Pub Date : 2024-10-30DOI: 10.1109/TIM.2024.3488152
Qingquan Xu;Jie Dong;Kaixiang Peng;Qichun Zhang
In the process industry production, the online sensing of process performance is very important for the optimization and control of the manufacturing process. However, the information island is formed by long processes and multiple systems of complex production processes. The process data are characterized by high dimensional heterogeneity, nonlinearity, and strong coupling, and the offline assay of process performance is characterized by high discretization and irregular sampling period. In order to solve the above problems, a cloud-edge collaborative soft sensing framework for multiperformance indicators prediction of manufacturing processes with nonregular sampling is proposed. Also, some experiments are carried out with the actual hot strip rolling process, which realizes the joint real-time sensing of the three performance indicators of yield strength (YS), tensile strength (TS), and elongation (EL) with good accuracy.
{"title":"A Cloud-Edge Collaborative Soft Sensing Framework for Multiperformance Indicators of Manufacturing Processes With Irregular Sampling","authors":"Qingquan Xu;Jie Dong;Kaixiang Peng;Qichun Zhang","doi":"10.1109/TIM.2024.3488152","DOIUrl":"https://doi.org/10.1109/TIM.2024.3488152","url":null,"abstract":"In the process industry production, the online sensing of process performance is very important for the optimization and control of the manufacturing process. However, the information island is formed by long processes and multiple systems of complex production processes. The process data are characterized by high dimensional heterogeneity, nonlinearity, and strong coupling, and the offline assay of process performance is characterized by high discretization and irregular sampling period. In order to solve the above problems, a cloud-edge collaborative soft sensing framework for multiperformance indicators prediction of manufacturing processes with nonregular sampling is proposed. Also, some experiments are carried out with the actual hot strip rolling process, which realizes the joint real-time sensing of the three performance indicators of yield strength (YS), tensile strength (TS), and elongation (EL) with good accuracy.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-10"},"PeriodicalIF":5.6,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1109/TIM.2024.3488136
Xiaohua Huang;Jiahao Zhu;Ying Huo
In the manufacturing process of hot-rolled steel strips, various mechanical forces, and environmental conditions can cause surface defects, making their detection crucial for ensuring high-quality product production and preventing significant economic losses in the industry. However, existing models within the you only look once (YOLO) family, commonly employed for steel surface defect detection, have exhibited limited effectiveness. In this article, we propose an improved version of YOLO, namely, YOLO enhanced by a convolution squeeze-and-excitation (CSE) module, Conv2d-BatchNorm-SiLU (CBS) with Swin transformer (CST) module, and adaptive spatial feature fusion (ASFF) detection head module, i.e., SSA-YOLO, specifically tailored for end-to-end surface defect detection. Our approach incorporates several key modifications aimed at improving performance. First, we integrate a channel attention mechanism module into the shallow convolutional network module of the backbone. This enhancement focuses on channel information to improve feature extraction related to small defects while reducing redundant information in candidate boxes. In addition, we fuse a Swin transformer (Swin-T) module into the neck to enhance feature representation for detecting diverse and multiscale defects. Finally, the ASFF is introduced in YOLO to increase cross-interaction between high and low levels in the feature pyramid network (FPN). Experimental results demonstrate the superior performance and effectiveness of our SSA-YOLO model compared to other state-of-the-art models. Our approach achieves higher accuracy and sensitivity in detecting surface defects, offering significant advancements in steel strip production quality control. The code is available at https://github.com/MIPIT-Team/SSA-YOLO .
{"title":"SSA-YOLO: An Improved YOLO for Hot-Rolled Strip Steel Surface Defect Detection","authors":"Xiaohua Huang;Jiahao Zhu;Ying Huo","doi":"10.1109/TIM.2024.3488136","DOIUrl":"https://doi.org/10.1109/TIM.2024.3488136","url":null,"abstract":"In the manufacturing process of hot-rolled steel strips, various mechanical forces, and environmental conditions can cause surface defects, making their detection crucial for ensuring high-quality product production and preventing significant economic losses in the industry. However, existing models within the you only look once (YOLO) family, commonly employed for steel surface defect detection, have exhibited limited effectiveness. In this article, we propose an improved version of YOLO, namely, YOLO enhanced by a convolution squeeze-and-excitation (CSE) module, Conv2d-BatchNorm-SiLU (CBS) with Swin transformer (CST) module, and adaptive spatial feature fusion (ASFF) detection head module, i.e., SSA-YOLO, specifically tailored for end-to-end surface defect detection. Our approach incorporates several key modifications aimed at improving performance. First, we integrate a channel attention mechanism module into the shallow convolutional network module of the backbone. This enhancement focuses on channel information to improve feature extraction related to small defects while reducing redundant information in candidate boxes. In addition, we fuse a Swin transformer (Swin-T) module into the neck to enhance feature representation for detecting diverse and multiscale defects. Finally, the ASFF is introduced in YOLO to increase cross-interaction between high and low levels in the feature pyramid network (FPN). Experimental results demonstrate the superior performance and effectiveness of our SSA-YOLO model compared to other state-of-the-art models. Our approach achieves higher accuracy and sensitivity in detecting surface defects, offering significant advancements in steel strip production quality control. The code is available at \u0000<uri>https://github.com/MIPIT-Team/SSA-YOLO</uri>\u0000.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-17"},"PeriodicalIF":5.6,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this study, we present a novel relaxed-intensified exploration algorithm (RIEA) to synthesize large-aperture sensor arrays producing good array sparsity and optimal weight vector of the sparse sensor arrays for sensing unmanned aerial vehicles (UAVs) in airspace. The proposed algorithm is based on the compressed-sensing framework integrated with a kind of relaxed-intensified optimization thought, which comprises two core stages: the relaxed optimization stage and the intensified reoptimization stage. The relaxed-intensified exploration algorithm (RIEA) is tailored to accelerate array synthesis efficiency and promote global optimization. For the proposed algorithm, the ability to approach the global convergence is embodied in two key stages. The first stage aims to generate an optimal sparse sensor array with arbitrary upper mask constraints, whose upper mask is slightly relaxed to expand the solution space for further enhancing the array sparsity. Meanwhile, direction dimension reduction is further conducted to relax the radiating direction matrix for reducing massive computational cost. For the intensified reoptimization stage, the “relaxed” upper mask is first readjusted back to the strictly constrained strength and the weight vector of the designed sparse sensor array in the previous stage is then further optimized to approach the global optimal solution. Finally, the presence of element pattern for an individual sensor and array beam-scanning capability are also considered and investigated in synthesizing the sparse sensor arrays for precise positioning and sensing of UAVs. Several representative examples of the small/large-aperture sparse sensor arrays are performed to demonstrate the superiority, effectiveness, and robustness of the proposed RIEA.
{"title":"Synthesis of Large Sparse Sensor Arrays Utilizing Relaxed-Intensified Exploration Algorithm (RIEA) for Optimal UAVs Beamforming","authors":"Zhigang Zhou;Cao Zeng;Lan Lan;Guisheng Liao;Shengqi Zhu;Baixiao Chen","doi":"10.1109/TIM.2024.3488133","DOIUrl":"https://doi.org/10.1109/TIM.2024.3488133","url":null,"abstract":"In this study, we present a novel relaxed-intensified exploration algorithm (RIEA) to synthesize large-aperture sensor arrays producing good array sparsity and optimal weight vector of the sparse sensor arrays for sensing unmanned aerial vehicles (UAVs) in airspace. The proposed algorithm is based on the compressed-sensing framework integrated with a kind of relaxed-intensified optimization thought, which comprises two core stages: the relaxed optimization stage and the intensified reoptimization stage. The relaxed-intensified exploration algorithm (RIEA) is tailored to accelerate array synthesis efficiency and promote global optimization. For the proposed algorithm, the ability to approach the global convergence is embodied in two key stages. The first stage aims to generate an optimal sparse sensor array with arbitrary upper mask constraints, whose upper mask is slightly relaxed to expand the solution space for further enhancing the array sparsity. Meanwhile, direction dimension reduction is further conducted to relax the radiating direction matrix for reducing massive computational cost. For the intensified reoptimization stage, the “relaxed” upper mask is first readjusted back to the strictly constrained strength and the weight vector of the designed sparse sensor array in the previous stage is then further optimized to approach the global optimal solution. Finally, the presence of element pattern for an individual sensor and array beam-scanning capability are also considered and investigated in synthesizing the sparse sensor arrays for precise positioning and sensing of UAVs. Several representative examples of the small/large-aperture sparse sensor arrays are performed to demonstrate the superiority, effectiveness, and robustness of the proposed RIEA.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-15"},"PeriodicalIF":5.6,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1109/TIM.2024.3488140
Huang-Chen Lee;Soun-Cheng Wang;Zih-Hua Lin
A runner’s duty factor (DF) is defined as the ratio of ground contact time (GCT) to stride time. Fast runners tend to have short GCTs as well as a small DF. In the current method of DF measurement, the runner needs to run on a treadmill and use a high-speed motion capture camera for video recording to examine manually when the runner’s foot touches and leaves the ground. This method is labor costly, slow, and inefficient. To ease the DF measurement, we proposed a novel method by designing a special wearable sensor system, the Tag, can collect the acceleration of runners and compute DFs automatically. The Tag can be installed on the head, waist, or ankle to obtain the acceleration of runners for DF calculation. However, different runners will generate significantly varying characteristics of acceleration as their body shapes and running habits may not be similar. Therefore, a machine-learning algorithm was introduced to overcome this issue. The proposed system was evaluated on 27 runners with different running professions, genders, heights, and weights. Results indicate that by using acceleration data measured from the runner’s head and training data based on the runner’s profession category, the proposed design can accurately measure the DF, with a mean absolute error (MAE) of 5%. To facilitate the development of this domain, this study features the first open-source wearable sensor design for this application. New sensing components and data processing algorithms may be introduced to enhance the performance and open additional possibilities to apply this technology in this area.
{"title":"An Open-Source Wearable Sensor System for Measuring the Duty Factor of Runners","authors":"Huang-Chen Lee;Soun-Cheng Wang;Zih-Hua Lin","doi":"10.1109/TIM.2024.3488140","DOIUrl":"https://doi.org/10.1109/TIM.2024.3488140","url":null,"abstract":"A runner’s duty factor (DF) is defined as the ratio of ground contact time (GCT) to stride time. Fast runners tend to have short GCTs as well as a small DF. In the current method of DF measurement, the runner needs to run on a treadmill and use a high-speed motion capture camera for video recording to examine manually when the runner’s foot touches and leaves the ground. This method is labor costly, slow, and inefficient. To ease the DF measurement, we proposed a novel method by designing a special wearable sensor system, the Tag, can collect the acceleration of runners and compute DFs automatically. The Tag can be installed on the head, waist, or ankle to obtain the acceleration of runners for DF calculation. However, different runners will generate significantly varying characteristics of acceleration as their body shapes and running habits may not be similar. Therefore, a machine-learning algorithm was introduced to overcome this issue. The proposed system was evaluated on 27 runners with different running professions, genders, heights, and weights. Results indicate that by using acceleration data measured from the runner’s head and training data based on the runner’s profession category, the proposed design can accurately measure the DF, with a mean absolute error (MAE) of 5%. To facilitate the development of this domain, this study features the first open-source wearable sensor design for this application. New sensing components and data processing algorithms may be introduced to enhance the performance and open additional possibilities to apply this technology in this area.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-10"},"PeriodicalIF":5.6,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1109/TIM.2024.3488135
Yong-Un Jeong;Joo-Hyung Chae
To achieve a high input and output (I/O) bandwidth, memory interfaces adopt a parallel I/O structure, in which the offset caused by systemic and random mismatches can limit the I/O bandwidth; thus, offset measurement and correction are required. A receiver with a loop-unrolled decision feedback equalizer (DFE) can have a per-DFE offset between two loop-unrolled data paths, degrading the overall performance. We propose an offset calibration method that can identify and adjust the per-DFE offset, thereby correcting each input-referred offset between multiple lanes. We implemented a prototype that has a two-lane receiver adopting a one-tap weighted-VREF-based DFE in a 28-nm CMOS process. Its energy efficiency and area are 0.21 pJ/bit/lane and 0.004 mm2/lane, respectively. Through the offset calibration with the DFE, a bit error rate (BER) of 10-12 and an improved eye shmoo were achieved at 12 Gb/s in a total of six data lanes in three chips.
{"title":"Per-DFE Offset Measurement and Cancellation of Weighted-VREF-Based Loop-Unrolled DFE for Memory Interfaces","authors":"Yong-Un Jeong;Joo-Hyung Chae","doi":"10.1109/TIM.2024.3488135","DOIUrl":"https://doi.org/10.1109/TIM.2024.3488135","url":null,"abstract":"To achieve a high input and output (I/O) bandwidth, memory interfaces adopt a parallel I/O structure, in which the offset caused by systemic and random mismatches can limit the I/O bandwidth; thus, offset measurement and correction are required. A receiver with a loop-unrolled decision feedback equalizer (DFE) can have a per-DFE offset between two loop-unrolled data paths, degrading the overall performance. We propose an offset calibration method that can identify and adjust the per-DFE offset, thereby correcting each input-referred offset between multiple lanes. We implemented a prototype that has a two-lane receiver adopting a one-tap weighted-VREF-based DFE in a 28-nm CMOS process. Its energy efficiency and area are 0.21 pJ/bit/lane and 0.004 mm2/lane, respectively. Through the offset calibration with the DFE, a bit error rate (BER) of 10-12 and an improved eye shmoo were achieved at 12 Gb/s in a total of six data lanes in three chips.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-8"},"PeriodicalIF":5.6,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1109/TIM.2024.3488156
Feng Zhu;Xi Chen;Qinqing Cai;Xiaohong Zhang
High-precision continuous position and attitude determination are the critical modules of mobile mapping and autonomous driving (AD). Research in the integration of Global Navigation Satellite System (GNSS) and strapdown inertial navigation system (SINS) has greatly enhanced the accuracy and robustness of position and attitude in different scenes. However, the complexity and variability of the real scenes are still challenging for the existing models, parameters, strategies, and algorithms (MPSA). It is worth noting that high-quality datasets are key to accelerating the research and development of MPSA, which has been proved in the computer vision (CV) fields represented by the ImageNet dataset. Unfortunately, current public datasets either do not provide the raw observations of GNSS and inertial measurement unit (IMUs) or are not collected in abundant scenes and moving platforms. Therefore, a large-scale diverse GNSS/SINS dataset, named SmartPNT-POS, is presented. This dataset covers rich real-world environments, such as open-sky and complex urban, and multiple moving platforms, such as aircraft, land vehicles, and ships. In addition, different types of IMUs, including those manufactured in Hexagon, iMAR Navigation GmbH, and Honeywell, are contained in SmartPNT-POS as well. Moreover, it provides ground truths in each group of data for users to analyze and evaluate their MPSA. Now, the dataset is publicly available through Kaggle, a data science community, and the website to obtain the dataset is provided in the text. There have been 30 sets of data published on the website up to the present, and comprehensive analyses have been made in this contribution for the position and attitude determination results obtained by different processing modes. More data will be collected for different environments and applications and published on the same website in the future.
{"title":"A Large-Scale Diverse GNSS/SINS Dataset: Construction, Publication, and Application","authors":"Feng Zhu;Xi Chen;Qinqing Cai;Xiaohong Zhang","doi":"10.1109/TIM.2024.3488156","DOIUrl":"https://doi.org/10.1109/TIM.2024.3488156","url":null,"abstract":"High-precision continuous position and attitude determination are the critical modules of mobile mapping and autonomous driving (AD). Research in the integration of Global Navigation Satellite System (GNSS) and strapdown inertial navigation system (SINS) has greatly enhanced the accuracy and robustness of position and attitude in different scenes. However, the complexity and variability of the real scenes are still challenging for the existing models, parameters, strategies, and algorithms (MPSA). It is worth noting that high-quality datasets are key to accelerating the research and development of MPSA, which has been proved in the computer vision (CV) fields represented by the ImageNet dataset. Unfortunately, current public datasets either do not provide the raw observations of GNSS and inertial measurement unit (IMUs) or are not collected in abundant scenes and moving platforms. Therefore, a large-scale diverse GNSS/SINS dataset, named SmartPNT-POS, is presented. This dataset covers rich real-world environments, such as open-sky and complex urban, and multiple moving platforms, such as aircraft, land vehicles, and ships. In addition, different types of IMUs, including those manufactured in Hexagon, iMAR Navigation GmbH, and Honeywell, are contained in SmartPNT-POS as well. Moreover, it provides ground truths in each group of data for users to analyze and evaluate their MPSA. Now, the dataset is publicly available through Kaggle, a data science community, and the website to obtain the dataset is provided in the text. There have been 30 sets of data published on the website up to the present, and comprehensive analyses have been made in this contribution for the position and attitude determination results obtained by different processing modes. More data will be collected for different environments and applications and published on the same website in the future.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-13"},"PeriodicalIF":5.6,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-29DOI: 10.1109/TIM.2024.3485429
Zeyu Gu;Gang Tang;Jianwei Ma
The mechanical and electrical performance degradation of satellite components has a serious impact on imaging. How to perform high-precision reconstruction of the monitor data from compressive-sensing (CS) data (limited by online computing, storage and transmission) is often the first stage in the fault diagnosis of in-orbit satellites. In this article, a deep generative model named denoising diffusion probabilistic model (DDPM) is applied for the equipment monitor data reconstruction. The priors-assisted reconstruction method is useful for reducing reconstruction error and decreasing measurement/monitor cost. The reconstruction method mainly consists of unconditional generation transition from pre-trained DDPM noise matching network and conditional likelihood correction step toward downsampling data. An inverse time decay technique is embedded into step size strategy of gradient computation to ensure data consistency. As an unsupervised learning paradigm, the learned deep generative priors can be utilized for measurements with different compressive sampling ratio (CSR) like plug-and-play prior. Numerical experiments executed on control moment gyro (CMG) data and reciprocating refrigeration compressor (RRC) data validate the effectiveness of the new method, in comparison with conventional sparse prior methods and advanced deep learning reconstruction methods. Finally, we conduct out-of-distribution (OOD) generalization experiments on fault working condition, which demonstrates the DDPM priors-assisted data reconstruction method are suitable for different operating conditions.
{"title":"Compressive-Sensing Reconstruction for Satellite Monitor Data Using a Deep Generative Model","authors":"Zeyu Gu;Gang Tang;Jianwei Ma","doi":"10.1109/TIM.2024.3485429","DOIUrl":"https://doi.org/10.1109/TIM.2024.3485429","url":null,"abstract":"The mechanical and electrical performance degradation of satellite components has a serious impact on imaging. How to perform high-precision reconstruction of the monitor data from compressive-sensing (CS) data (limited by online computing, storage and transmission) is often the first stage in the fault diagnosis of in-orbit satellites. In this article, a deep generative model named denoising diffusion probabilistic model (DDPM) is applied for the equipment monitor data reconstruction. The priors-assisted reconstruction method is useful for reducing reconstruction error and decreasing measurement/monitor cost. The reconstruction method mainly consists of unconditional generation transition from pre-trained DDPM noise matching network and conditional likelihood correction step toward downsampling data. An inverse time decay technique is embedded into step size strategy of gradient computation to ensure data consistency. As an unsupervised learning paradigm, the learned deep generative priors can be utilized for measurements with different compressive sampling ratio (CSR) like plug-and-play prior. Numerical experiments executed on control moment gyro (CMG) data and reciprocating refrigeration compressor (RRC) data validate the effectiveness of the new method, in comparison with conventional sparse prior methods and advanced deep learning reconstruction methods. Finally, we conduct out-of-distribution (OOD) generalization experiments on fault working condition, which demonstrates the DDPM priors-assisted data reconstruction method are suitable for different operating conditions.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-15"},"PeriodicalIF":5.6,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142598620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-29DOI: 10.1109/TIM.2024.3485392
Ze-Qi Ding;Qiang Qin;Yi-Fan Zhang;Yan-Hui Lin
In prognostic and health management (PHM), predicting remaining useful life (RUL) and quantifying the uncertainties in predictions are necessary. This article proposes a Gaussian process (GP) autoregression-variational autoencoder (GPVAE) framework that can predict RUL based on degradation data, quantify predictive uncertainty, decompose this uncertainty into epistemic and aleatory types, and further quantify epistemic uncertainties on RUL-related features. Subsequently, uncertainty calibration is proposed to ensure that the quantified uncertainty matches the actual error of the model. The calibrated uncertainty is used for out-of-distribution (OOD) detection and active learning for the labeled and unlabeled data, which can improve the RUL prediction accuracy with limited computational resources and limited cost of degradation tests for obtaining RUL labels. The effectiveness of the proposed method is illustrated by the case study on lithium-ion batteries dataset.
{"title":"An Uncertainty Quantification and Calibration Framework for RUL Prediction and Accuracy Improvement","authors":"Ze-Qi Ding;Qiang Qin;Yi-Fan Zhang;Yan-Hui Lin","doi":"10.1109/TIM.2024.3485392","DOIUrl":"https://doi.org/10.1109/TIM.2024.3485392","url":null,"abstract":"In prognostic and health management (PHM), predicting remaining useful life (RUL) and quantifying the uncertainties in predictions are necessary. This article proposes a Gaussian process (GP) autoregression-variational autoencoder (GPVAE) framework that can predict RUL based on degradation data, quantify predictive uncertainty, decompose this uncertainty into epistemic and aleatory types, and further quantify epistemic uncertainties on RUL-related features. Subsequently, uncertainty calibration is proposed to ensure that the quantified uncertainty matches the actual error of the model. The calibrated uncertainty is used for out-of-distribution (OOD) detection and active learning for the labeled and unlabeled data, which can improve the RUL prediction accuracy with limited computational resources and limited cost of degradation tests for obtaining RUL labels. The effectiveness of the proposed method is illustrated by the case study on lithium-ion batteries dataset.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-13"},"PeriodicalIF":5.6,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142598636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article presents an ultrasonic gas meter based on a scandium-doped aluminum nitride (Sc0.2Al0.8N) piezoelectric micromachined ultrasonic transducer (PMUT) array, where the characteristic dimension of each PMUT cell is only $600~mu text {m}$ . The ultrasonic time-of-flight (TOF) difference method is employed to measure the gas flow rate, followed by ultrasonic signal processing and subsequent velocity profile and temperature compensation performed by the microcontroller. The cross correlation method is employed to detect the ultrasonic TOF difference and further suppress noise. To conduct a feasibility evaluation of the designed ultrasonic gas meter, the PMUT array, system control circuit, and ultrasonic flow channel are combined and encapsulated in a meter case. Results indicate that the ultrasonic gas meter exhibits outstanding accuracy, repeatability, and temperature adaptability. In the flow range of 0.025–2.8 m3/h, the minimum mean error and minimum repeatability error are 0.11% and 0.13%, respectively. Even when the temperature reaches 323.15 K, the designed device can achieve a mean error of no more than 0.41% with temperature compensation, which is comparable to commercialized ultrasonic gas meters. The highly reliable ultrasonic gas meter presented in this article will provide a feasible solution for advancing portable devices.
{"title":"A High-Accuracy Ultrasonic Gas Flowmeter Based on Scandium-Doped Aluminum Nitride Piezoelectric Micromachined Ultrasonic Transducers","authors":"Hanzhe Liu;Xiangyang Wang;Chongbin Liu;Yuzhe Lin;Lujiang Zhang;Hui Zhao;Xiaofei Cui;Jianke Feng;Guoqiang Wu;Jifang Tao","doi":"10.1109/TIM.2024.3481593","DOIUrl":"https://doi.org/10.1109/TIM.2024.3481593","url":null,"abstract":"This article presents an ultrasonic gas meter based on a scandium-doped aluminum nitride (Sc0.2Al0.8N) piezoelectric micromachined ultrasonic transducer (PMUT) array, where the characteristic dimension of each PMUT cell is only \u0000<inline-formula> <tex-math>$600~mu text {m}$ </tex-math></inline-formula>\u0000. The ultrasonic time-of-flight (TOF) difference method is employed to measure the gas flow rate, followed by ultrasonic signal processing and subsequent velocity profile and temperature compensation performed by the microcontroller. The cross correlation method is employed to detect the ultrasonic TOF difference and further suppress noise. To conduct a feasibility evaluation of the designed ultrasonic gas meter, the PMUT array, system control circuit, and ultrasonic flow channel are combined and encapsulated in a meter case. Results indicate that the ultrasonic gas meter exhibits outstanding accuracy, repeatability, and temperature adaptability. In the flow range of 0.025–2.8 m3/h, the minimum mean error and minimum repeatability error are 0.11% and 0.13%, respectively. Even when the temperature reaches 323.15 K, the designed device can achieve a mean error of no more than 0.41% with temperature compensation, which is comparable to commercialized ultrasonic gas meters. The highly reliable ultrasonic gas meter presented in this article will provide a feasible solution for advancing portable devices.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-10"},"PeriodicalIF":5.6,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-28DOI: 10.1109/TIM.2024.3485395
Jun Zhu;Liwei Jiang;Jiali Liu;Xin Zhao;Chi Fang;Qi Shao;Yuntian Zou;Zhuo Wang
The atomic magnetometers operated in Earth-scale magnetic field are susceptible to the nonlinear Zeeman (NLZ) effect, resulting in multiple resonance peaks and heading error, which restricts their practical applications. We introduce a spin-locking method based on magnetic field modulation to overcome the NLZ effect and thus suppress the heading error in atomic magnetometers. The suppression effect of spin-locking is proportional to the amplitude of the modulation field. However, an excessively high modulation field amplitude can lead to broadening of the measurement linewidth. A novel model characterizing the linewidth for the amplitude of modulated magnetic field under different environmental magnetic field is established by considering the NLZ effect. From the test results, the novel model can more accurately predict the linewidth under different environmental magnetic fields compared with traditional models. The optimized amplitude of modulated magnetic field is obtained based on the linewidth model, and the heading error is suppressed by about 80% within the magnetic field inclination angle of 28.76°. The theory and method presented here are important for the application of magnetometers in Earth-scale magnetic field, which can suppress the heading error while keeping the linewidth unchanged.
{"title":"Suppression of Heading Error in Bell-Bloom Atomic Magnetometer by Controlling RF Magnetic Field","authors":"Jun Zhu;Liwei Jiang;Jiali Liu;Xin Zhao;Chi Fang;Qi Shao;Yuntian Zou;Zhuo Wang","doi":"10.1109/TIM.2024.3485395","DOIUrl":"https://doi.org/10.1109/TIM.2024.3485395","url":null,"abstract":"The atomic magnetometers operated in Earth-scale magnetic field are susceptible to the nonlinear Zeeman (NLZ) effect, resulting in multiple resonance peaks and heading error, which restricts their practical applications. We introduce a spin-locking method based on magnetic field modulation to overcome the NLZ effect and thus suppress the heading error in atomic magnetometers. The suppression effect of spin-locking is proportional to the amplitude of the modulation field. However, an excessively high modulation field amplitude can lead to broadening of the measurement linewidth. A novel model characterizing the linewidth for the amplitude of modulated magnetic field under different environmental magnetic field is established by considering the NLZ effect. From the test results, the novel model can more accurately predict the linewidth under different environmental magnetic fields compared with traditional models. The optimized amplitude of modulated magnetic field is obtained based on the linewidth model, and the heading error is suppressed by about 80% within the magnetic field inclination angle of 28.76°. The theory and method presented here are important for the application of magnetometers in Earth-scale magnetic field, which can suppress the heading error while keeping the linewidth unchanged.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-9"},"PeriodicalIF":5.6,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
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：