
铜箔和铝箔是流体收集器的主要材料,其中的缺陷会严重影响电池的电化学性能。然而,现有的非铁磁性薄金属(如铜箔和铝箔)缺陷检测方法存在一些局限性。本研究旨在满足检测 0.1 毫米铜箔上微米级缺陷的需求,以符合工业领域的要求。我们设计了一种基于感应磁场检测原理的检测设备,并利用 COMSOL 建模探索了铜箔起伏对微米级缺陷检测的影响。随后,我们引入了相干累积差分算法,以有效降低电路噪声和采样波浪噪声对缺陷信号的影响。因此,100 微米和 200 微米缺陷信号的信噪比分别显著提高了 157% 和 234%。这种方法为检测非铁磁性薄金属中的微米级缺陷带来了希望,并为未来的缺陷识别和反转工作奠定了坚实的基础。
{"title":"Non-ferromagnetic thin metal micron-sized defect detection system based on coherent accumulation-difference method","authors":"Bingkun Wei, Chen Chen, Runcong Liu, Jinling Yang, Xiaodong Wang","doi":"10.1088/1361-6501/ad1c46","DOIUrl":"https://doi.org/10.1088/1361-6501/ad1c46","url":null,"abstract":"\u0000 Copper and aluminum foils serve as predominant materials in fluid collectors, and defects within them can significantly impact the electrochemical performance of cells. However, existing methods for detecting defects within non-ferromagnetic thin metals, such as copper and aluminum foils, have several limitations. This study aims to address the need for detecting micrometer-scale defects on 0.1 mm copper foils, aligning with industrial field requirements. We devised an inspection device based on the induced magnetic field detection principle and explored the impact of copper foil undulations on micrometer-scale defect detection using COMSOL modeling. Subsequently, we introduced a coherent cumulative-differential algorithm to effectively mitigate the influences of circuit noise and sampling heave noise on defect signals. Consequently, the signal-to-noise ratios of 100- and 200-micron defect signals were significantly improved by 157% and 234%, respectively. This approach shows promise for detecting micrometer-scale defects in non-ferromagnetic thin metals and lays a robust foundation for future defect identification and inversion endeavors.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":"43 3","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139444942","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}
引用次数: 0
A novel approach for bearings multiclass fault diagnosis fusing multiscale deep convolution and hybrid attention networks 融合多尺度深度卷积和混合注意力网络的轴承多类故障诊断新方法
IF 2.4 3区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-01-08 DOI: 10.1088/1361-6501/ad1c47
Fule Li, Xinlong Zhao
Insufficient and imbalanced samples pose a significant challenge in bearing fault diagnosis, leading to low diagnosis accuracy. However, the fault characteristics of vibration signals are weak and difficult to extract when faults occur in the early stage. This paper proposes an effective fault diagnosis method that addresses small and imbalanced sample problems under noise interference. First, the number of faulty samples in the form of 1D signals is increased mainly by the sliding split sampling method. The preprocessed data are used to create 2D time–frequency diagrams using the continuous wavelet transform (CWT), which can extract effective features to improve the data quality. Subsequently, the minority samples are oversampled by combining Synthetic Minority Oversampling Technique (SMOTE) to realize TFCAO. Moreover, the clustering method and random undersampling method are introduced to prevent the overfitting and underfitting problems respectively. Then, we propose a hybrid attention mechanism to enhance the extraction of effective feature information. This combination, integrating CWT with a multicolumn modified DRN, effectively extracts fault characteristics and suppresses noise effects. The experimental results demonstrate the effectiveness of the proposed method by comparison with other advanced methods using two case studies of bearing datasets.
样本不足和不平衡是轴承故障诊断的一大挑战,导致诊断准确率较低。然而,当故障发生在早期阶段时,振动信号的故障特征较弱且难以提取。本文提出了一种有效的故障诊断方法,以解决噪声干扰下样本少和不平衡的问题。首先,主要通过滑动分割采样法增加一维信号形式的故障样本数量。预处理后的数据利用连续小波变换(CWT)创建二维时频图,从而提取有效特征,提高数据质量。随后,结合合成少数样本过采样技术(SMOTE)对少数样本进行过采样,实现 TFCAO。此外,我们还引入了聚类方法和随机欠采样方法,分别防止过拟合和欠拟合问题。然后,我们提出了一种混合注意机制,以加强对有效特征信息的提取。这种将 CWT 与多列修正 DRN 相结合的方法能有效提取故障特征并抑制噪声影响。实验结果通过与其他先进方法的比较,证明了所提方法的有效性。
{"title":"A novel approach for bearings multiclass fault diagnosis fusing multiscale deep convolution and hybrid attention networks","authors":"Fule Li, Xinlong Zhao","doi":"10.1088/1361-6501/ad1c47","DOIUrl":"https://doi.org/10.1088/1361-6501/ad1c47","url":null,"abstract":"\u0000 Insufficient and imbalanced samples pose a significant challenge in bearing fault diagnosis, leading to low diagnosis accuracy. However, the fault characteristics of vibration signals are weak and difficult to extract when faults occur in the early stage. This paper proposes an effective fault diagnosis method that addresses small and imbalanced sample problems under noise interference. First, the number of faulty samples in the form of 1D signals is increased mainly by the sliding split sampling method. The preprocessed data are used to create 2D time–frequency diagrams using the continuous wavelet transform (CWT), which can extract effective features to improve the data quality. Subsequently, the minority samples are oversampled by combining Synthetic Minority Oversampling Technique (SMOTE) to realize TFCAO. Moreover, the clustering method and random undersampling method are introduced to prevent the overfitting and underfitting problems respectively. Then, we propose a hybrid attention mechanism to enhance the extraction of effective feature information. This combination, integrating CWT with a multicolumn modified DRN, effectively extracts fault characteristics and suppresses noise effects. The experimental results demonstrate the effectiveness of the proposed method by comparison with other advanced methods using two case studies of bearing datasets.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":"31 12","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139445813","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}
引用次数: 0
A novel deep learning algorithm applied to machine vision inspection for surface defects of injection moulded products 应用于机器视觉检测注塑产品表面缺陷的新型深度学习算法
IF 2.4 3区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-01-08 DOI: 10.1088/1361-6501/ad1c4c
Haipeng Fan, Zhongjun Qiu
In modern industry, the surface defect inspection of injection moulded products is crucial for controlling product quality and optimizing the manufacturing process. With the development of optical measurement and computer technology, machine vision inspection methods have been widely adopted instead of manual inspection. However, current machine vision inspection methods are difficult to simultaneously ensure the accuracy and efficiency of surface defect inspection of injection moulded products. Considering this problem, a novel deep learning algorithm applied to machine vision inspection for surface defects of injection moulded products is proposed. To train and evaluate the proposed deep learning algorithm, an image acquisition platform is established and the dataset of surface defects in moulded products is obtained. In the proposed deep learning algorithm, reparameterization-based convolution modules are employed for feature extraction and feature fusion. A median iterative clustering algorithm based on hierarchical clustering initialization is proposed to obtain prior anchors that are highly matched with the actual distribution of defect sizes. A novel Focus-Entire Union over Covering (Focus-EUoC) loss function is utilized for bounding box regression. On these bases, the proposed deep learning algorithm applied to machine vision inspection is evaluated on the dataset of surface defects in moulded products. The experimental results indicate that compared to the traditional inspection algorithms and other deep learning algorithms currently used in machine vision inspection, the proposed deep learning algorithm exhibits superior inspection accuracy and inspection efficiency on the acquired dataset. The inspection precision reaches 0.964, the inspection recall reaches 0.955, and the inference time for each subgraph is only 6.1ms, confirming its effectiveness.
在现代工业中,注塑产品的表面缺陷检测对于控制产品质量和优化生产过程至关重要。随着光学测量和计算机技术的发展,机器视觉检测方法取代人工检测已被广泛采用。然而,目前的机器视觉检测方法很难同时确保注塑产品表面缺陷检测的准确性和效率。考虑到这一问题,本文提出了一种应用于注塑产品表面缺陷机器视觉检测的新型深度学习算法。为了训练和评估所提出的深度学习算法,建立了一个图像采集平台,并获得了注塑产品表面缺陷的数据集。在所提出的深度学习算法中,基于重参数化的卷积模块被用于特征提取和特征融合。提出了一种基于分层聚类初始化的中值迭代聚类算法,以获得与实际缺陷尺寸分布高度匹配的先验锚点。在边界框回归中使用了新颖的 Focus-Entire Union over Covering(Focus-EUoC)损失函数。在此基础上,在模制产品表面缺陷数据集上对应用于机器视觉检测的深度学习算法进行了评估。实验结果表明,与传统检测算法和目前机器视觉检测中使用的其他深度学习算法相比,所提出的深度学习算法在获取的数据集上表现出更高的检测精度和检测效率。检测精度达到 0.964,检测召回率达到 0.955,每个子图的推理时间仅为 6.1ms,证实了其有效性。
{"title":"A novel deep learning algorithm applied to machine vision inspection for surface defects of injection moulded products","authors":"Haipeng Fan, Zhongjun Qiu","doi":"10.1088/1361-6501/ad1c4c","DOIUrl":"https://doi.org/10.1088/1361-6501/ad1c4c","url":null,"abstract":"\u0000 In modern industry, the surface defect inspection of injection moulded products is crucial for controlling product quality and optimizing the manufacturing process. With the development of optical measurement and computer technology, machine vision inspection methods have been widely adopted instead of manual inspection. However, current machine vision inspection methods are difficult to simultaneously ensure the accuracy and efficiency of surface defect inspection of injection moulded products. Considering this problem, a novel deep learning algorithm applied to machine vision inspection for surface defects of injection moulded products is proposed. To train and evaluate the proposed deep learning algorithm, an image acquisition platform is established and the dataset of surface defects in moulded products is obtained. In the proposed deep learning algorithm, reparameterization-based convolution modules are employed for feature extraction and feature fusion. A median iterative clustering algorithm based on hierarchical clustering initialization is proposed to obtain prior anchors that are highly matched with the actual distribution of defect sizes. A novel Focus-Entire Union over Covering (Focus-EUoC) loss function is utilized for bounding box regression. On these bases, the proposed deep learning algorithm applied to machine vision inspection is evaluated on the dataset of surface defects in moulded products. The experimental results indicate that compared to the traditional inspection algorithms and other deep learning algorithms currently used in machine vision inspection, the proposed deep learning algorithm exhibits superior inspection accuracy and inspection efficiency on the acquired dataset. The inspection precision reaches 0.964, the inspection recall reaches 0.955, and the inference time for each subgraph is only 6.1ms, confirming its effectiveness.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":"4 6","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139446042","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}
引用次数: 0
Adaptive rotating machinery fault diagnosis method using MKIST 利用 MKIST 的自适应旋转机械故障诊断方法
IF 2.4 3区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-01-08 DOI: 10.1088/1361-6501/ad1c49
Jiliang Yi, Huabing Tan, Jun Yan, Xin Chen
An adaptive fault diagnosis method for rotating machinery based on maximum kurtosis incomplete S-transform is proposed in this paper. Firstly, the incomplete S-transform is performed on the fault frequency band of the vibration signal, and the module vector group is obtained through module calculation. Subsequently, the kurtosis of all the modulus vectors are calculated and the vector corresponding to the maximum kurtosis is located to adaptively determine the envelope of the fault frequency component in the vibration signal. Then, fast Fourier transform is performed on the envelope to obtain its main frequency, which is matched with the fault mode frequency to achieve fault diagnosis of rotating machinery. Finally, the mean peak ratio (MPR) was used to evaluate the performance of different methods under various operating conditions. The results show that the maximum MPR is obtained by the proposed method, demonstrating its stronger noise resistance and demodulation ability.
本文提出了一种基于最大峰度不完全 S 变换的旋转机械自适应故障诊断方法。首先,对振动信号的故障频带进行不完全 S 变换,通过模数计算得到模数矢量组。随后,计算所有模数矢量的峰度,找到峰度最大的对应矢量,从而自适应地确定振动信号中故障频率分量的包络。然后,对包络进行快速傅里叶变换,以获得其主频,并与故障模式频率相匹配,从而实现旋转机械的故障诊断。最后,使用平均峰值比(MPR)来评估不同方法在各种运行条件下的性能。结果表明,所提出的方法获得了最大的 MPR,显示了其更强的抗噪声和解调能力。
{"title":"Adaptive rotating machinery fault diagnosis method using MKIST","authors":"Jiliang Yi, Huabing Tan, Jun Yan, Xin Chen","doi":"10.1088/1361-6501/ad1c49","DOIUrl":"https://doi.org/10.1088/1361-6501/ad1c49","url":null,"abstract":"An adaptive fault diagnosis method for rotating machinery based on maximum kurtosis incomplete S-transform is proposed in this paper. Firstly, the incomplete S-transform is performed on the fault frequency band of the vibration signal, and the module vector group is obtained through module calculation. Subsequently, the kurtosis of all the modulus vectors are calculated and the vector corresponding to the maximum kurtosis is located to adaptively determine the envelope of the fault frequency component in the vibration signal. Then, fast Fourier transform is performed on the envelope to obtain its main frequency, which is matched with the fault mode frequency to achieve fault diagnosis of rotating machinery. Finally, the mean peak ratio (MPR) was used to evaluate the performance of different methods under various operating conditions. The results show that the maximum MPR is obtained by the proposed method, demonstrating its stronger noise resistance and demodulation ability.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":"49 20","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139447233","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}
引用次数: 0
A Steel Surface Defect Detection Model Based on Graph Neural Networks 基于图神经网络的钢铁表面缺陷检测模型
IF 2.4 3区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-01-08 DOI: 10.1088/1361-6501/ad1c4b
Wenkai Pang, Zhi Tan
Steel is an indispensable raw material in the construction industry. To avert catastrophic events such as building collapse, it is essential to detect minute defects on steel surfaces during production. However, this has been a persistent challenge due to the minuscule and dense nature of these defects. To this end, we propose an efficient defect detector called Vision Grapher with Hadamard (ViGh) , which employs a novel attention mecha-nism (HDmA) to establish local-to-local relationships within an image and integrates global relationships by graph convolution. With the HDmA module, we can not only fuse information under the same field of view, but also under different fields of view, which significantly enhances the richness of the acquired features. In addition, com-pared to convolutional neural networks, graph neural networks can utilize the contextual information in the image more effectively and resulting in better performance. We eval-uate our model on the NEU-DET and GC-10 benchmark datasets, which encompass six and ten types of defects on the surfaces of hot-rolled and cold-rolled steel, and our mod-el achieves a mean Average Precision (mAP) of 79.04% and 66.93% on the two datasets, respectively. The results demonstrate that our model significantly improves the accuracy of defect detection compared to existing methods.
钢材是建筑业不可或缺的原材料。为了避免建筑物倒塌等灾难性事件的发生,必须在生产过程中检测钢材表面的微小缺陷。然而,由于这些缺陷微小而密集,这一直是个难题。为此,我们提出了一种名为 "哈达玛视觉图像器"(Vision Grapher with Hadamard,ViGh)的高效缺陷检测器,它采用一种新颖的注意力机制(HDmA)在图像中建立局部到局部的关系,并通过图卷积来整合全局关系。利用 HDmA 模块,我们不仅可以融合同一视场下的信息,还可以融合不同视场下的信息,从而大大提高了获取特征的丰富性。此外,与卷积神经网络相比,图神经网络能更有效地利用图像中的上下文信息,从而获得更好的性能。我们在 NEU-DET 和 GC-10 基准数据集上评估了我们的模型,这两个数据集包括热轧和冷轧钢材表面的六种和十种缺陷,我们的模型在这两个数据集上的平均精度(mAP)分别达到了 79.04% 和 66.93%。结果表明,与现有方法相比,我们的模型大大提高了缺陷检测的准确性。
{"title":"A Steel Surface Defect Detection Model Based on Graph Neural Networks","authors":"Wenkai Pang, Zhi Tan","doi":"10.1088/1361-6501/ad1c4b","DOIUrl":"https://doi.org/10.1088/1361-6501/ad1c4b","url":null,"abstract":"\u0000 Steel is an indispensable raw material in the construction industry. To avert catastrophic events such as building collapse, it is essential to detect minute defects on steel surfaces during production. However, this has been a persistent challenge due to the minuscule and dense nature of these defects. To this end, we propose an efficient defect detector called Vision Grapher with Hadamard (ViGh) , which employs a novel attention mecha-nism (HDmA) to establish local-to-local relationships within an image and integrates global relationships by graph convolution. With the HDmA module, we can not only fuse information under the same field of view, but also under different fields of view, which significantly enhances the richness of the acquired features. In addition, com-pared to convolutional neural networks, graph neural networks can utilize the contextual information in the image more effectively and resulting in better performance. We eval-uate our model on the NEU-DET and GC-10 benchmark datasets, which encompass six and ten types of defects on the surfaces of hot-rolled and cold-rolled steel, and our mod-el achieves a mean Average Precision (mAP) of 79.04% and 66.93% on the two datasets, respectively. The results demonstrate that our model significantly improves the accuracy of defect detection compared to existing methods.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":"50 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139447229","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}
引用次数: 0
Comparison of aerosol spectrometers : Accounting for evaporation and sampling losses 气溶胶光谱仪的比较:考虑蒸发和采样损失
IF 2.4 3区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-01-05 DOI: 10.1088/1361-6501/ad1b9e
Xavier Lefebvre, Antonella Succar, E. Bédard, Michèle Prévost, E. Robert
Measuring aerosol size distribution with precision is critical to understand the transmission of pathogens causing respiratory illnesses and to identify risk mitigation strategies. It is however a challenging task as the size of pathogen-carrying particles evolves over time due to evaporation. Although measurement techniques well established in the field of aerosol science are often used to characterize bioaerosols, their performance is seldom assessed with respect to evaporation and deposition in sampling lines. Four instruments providing aerosol size distribution were compared using oil and water-based particles. They each rely on different measurement principles: phase doppler anemometry, light scattering, electrical mobility and aerodynamic impaction. Size distributions of oil-based particles showed consistency across different measurement instruments, but significant discrepancies arose for water-based particles undergoing evaporation. These larger differences result from both evaporation and particle deposition in transit between the sampling point and the measurement inside the instrument. Phase doppler anemometry was best suited for precise size distribution measurement, as it eliminates the need for a sampling line, thereby preventing particle loss or evaporation during transit. With this instrument as a reference, empirical correction factors for evaporation and deposition were derived from dimensionless numbers and experimental data, enabling quantitative assessment of bioaerosol size distribution using different instruments. To obtain the size distribution at the source of the aerosol generation, complete drying of a salt solution was performed. Using the complete drying technique and accounting for losses, sampling instruments can reliably provide this critical information and allow for thorough risk assessment in the context of airborne transmission.
精确测量气溶胶粒径分布对于了解导致呼吸道疾病的病原体的传播情况和确定风险缓解策略至关重要。然而,这是一项具有挑战性的任务,因为病原体携带颗粒的大小会随着时间的推移而蒸发。虽然气溶胶科学领域成熟的测量技术经常被用于描述生物气溶胶的特征,但很少对它们在采样线中的蒸发和沉积性能进行评估。我们使用油基和水基颗粒对四种提供气溶胶粒度分布的仪器进行了比较。它们各自依赖于不同的测量原理:相位多普勒风速法、光散射法、电迁移率法和气动撞击法。在不同的测量仪器上,油基颗粒的粒度分布显示出一致性,但在蒸发过程中的水基颗粒上却出现了明显的差异。这些较大的差异是由取样点与仪器内部测量之间的蒸发和颗粒沉积造成的。相位多普勒风速仪最适合精确测量粒度分布,因为它不需要采样线,从而避免了颗粒在运输过程中的损失或蒸发。以该仪器为参考,根据无量纲数字和实验数据得出了蒸发和沉积的经验修正系数,从而可以使用不同仪器对生物气溶胶的粒度分布进行定量评估。为了获得气溶胶产生源的粒度分布,对盐溶液进行了完全干燥。利用完全干燥技术并考虑到损失,采样仪器可以可靠地提供这一关键信息,并对空气传播进行全面的风险评估。
{"title":"Comparison of aerosol spectrometers : Accounting for evaporation and sampling losses","authors":"Xavier Lefebvre, Antonella Succar, E. Bédard, Michèle Prévost, E. Robert","doi":"10.1088/1361-6501/ad1b9e","DOIUrl":"https://doi.org/10.1088/1361-6501/ad1b9e","url":null,"abstract":"\u0000 Measuring aerosol size distribution with precision is critical to understand the transmission of pathogens causing respiratory illnesses and to identify risk mitigation strategies. It is however a challenging task as the size of pathogen-carrying particles evolves over time due to evaporation. Although measurement techniques well established in the field of aerosol science are often used to characterize bioaerosols, their performance is seldom assessed with respect to evaporation and deposition in sampling lines. Four instruments providing aerosol size distribution were compared using oil and water-based particles. They each rely on different measurement principles: phase doppler anemometry, light scattering, electrical mobility and aerodynamic impaction. Size distributions of oil-based particles showed consistency across different measurement instruments, but significant discrepancies arose for water-based particles undergoing evaporation. These larger differences result from both evaporation and particle deposition in transit between the sampling point and the measurement inside the instrument. Phase doppler anemometry was best suited for precise size distribution measurement, as it eliminates the need for a sampling line, thereby preventing particle loss or evaporation during transit. With this instrument as a reference, empirical correction factors for evaporation and deposition were derived from dimensionless numbers and experimental data, enabling quantitative assessment of bioaerosol size distribution using different instruments. To obtain the size distribution at the source of the aerosol generation, complete drying of a salt solution was performed. Using the complete drying technique and accounting for losses, sampling instruments can reliably provide this critical information and allow for thorough risk assessment in the context of airborne transmission.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":"32 42","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139382562","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}
引用次数: 0
A bearing fault diagnosis method with improved symplectic geometry mode decomposition and feature selection 改进的交映体几何模式分解和特征选择轴承故障诊断方法
IF 2.4 3区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-01-05 DOI: 10.1088/1361-6501/ad1ba4
Shengfan Chen, Xiaoxia Zheng
A rolling bearing fault diagnosis method based on improved symplectic geometry mode decomposition and feature selection was proposed to solve the problem of low fault identification due to the influence of noise on early bearing fault features. First, the symplectic geometry mode decomposition is improved to enhance its robustness in decomposing signals with noise, then the time domain, frequency domain, and time-frequency features of each symplectic geometric component are extracted as feature vectors. Second, a comprehensive feature selection strategy is proposed to select the optimal subset of features that are conducive to fault classification. Finally, considering the problem of low classification accuracy of a single machine learning model, the AdaBoost-WSO-SVM model is constructed for fault classification using the AdaBoost algorithm of integrated learning. Experimental decomposition of complex signals with noise indicates that the improved symplectic geometry mode decomposition is more effective compared to traditional symplectic geometry mode decomposition. Subsequently, multiple experiments were conducted using the bearing datasets from Case Western Reserve University (CWRU) and Jiangnan University (JNU). The experimental results reveal that, after comprehensive feature selection and ensemble learning pattern recognition experiments on the CWRU dataset, the average accuracy of fault diagnosis can reach 99.67%. On the JNU dataset, the proposed fault diagnosis method achieves an average accuracy of 95.03%. This suggests that, compared to other feature selection methods and classification models, the proposed approach in this paper exhibits higher accuracy and generalization capabilities.
提出了一种基于改进的交映体几何模式分解和特征选择的滚动轴承故障诊断方法,以解决由于噪声对早期轴承故障特征的影响而导致的故障识别率低的问题。首先,改进了交映体几何模式分解,以增强其在分解带噪声信号时的鲁棒性,然后提取每个交映体几何分量的时域、频域和时频特征作为特征向量。其次,提出了一种综合特征选择策略,以选择有利于故障分类的最优特征子集。最后,考虑到单一机器学习模型分类精度较低的问题,利用集成学习的 AdaBoost 算法构建了用于故障分类的 AdaBoost-WSO-SVM 模型。对带有噪声的复杂信号进行分解的实验表明,与传统的交映几何模式分解相比,改进的交映几何模式分解更为有效。随后,利用凯斯西储大学(CWRU)和江南大学(JNU)的轴承数据集进行了多次实验。实验结果表明,在 CWRU 数据集上进行综合特征选择和集合学习模式识别实验后,故障诊断的平均准确率可达 99.67%。在 JNU 数据集上,所提出的故障诊断方法的平均准确率达到了 95.03%。这表明,与其他特征选择方法和分类模型相比,本文提出的方法具有更高的准确率和泛化能力。
{"title":"A bearing fault diagnosis method with improved symplectic geometry mode decomposition and feature selection","authors":"Shengfan Chen, Xiaoxia Zheng","doi":"10.1088/1361-6501/ad1ba4","DOIUrl":"https://doi.org/10.1088/1361-6501/ad1ba4","url":null,"abstract":"\u0000 A rolling bearing fault diagnosis method based on improved symplectic geometry mode decomposition and feature selection was proposed to solve the problem of low fault identification due to the influence of noise on early bearing fault features. First, the symplectic geometry mode decomposition is improved to enhance its robustness in decomposing signals with noise, then the time domain, frequency domain, and time-frequency features of each symplectic geometric component are extracted as feature vectors. Second, a comprehensive feature selection strategy is proposed to select the optimal subset of features that are conducive to fault classification. Finally, considering the problem of low classification accuracy of a single machine learning model, the AdaBoost-WSO-SVM model is constructed for fault classification using the AdaBoost algorithm of integrated learning. Experimental decomposition of complex signals with noise indicates that the improved symplectic geometry mode decomposition is more effective compared to traditional symplectic geometry mode decomposition. Subsequently, multiple experiments were conducted using the bearing datasets from Case Western Reserve University (CWRU) and Jiangnan University (JNU). The experimental results reveal that, after comprehensive feature selection and ensemble learning pattern recognition experiments on the CWRU dataset, the average accuracy of fault diagnosis can reach 99.67%. On the JNU dataset, the proposed fault diagnosis method achieves an average accuracy of 95.03%. This suggests that, compared to other feature selection methods and classification models, the proposed approach in this paper exhibits higher accuracy and generalization capabilities.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":"106 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139383528","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}
引用次数: 0
Enhanced Curve-Based Segmentation Method for Point Clouds of Curved and Irregular Structures 基于曲线的曲面和不规则结构点云增强型分割方法
IF 2.4 3区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-01-05 DOI: 10.1088/1361-6501/ad1ba1
Limei Song, Zongyang Zhang, Chongdi Xu, Yangang Yang, Xinjun Zhu
This paper proposes an improved method for model-based segmentation of curved and irregular mounded structures in 3D measurements. The proposed method divides the point cloud data into several levels according to the reasonable width calculated from the density of points, and then fits a curve model with 2D points to each level separately. The classification results of specific types are merged to obtain specific structural measurement data in 3D space. Experiments were conducted on the proposed method using the region growth algorithm (SRG) and the model-based segmentation method (MS) provided in the PCL library as the control group. The results show that the proposed method achieves higher accuracy with a mean intersection merge ratio (MloU) of more than 0.8238, which is at least 37.92% higher than SRG and MS. The proposed method is also faster with a time-consuming only 1/5 of SRG and 1/2 of MS. Therefore, the proposed method is an effective and efficient way to segment the measurement data of curved and irregular mounded structures in 3D measurements. The method proposed in this paper has also applied in the practical robotic grinding task, the root mean square error of the grinding amount is less than 2 mm, and good grinding results are achieved.grinding results are achieved.
本文提出了一种基于模型的改进方法,用于在三维测量中对曲线和不规则土墩结构进行分割。该方法根据点的密度计算出的合理宽度,将点云数据划分为多个层次,然后分别对每个层次拟合出具有二维点的曲线模型。合并特定类型的分类结果,即可获得三维空间中的特定结构测量数据。以 PCL 库中提供的区域增长算法(SRG)和基于模型的分割方法(MS)为对照组,对提出的方法进行了实验。结果表明,提出的方法实现了更高的精确度,平均交叉合并比(MloU)超过 0.8238,比 SRG 和 MS 至少高出 37.92%。同时,所提方法耗时仅为 SRG 的 1/5、MS 的 1/2,速度更快。因此,本文提出的方法是在三维测量中分割曲面和不规则土墩结构测量数据的一种有效且高效的方法。本文提出的方法还应用于实际的机器人打磨任务中,打磨量的均方根误差小于 2 毫米,并取得了良好的打磨效果。
{"title":"Enhanced Curve-Based Segmentation Method for Point Clouds of Curved and Irregular Structures","authors":"Limei Song, Zongyang Zhang, Chongdi Xu, Yangang Yang, Xinjun Zhu","doi":"10.1088/1361-6501/ad1ba1","DOIUrl":"https://doi.org/10.1088/1361-6501/ad1ba1","url":null,"abstract":"\u0000 This paper proposes an improved method for model-based segmentation of curved and irregular mounded structures in 3D measurements. The proposed method divides the point cloud data into several levels according to the reasonable width calculated from the density of points, and then fits a curve model with 2D points to each level separately. The classification results of specific types are merged to obtain specific structural measurement data in 3D space. Experiments were conducted on the proposed method using the region growth algorithm (SRG) and the model-based segmentation method (MS) provided in the PCL library as the control group. The results show that the proposed method achieves higher accuracy with a mean intersection merge ratio (MloU) of more than 0.8238, which is at least 37.92% higher than SRG and MS. The proposed method is also faster with a time-consuming only 1/5 of SRG and 1/2 of MS. Therefore, the proposed method is an effective and efficient way to segment the measurement data of curved and irregular mounded structures in 3D measurements. The method proposed in this paper has also applied in the practical robotic grinding task, the root mean square error of the grinding amount is less than 2 mm, and good grinding results are achieved.grinding results are achieved.","PeriodicalId":18526,"journal":{"name":"Measurement Science and Technology","volume":"89 7","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139381326","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}
引用次数: 0
期刊
Measurement Science and Technology
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1