Pub Date : 2024-07-22DOI: 10.1088/1361-6501/ad6623
M. Ellmeier, A. Betzler, C. Amtmann, A. Pollinger, C. Hagen, I. Jernej, M. Agú, W. Magnes, L. Windholz, Michele Dougherty, Patrick Brown, R. Lammegger
The Coupled Dark State Magnetometer (CDSM) is an optically pumped magnetometer. For the Jupiter Icy Moons Explorer (JUICE) mission, the CDSM and two fluxgate magnetometers are combined in the J-MAG instrument to measure the static and low frequency magnetic field in the Jupiter system. During certain calibration manoeuvres, the CDSM has to be able to measure magnetic field strengths down to 100 nT with an accuracy of 0.2 nT (1 σ). At such low magnetic fields, the CDSM’s operational parameters must be carefully selected to obtain narrow resonance structures. Otherwise, the coupled dark state resonances, used for the magnetic field detection in different instrument modes, overlap and result in a systematic error. In this paper we demonstrate that with the found instrument settings the CDSM is able to measure magnetic field strengths below 100 nT with a systematic error less than 0.2 nT resulting from the overlap of the resonances.
耦合暗态磁强计（CDSM）是一种光学泵浦磁强计。在木星冰月探测器（JUICE）任务中，耦合暗态磁强计和两个磁通门磁强计被组合到 J-MAG 仪器中，用于测量木星系统中的静态和低频磁场。在某些校准动作中，CDSM 必须能够测量低至 100 nT 的磁场强度，精度为 0.2 nT（1 σ）。在如此低的磁场中，必须仔细选择 CDSM 的运行参数，以获得窄共振结构。否则，在不同仪器模式下用于磁场探测的耦合暗态共振会发生重叠，从而产生系统误差。在本文中，我们证明了在已找到的仪器设置下，CDSM 能够测量低于 100 nT 的磁场强度，共振重叠导致的系统误差小于 0.2 nT。
{"title":"Lower magnetic field measurement limit of the Coupled Dark State Magnetometer","authors":"M. Ellmeier, A. Betzler, C. Amtmann, A. Pollinger, C. Hagen, I. Jernej, M. Agú, W. Magnes, L. Windholz, Michele Dougherty, Patrick Brown, R. Lammegger","doi":"10.1088/1361-6501/ad6623","DOIUrl":"https://doi.org/10.1088/1361-6501/ad6623","url":null,"abstract":"\u0000 The Coupled Dark State Magnetometer (CDSM) is an optically pumped magnetometer. For the Jupiter Icy Moons Explorer (JUICE) mission, the CDSM and two fluxgate magnetometers are combined in the J-MAG instrument to measure the static and low frequency magnetic field in the Jupiter system. During certain calibration manoeuvres, the CDSM has to be able to measure magnetic field strengths down to 100 nT with an accuracy of 0.2 nT (1 σ). At such low magnetic fields, the CDSM’s operational parameters must be carefully selected to obtain narrow resonance structures. Otherwise, the coupled dark state resonances, used for the magnetic field detection in different instrument modes, overlap and result in a systematic error. In this paper we demonstrate that with the found instrument settings the CDSM is able to measure magnetic field strengths below 100 nT with a systematic error less than 0.2 nT resulting from the overlap of the resonances.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"24 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141815670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-22DOI: 10.1088/1361-6501/ad662e
jiayi Xin, Hongkai Jiang, Wenxin Jiang, Lintao Li
The extraction of fault features from rolling bearings is a challenging and highly important task. Since they have complex operating conditions and are usually under a strong noise background. In this study, a novel approach termed phase space feature extraction guided by an adaptive feature mode decomposition (AFMDPSFE) is proposed to detect subtle faults in rolling bearings. Initially, a new method using Kullback-Leiber divergence is introduced to automatically select the optimal mode number and filter length for the decomposition of vibration signals, facilitating the automatic extraction of optimal components and ensuring efficient screening. This eliminates the need for manual configuration of feature mode decomposition parameters. Furthermore, a criterion that could determine two crucial parameters to capture system dynamics characteristics in phase space reconstruction is embedded into AFMDPSFE algorithm. Subsequently, a series of high-dimensional independent components is derived. The envelope spectrum of the principal component exhibiting the highest kurtosis value is computed to achieve fault identification, consequently enhancing the separation of signal from noise. Both simulations and experimental results confirm the effectiveness of AFMDPSFE approach. A comparison analysis shows the excellent performance of AFMDPSFE in extracting fault features from significant noise interference.
{"title":"An adaptive feature mode decomposition-guided phase space feature extraction method for rolling bearing fault diagnosis","authors":"jiayi Xin, Hongkai Jiang, Wenxin Jiang, Lintao Li","doi":"10.1088/1361-6501/ad662e","DOIUrl":"https://doi.org/10.1088/1361-6501/ad662e","url":null,"abstract":"\u0000 The extraction of fault features from rolling bearings is a challenging and highly important task. Since they have complex operating conditions and are usually under a strong noise background. In this study, a novel approach termed phase space feature extraction guided by an adaptive feature mode decomposition (AFMDPSFE) is proposed to detect subtle faults in rolling bearings. Initially, a new method using Kullback-Leiber divergence is introduced to automatically select the optimal mode number and filter length for the decomposition of vibration signals, facilitating the automatic extraction of optimal components and ensuring efficient screening. This eliminates the need for manual configuration of feature mode decomposition parameters. Furthermore, a criterion that could determine two crucial parameters to capture system dynamics characteristics in phase space reconstruction is embedded into AFMDPSFE algorithm. Subsequently, a series of high-dimensional independent components is derived. The envelope spectrum of the principal component exhibiting the highest kurtosis value is computed to achieve fault identification, consequently enhancing the separation of signal from noise. Both simulations and experimental results confirm the effectiveness of AFMDPSFE approach. A comparison analysis shows the excellent performance of AFMDPSFE in extracting fault features from significant noise interference.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"32 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141816900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-22DOI: 10.1088/1361-6501/ad662a
Zechao Liu, Jingzhao Li, Changlu Zheng, G. Wang
Monorail cranes are crucial in facilitating auxiliary transportation within deep mining operations. As unmanned driving technology becomes increasingly prevalent in monorail crane operations, it encounters challenges such as low accuracy and unreliable attitude recognition, significantly jeopardizing the safety of monorail crane operations. Hence, this study proposes a dynamic inclination estimation methodology utilizing the Estimation-Focused-EKFNet algorithm. Firstly, based on the driving characteristics of the monorail crane, a dynamic inclination model of the monorail crane is established, based on which the dynamic inclination value can be calculated in real-time by the extended Kalman filter (EKF) estimator; however, given the complexity of the driving road conditions, in order to improve the dynamic inclination recognition accuracy, the CNN-LSTM-ATT algorithm combining the convolutional neural network (CNN), the long short-term memory (LSTM) neural network and the attention mechanism (ATT) is used to firstly predict the current dynamic camber is predicted by the CNN-LSTM-ATT algorithm combined with the convolutional neural network and the attention mechanism, and then the predicted dynamic inclination value is used as the observation value of the EKF estimator, which finally realizes that the EKF estimator can output the accurate dynamic inclination value in real-time. Experimental results indicate that, compared with the unscented Kalman filter (UKF), LSTM-ATT, and CNN-LSTM algorithms, the Estimation-Focused-EKFNet algorithm enhances dynamic inclination recognition in complex road conditions by at least 52.34%, significantly improving recognition reliability. Its recognition accuracy reaches 99.28%, effectively ensuring the safety of unmanned driving for monorail cranes.
{"title":"Data-driven dynamic inclination angle estimation of monorail crane under complex road conditions","authors":"Zechao Liu, Jingzhao Li, Changlu Zheng, G. Wang","doi":"10.1088/1361-6501/ad662a","DOIUrl":"https://doi.org/10.1088/1361-6501/ad662a","url":null,"abstract":"\u0000 Monorail cranes are crucial in facilitating auxiliary transportation within deep mining operations. As unmanned driving technology becomes increasingly prevalent in monorail crane operations, it encounters challenges such as low accuracy and unreliable attitude recognition, significantly jeopardizing the safety of monorail crane operations. Hence, this study proposes a dynamic inclination estimation methodology utilizing the Estimation-Focused-EKFNet algorithm. Firstly, based on the driving characteristics of the monorail crane, a dynamic inclination model of the monorail crane is established, based on which the dynamic inclination value can be calculated in real-time by the extended Kalman filter (EKF) estimator; however, given the complexity of the driving road conditions, in order to improve the dynamic inclination recognition accuracy, the CNN-LSTM-ATT algorithm combining the convolutional neural network (CNN), the long short-term memory (LSTM) neural network and the attention mechanism (ATT) is used to firstly predict the current dynamic camber is predicted by the CNN-LSTM-ATT algorithm combined with the convolutional neural network and the attention mechanism, and then the predicted dynamic inclination value is used as the observation value of the EKF estimator, which finally realizes that the EKF estimator can output the accurate dynamic inclination value in real-time. Experimental results indicate that, compared with the unscented Kalman filter (UKF), LSTM-ATT, and CNN-LSTM algorithms, the Estimation-Focused-EKFNet algorithm enhances dynamic inclination recognition in complex road conditions by at least 52.34%, significantly improving recognition reliability. Its recognition accuracy reaches 99.28%, effectively ensuring the safety of unmanned driving for monorail cranes.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"25 25","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141815351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Moving object segmentation is fundamental for various downstream tasks in robotics and autonomous driving, providing crucial information for them. Effectively extracting spatial-temporal information from consecutive frames and addressing the scarcity of dataset is paramount for learning-based 3D LiDAR Moving Object Segmentation (LIDAR-MOS). In this work, we propose a novel deep neural network based on Vision Transformers (ViTs) to tackle this problem. We first validate the feasibility of Transformer networks for this task, offering an alternative to CNNs. Specifically, we utilize a dual-branch structure based on range-image data to extract spatial-temporal information from consecutive frames and fuse it using a motion-guided attention mechanism. Furthermore, we employ the ViT as the backbone, keeping its architecture unchanged from what is used for RGB images. This enables us to leverage pre-trained models from RGB images to improve results, addressing the issue of limited LIDAR point cloud data, which is cheaper compared to acquiring and annotating point cloud data. We validate the effectiveness of our approach on the LIDAR-MOS benchmark of SemanticKitti and achieve comparable results to methods that use CNNs on range image data. The source code and trained models are available at https://github.com/mafangniu/MOSViT.git.
{"title":"MosViT: Towards Vision Transformers for moving object segmentation based on Lidar point cloud","authors":"Chunyun Ma, Xiaojun Shi, Yingxin Wang, Shuai Song, Zhen Pan, Jiaxiang Hu","doi":"10.1088/1361-6501/ad6626","DOIUrl":"https://doi.org/10.1088/1361-6501/ad6626","url":null,"abstract":"\u0000 Moving object segmentation is fundamental for various downstream tasks in robotics and autonomous driving, providing crucial information for them. Effectively extracting spatial-temporal information from consecutive frames and addressing the scarcity of dataset is paramount for learning-based 3D LiDAR Moving Object Segmentation (LIDAR-MOS). In this work, we propose a novel deep neural network based on Vision Transformers (ViTs) to tackle this problem. We first validate the feasibility of Transformer networks for this task, offering an alternative to CNNs. Specifically, we utilize a dual-branch structure based on range-image data to extract spatial-temporal information from consecutive frames and fuse it using a motion-guided attention mechanism. Furthermore, we employ the ViT as the backbone, keeping its architecture unchanged from what is used for RGB images. This enables us to leverage pre-trained models from RGB images to improve results, addressing the issue of limited LIDAR point cloud data, which is cheaper compared to acquiring and annotating point cloud data. We validate the effectiveness of our approach on the LIDAR-MOS benchmark of SemanticKitti and achieve comparable results to methods that use CNNs on range image data. The source code and trained models are available at https://github.com/mafangniu/MOSViT.git.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"40 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141816889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-22DOI: 10.1088/1361-6501/ad6629
Qiongyao Wang, Kai Ping, Wenhua Xu, Jiarong Huang, Lingcao Tan
The phenomenon of liquid sloshing inside partially filled tank trucks adversely affects the stability of the tanktrucks. In order to mitigate the negative effects of liquid sloshing inside the tank, this study proposes several baffle configurations and investigates their anti-slosh effect on liquid sloshing. First, a numerical model of liquid sloshing is established. Then, the effectiveness of the numerical model is validated by comparing the results of free surface deformation, wall pressure, and sloshing frequency obtained from simulations and experiments under identical conditions. During the research process, it was found that the air pressure formed in locally sealed spaces within the tank also plays a positive role in suppressing liquid sloshing. The research results indicate that, under low fill volumes, baffles fixed at the bottom of the tank are more effective in suppressing liquid sloshing inside the tank, while under high fill volumes, baffles fixed at the top of the tank are more effective. Considering the tank’s airtightness, the air pressure formed in locally sealed spaces within the tank plays an important role in suppressing liquid sloshing when baffles are fixed at the top of the tank and the fill volume is high.
{"title":"Anti-slosh effect of baffle configurations and air pressure on liquid sloshing in partially filled tank trucks","authors":"Qiongyao Wang, Kai Ping, Wenhua Xu, Jiarong Huang, Lingcao Tan","doi":"10.1088/1361-6501/ad6629","DOIUrl":"https://doi.org/10.1088/1361-6501/ad6629","url":null,"abstract":"\u0000 The phenomenon of liquid sloshing inside partially filled tank trucks adversely affects the stability of the tanktrucks. In order to mitigate the negative effects of liquid sloshing inside the tank, this study proposes several baffle configurations and investigates their anti-slosh effect on liquid sloshing. First, a numerical model of liquid sloshing is established. Then, the effectiveness of the numerical model is validated by comparing the results of free surface deformation, wall pressure, and sloshing frequency obtained from simulations and experiments under identical conditions. During the research process, it was found that the air pressure formed in locally sealed spaces within the tank also plays a positive role in suppressing liquid sloshing. The research results indicate that, under low fill volumes, baffles fixed at the bottom of the tank are more effective in suppressing liquid sloshing inside the tank, while under high fill volumes, baffles fixed at the top of the tank are more effective. Considering the tank’s airtightness, the air pressure formed in locally sealed spaces within the tank plays an important role in suppressing liquid sloshing when baffles are fixed at the top of the tank and the fill volume is high.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"15 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141816940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-19DOI: 10.1088/1361-6501/ad6582
Xi Qiao, Kun Zhang, Xiangfeng Zhang, Long Zhang, Yonggang Xu
Rolling bearings are critical components in modern mechanical equipment, and the health monitoring and predictive maintenance of bearings are crucial for the normal operation of machinery. Hence, there is a compelling need to delve into advanced methodologies for enhancing the detection of fault characteristics in bearings. Faulty bearings produce periodic impulses during constant-speed rotation, which can typically be detected through envelope analysis. However, in some complex conditions, the relevant fault frequencies may be hidden within interfering components. This paper presents an amplitude modulation technique called the hyperbolic tangent Gaussian (HTG) transformation, designed to extract weak fault components from signals. Firstly, a family of amplitude modulation functions, known as the HTG functions, is constructed. These functions modulate signals with normalized amplitudes to obtain a series of modulated signals. Simultaneously, a frequency domain amplitude ratio (FDAR) metric is used for the automatic selection of the optimal components. Finally, the HTGgram is introduced, a spectral decomposition method based on trend components, aiming to identify the best combination of filtering and modulation components. Simulations with multi-component bearing fault signals and experimental signals with composite bearing faults demonstrate that this method not only highlights fault features and suppresses noise interference but also adaptively selects frequency bands related to faults, enhancing fault information. This approach exhibits excellent adaptability and effectiveness in complex operating conditions with multiple interference components.
{"title":"HTG transformation: an amplitude modulation method and its application in bearing fault diagnosis","authors":"Xi Qiao, Kun Zhang, Xiangfeng Zhang, Long Zhang, Yonggang Xu","doi":"10.1088/1361-6501/ad6582","DOIUrl":"https://doi.org/10.1088/1361-6501/ad6582","url":null,"abstract":"\u0000 Rolling bearings are critical components in modern mechanical equipment, and the health monitoring and predictive maintenance of bearings are crucial for the normal operation of machinery. Hence, there is a compelling need to delve into advanced methodologies for enhancing the detection of fault characteristics in bearings. Faulty bearings produce periodic impulses during constant-speed rotation, which can typically be detected through envelope analysis. However, in some complex conditions, the relevant fault frequencies may be hidden within interfering components. This paper presents an amplitude modulation technique called the hyperbolic tangent Gaussian (HTG) transformation, designed to extract weak fault components from signals. Firstly, a family of amplitude modulation functions, known as the HTG functions, is constructed. These functions modulate signals with normalized amplitudes to obtain a series of modulated signals. Simultaneously, a frequency domain amplitude ratio (FDAR) metric is used for the automatic selection of the optimal components. Finally, the HTGgram is introduced, a spectral decomposition method based on trend components, aiming to identify the best combination of filtering and modulation components. Simulations with multi-component bearing fault signals and experimental signals with composite bearing faults demonstrate that this method not only highlights fault features and suppresses noise interference but also adaptively selects frequency bands related to faults, enhancing fault information. This approach exhibits excellent adaptability and effectiveness in complex operating conditions with multiple interference components.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":" 679","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141823529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Strong noise interference can lead to failure of bearing fault diagnosis techniques. This paper proposes a two-step fault diagnosis strategy to address the challenge of weak fault feature extraction in bearing fault diagnosis using acoustic or vibration data at varying speed. Firstly, the paper introduces a short-time symplectic modal decomposition (stSGMD) method that utilizes fractional Fourier transform. This method involves signal processing with short-time windowing to extract fault-sensitive components. The window is then expanded to obtain the complete component through fractional Fourier narrow-band filtering based on energy concentration in the fractional Fourier domain. A novel entropy index, standard deviation discrete entropy, is introduced to quantify the intensity of fault shocks in non-stationary signal and is used to select components in the stSGMD. Subsequently, a fault feature extraction framework called global objective deconvolution (GOD) is presented for extracting instantaneous fault features at varying speed. This method establishes a global objective matrix for the extraction process. The GOD is utilized to deconvolute the complete fault-sensitive component, followed by envelope order analysis for demodulating the fault feature order. Numerical simulations and experimental studies on acoustics and vibration are performed. The results demonstrate that stSGMD improves the demodulation capability of SGMD, while GOD effectively extracts fault features. It is expected that the presented method will be effectively utilized for fault feature extractions in bearings operating under linear variable speed conditions.
强噪声干扰会导致轴承故障诊断技术失效。本文提出了一种两步故障诊断策略，以解决利用变速声学或振动数据进行轴承故障诊断中弱故障特征提取的难题。首先，本文介绍了一种利用分数傅里叶变换的短时交映模态分解（stSGMD）方法。该方法涉及信号处理，通过短时窗口提取故障敏感成分。然后，根据分数傅里叶域中的能量集中度，通过分数傅里叶窄带滤波扩展窗口以获得完整的分量。引入了一种新的熵指数--标准偏差离散熵，用于量化非稳态信号中故障冲击的强度，并用于选择 stSGMD 中的分量。随后，提出了一种名为全局目标解卷积（GOD）的故障特征提取框架，用于提取不同速度下的瞬时故障特征。这种方法为提取过程建立了一个全局目标矩阵。利用 GOD 对完整的故障敏感元件进行解旋，然后通过包络阶次分析解调故障特征阶次。对声学和振动进行了数值模拟和实验研究。结果表明，stSGMD 提高了 SGMD 的解调能力，而 GOD 则有效地提取了故障特征。预计所提出的方法将有效地用于线性变速条件下轴承的故障特征提取。
{"title":"A Two-step Bearing Fault Diagnosis Strategy under Variable Speed based on Symplectic Geometry Modal Decomposition and Practical Fault Feature Extraction Framework","authors":"Shuai Huang, Junxia Li, Yandong Wang, Zhixiang Qin","doi":"10.1088/1361-6501/ad6583","DOIUrl":"https://doi.org/10.1088/1361-6501/ad6583","url":null,"abstract":"\u0000 Strong noise interference can lead to failure of bearing fault diagnosis techniques. This paper proposes a two-step fault diagnosis strategy to address the challenge of weak fault feature extraction in bearing fault diagnosis using acoustic or vibration data at varying speed. Firstly, the paper introduces a short-time symplectic modal decomposition (stSGMD) method that utilizes fractional Fourier transform. This method involves signal processing with short-time windowing to extract fault-sensitive components. The window is then expanded to obtain the complete component through fractional Fourier narrow-band filtering based on energy concentration in the fractional Fourier domain. A novel entropy index, standard deviation discrete entropy, is introduced to quantify the intensity of fault shocks in non-stationary signal and is used to select components in the stSGMD. Subsequently, a fault feature extraction framework called global objective deconvolution (GOD) is presented for extracting instantaneous fault features at varying speed. This method establishes a global objective matrix for the extraction process. The GOD is utilized to deconvolute the complete fault-sensitive component, followed by envelope order analysis for demodulating the fault feature order. Numerical simulations and experimental studies on acoustics and vibration are performed. The results demonstrate that stSGMD improves the demodulation capability of SGMD, while GOD effectively extracts fault features. It is expected that the presented method will be effectively utilized for fault feature extractions in bearings operating under linear variable speed conditions.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"102 24","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141821593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-18DOI: 10.1088/1361-6501/ad64f5
Xiaozhuo Xu, xiquan chen, Yunji Zhao
As one of the important equipment of motor transmission, bearings play an important role in the production and manufacturing industry, if there are problems in the manufacturing process will bring significant economic losses or even endanger personal safety, so its state prediction and fault diagnosis is of great significance. In bearing fault diagnosis, it is a challenge to eliminate the effect of data imbalance on fault diagnosis. GAN networks have achieved some success in data imbalance fault diagnosis, but GAN networks suffer from sample generation bias when balancing samples. To solve this problem, fusion attention mechanism and global feature cross GAN networks (FA-GFCGANs) is proposed. Firstly, the spatial channel fusion attention mechanism is added to the generator, so that the generator selectively amplifies and processes sample features from different regions, which helps the generator learn more representative features from a few categories; secondly, the global feature cross module is added to the discriminator, so that the discriminator efficiently extracts features from different samples, and improves its ability of recognizing the sample discrepancy; at the same time, in order to improve the model's anti-noise ability, an anti-noise module is added to the discriminator to improve the efficiency of the model's data imbalance fault diagnosis; finally, this paper's method is validated by using two public bearing datasets and one self-constructed dataset. The experimental results prove that this method can effectively overcome the effect of data imbalance on GAN networks, and has a high accuracy rate in real industrial fault diagnosis tasks, what’s more, it proves that the method in this paper has a very good anti-noise performance and practical application value.
轴承作为电机传动的重要设备之一，在生产制造业中发挥着重要作用，如果在生产过程中出现问题，将带来重大经济损失甚至危及人身安全，因此其状态预测和故障诊断意义重大。在轴承故障诊断中，如何消除数据不平衡对故障诊断的影响是一个难题。GAN 网络在数据不平衡故障诊断中取得了一定的成功，但 GAN 网络在平衡样本时存在样本生成偏差。为解决这一问题，提出了融合关注机制和全局特征交叉 GAN 网络（FA-GFCGANs）。首先，在生成器中加入空间通道融合注意机制，使生成器有选择地放大和处理来自不同区域的样本特征，从而帮助生成器从少数几个类别中学习到更具代表性的特征；其次，在判别器中加入全局特征交叉模块，使判别器有效地从不同样本中提取特征，提高其识别样本差异的能力；同时，为了提高模型的抗噪声能力，在判别器中加入了抗噪声模块，以提高模型对数据不平衡故障诊断的效率；最后，本文的方法通过两个公共轴承数据集和一个自建数据集进行了验证。实验结果证明，该方法能有效克服数据不平衡对 GAN 网络的影响，在实际工业故障诊断任务中具有较高的准确率，同时也证明了本文方法具有很好的抗噪性能和实际应用价值。
{"title":"Data Imbalance Bearing Fault Diagnosis Based on Fusion Attention Mechanism and Global Feature Cross GAN Network","authors":"Xiaozhuo Xu, xiquan chen, Yunji Zhao","doi":"10.1088/1361-6501/ad64f5","DOIUrl":"https://doi.org/10.1088/1361-6501/ad64f5","url":null,"abstract":"\u0000 As one of the important equipment of motor transmission, bearings play an important role in the production and manufacturing industry, if there are problems in the manufacturing process will bring significant economic losses or even endanger personal safety, so its state prediction and fault diagnosis is of great significance. In bearing fault diagnosis, it is a challenge to eliminate the effect of data imbalance on fault diagnosis. GAN networks have achieved some success in data imbalance fault diagnosis, but GAN networks suffer from sample generation bias when balancing samples. To solve this problem, fusion attention mechanism and global feature cross GAN networks (FA-GFCGANs) is proposed. Firstly, the spatial channel fusion attention mechanism is added to the generator, so that the generator selectively amplifies and processes sample features from different regions, which helps the generator learn more representative features from a few categories; secondly, the global feature cross module is added to the discriminator, so that the discriminator efficiently extracts features from different samples, and improves its ability of recognizing the sample discrepancy; at the same time, in order to improve the model's anti-noise ability, an anti-noise module is added to the discriminator to improve the efficiency of the model's data imbalance fault diagnosis; finally, this paper's method is validated by using two public bearing datasets and one self-constructed dataset. The experimental results prove that this method can effectively overcome the effect of data imbalance on GAN networks, and has a high accuracy rate in real industrial fault diagnosis tasks, what’s more, it proves that the method in this paper has a very good anti-noise performance and practical application value.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":" 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141825848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-18DOI: 10.1088/1361-6501/ad64f8
Xiang Lu, Zenghao Liu, Yucan Shen, Fan Zhang, Ning Ma, Haifei Hao, Zhen Liang
The rigid guide is a crucial component of the mine hoisting system, which plays a role in guiding the smooth operation of the hoisting container in the process of mine hoisting. To address the issue of detection devices mounted on mobile equipment affecting normal production, this paper proposes to install the device inside the groove of the rigid guide, and directly collect the vibration signal of the rigid guide while the mine hoisting system is in operation. The collected vibration signals are preprocessed and subjected to Fast Fourier Transform (FFT). To fully extract the fault information hidden in the spectrogram, the vibration signals are transformed into a two-dimensional spectrogram in polar coordinates and used as a sample dataset for training a Convolutional Neural Network (CNN) to achieve fault classification and identification of the rigid guide. Experimental studies on this method show that the accuracy of CNN in identifying rigid guide fault categories reaches 92.63%. Compared to the method of collecting vibration signals from mobile devices, the fault identification accuracy also exceeds 90%. By analyzing the vibration signals of the rigid guide, it is possible to determine whether there is a fault.
{"title":"Research on fault diagnosis of rigid guide in hoist system based on vibration signal classification","authors":"Xiang Lu, Zenghao Liu, Yucan Shen, Fan Zhang, Ning Ma, Haifei Hao, Zhen Liang","doi":"10.1088/1361-6501/ad64f8","DOIUrl":"https://doi.org/10.1088/1361-6501/ad64f8","url":null,"abstract":"\u0000 The rigid guide is a crucial component of the mine hoisting system, which plays a role in guiding the smooth operation of the hoisting container in the process of mine hoisting. To address the issue of detection devices mounted on mobile equipment affecting normal production, this paper proposes to install the device inside the groove of the rigid guide, and directly collect the vibration signal of the rigid guide while the mine hoisting system is in operation. The collected vibration signals are preprocessed and subjected to Fast Fourier Transform (FFT). To fully extract the fault information hidden in the spectrogram, the vibration signals are transformed into a two-dimensional spectrogram in polar coordinates and used as a sample dataset for training a Convolutional Neural Network (CNN) to achieve fault classification and identification of the rigid guide. Experimental studies on this method show that the accuracy of CNN in identifying rigid guide fault categories reaches 92.63%. Compared to the method of collecting vibration signals from mobile devices, the fault identification accuracy also exceeds 90%. By analyzing the vibration signals of the rigid guide, it is possible to determine whether there is a fault.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":" 28","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141826942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The characteristic constant is commonly used to reconstruct the measured signal when a measurement chain with flat wideband frequency response is applied. The characteristic constant is often calibrated by a standard pulse that follows a rectangular pulse behavior. However, a pulse that more ‘similar’ with the measured signal is more suitable theoretically than a rectangular pulse as the calibration waveform. To reduce the measurement error caused by the calibration waveform, a novel method to optimize the calibration waveform is proposed in this paper. A dataset is constructed based on the prior information of the signal to be measured. Criterion for better calibration waveform is also discussed. Dataset construction along with the criterion makes the calibration waveform optimization a solvable mathematical problem. Then the calibration waveform is specified based on the prior information about the measured signal and the measurement chaincan be quantitively evaluation and optimized. The optimized calibration waveform will made the error caused by the fluctuations in frequency response of a proportional sensor as small as possible statistically. As an actual application case, simulation results are also provided for the intuitively explanation of the method. Then the procedure to obtain the characteristic constant based on the optimized calibration waveform is outlined. A calibration system for the given application case is built. At last, an experiment is designed and executed. The experimental results approved the method proposed in this paper well.
{"title":"A Novel Method to Obtain the Characteristic Constant of a Measurement Chain","authors":"Jing Yang, Zhitong Cui, Fei Cao, Zhizhen Zhu, Yayun Dong, Mengtong Qiu","doi":"10.1088/1361-6501/ad64f6","DOIUrl":"https://doi.org/10.1088/1361-6501/ad64f6","url":null,"abstract":"\u0000 The characteristic constant is commonly used to reconstruct the measured signal when a measurement chain with flat wideband frequency response is applied. The characteristic constant is often calibrated by a standard pulse that follows a rectangular pulse behavior. However, a pulse that more ‘similar’ with the measured signal is more suitable theoretically than a rectangular pulse as the calibration waveform. To reduce the measurement error caused by the calibration waveform, a novel method to optimize the calibration waveform is proposed in this paper. A dataset is constructed based on the prior information of the signal to be measured. Criterion for better calibration waveform is also discussed. Dataset construction along with the criterion makes the calibration waveform optimization a solvable mathematical problem. Then the calibration waveform is specified based on the prior information about the measured signal and the measurement chaincan be quantitively evaluation and optimized. The optimized calibration waveform will made the error caused by the fluctuations in frequency response of a proportional sensor as small as possible statistically. As an actual application case, simulation results are also provided for the intuitively explanation of the method. Then the procedure to obtain the characteristic constant based on the optimized calibration waveform is outlined. A calibration system for the given application case is built. At last, an experiment is designed and executed. The experimental results approved the method proposed in this paper well.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":" 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141827381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：