Accurate prediction of the rate of penetration(ROP)is significant for drilling optimization.While the intelligent ROP prediction model based on fully connected neural networks(FNN)outperforms traditional ROP equations...Accurate prediction of the rate of penetration(ROP)is significant for drilling optimization.While the intelligent ROP prediction model based on fully connected neural networks(FNN)outperforms traditional ROP equations and machine learning algorithms,its lack of interpretability undermines its credibility.This study proposes a novel interpretation and characterization method for the FNN ROP prediction model using the Rectified Linear Unit(ReLU)activation function.By leveraging the derivative of the ReLU function,the FNN function calculation process is transformed into vector operations.The FNN model is linearly characterized through further simplification,enabling its interpretation and analysis.The proposed method is applied in ROP prediction scenarios using drilling data from three vertical wells in the Tarim Oilfield.The results demonstrate that the FNN ROP prediction model with ReLU as the activation function performs exceptionally well.The relative activation frequency curve of hidden layer neurons aids in analyzing the overfitting of the FNN ROP model and determining drilling data similarity.In the well sections with similar drilling data,averaging the weight parameters enables linear characterization of the FNN ROP prediction model,leading to the establishment of a corresponding linear representation equation.Furthermore,the quantitative analysis of each feature's influence on ROP facilitates the proposal of drilling parameter optimization schemes for the current well section.The established linear characterization equation exhibits high precision,strong stability,and adaptability through the application and validation across multiple well sections.展开更多
This study investigates resilient platoon control for constrained intelligent and connected vehicles(ICVs)against F-local Byzantine attacks.We introduce a resilient distributed model-predictive platooning control fram...This study investigates resilient platoon control for constrained intelligent and connected vehicles(ICVs)against F-local Byzantine attacks.We introduce a resilient distributed model-predictive platooning control framework for such ICVs.This framework seamlessly integrates the predesigned optimal control with distributed model predictive control(DMPC)optimization and introduces a unique distributed attack detector to ensure the reliability of the transmitted information among vehicles.Notably,our strategy uses previously broadcasted information and a specialized convex set,termed the“resilience set”,to identify unreliable data.This approach significantly eases graph robustness prerequisites,requiring only an(F+1)-robust graph,in contrast to the established mean sequence reduced algorithms,which require a minimum(2F+1)-robust graph.Additionally,we introduce a verification algorithm to restore trust in vehicles under minor attacks,further reducing communication network robustness.Our analysis demonstrates the recursive feasibility of the DMPC optimization.Furthermore,the proposed method achieves exceptional control performance by minimizing the discrepancies between the DMPC control inputs and predesigned platoon control inputs,while ensuring constraint compliance and cybersecurity.Simulation results verify the effectiveness of our theoretical findings.展开更多
In this paper,a control scheme based on current optimization is proposed for dual three-phase permanent-magnet synchronous motor(DTP-PMSM)drive to reduce the low-frequency temperature swing.The reduction of temperatur...In this paper,a control scheme based on current optimization is proposed for dual three-phase permanent-magnet synchronous motor(DTP-PMSM)drive to reduce the low-frequency temperature swing.The reduction of temperature swing can be equivalent to reducing maximum instantaneous phase copper loss in this paper.First,a two-level optimization aiming at minimizing maximum instantaneous phase copper loss at each electrical angle is proposed.Then,the optimization is transformed to a singlelevel optimization by introducing the auxiliary variable for easy solving.Considering that singleobjective optimization trades a great total copper loss for a small reduction of maximum phase copper loss,the optimization considering both instantaneous total copper loss and maximum phase copper loss is proposed,which has the same performance of temperature swing reduction but with lower total loss.In this way,the proposed control scheme can reduce maximum junction temperature by 11%.Both simulation and experimental results are presented to prove the effectiveness and superiority of the proposed control scheme for low-frequency temperature swing reduction.展开更多
Generative artificial intelligence(AI),as an emerging paradigm in content generation,has demonstrated its great potentials in creating high-fidelity data including images,texts,and videos.Nowadays wireless networks an...Generative artificial intelligence(AI),as an emerging paradigm in content generation,has demonstrated its great potentials in creating high-fidelity data including images,texts,and videos.Nowadays wireless networks and applications have been rapidly evolving from achieving“connected things”to embracing“connected intelligence”.Generative AI has been recognized as a fundamentally innovative technology to drive the advancement of intelligent wireless communications and networks.展开更多
Bone age assessment(BAA)helps doctors determine how a child’s bones grow and develop in clinical medicine.Traditional BAA methods rely on clinician expertise,leading to time-consuming predictions and inaccurate resul...Bone age assessment(BAA)helps doctors determine how a child’s bones grow and develop in clinical medicine.Traditional BAA methods rely on clinician expertise,leading to time-consuming predictions and inaccurate results.Most deep learning-based BAA methods feed the extracted critical points of images into the network by providing additional annotations.This operation is costly and subjective.To address these problems,we propose a multi-scale attentional densely connected network(MSADCN)in this paper.MSADCN constructs a multi-scale dense connectivity mechanism,which can avoid overfitting,obtain the local features effectively and prevent gradient vanishing even in limited training data.First,MSADCN designs multi-scale structures in the densely connected network to extract fine-grained features at different scales.Then,coordinate attention is embedded to focus on critical features and automatically locate the regions of interest(ROI)without additional annotation.In addition,to improve the model’s generalization,transfer learning is applied to train the proposed MSADCN on the public dataset IMDB-WIKI,and the obtained pre-trained weights are loaded onto the Radiological Society of North America(RSNA)dataset.Finally,label distribution learning(LDL)and expectation regression techniques are introduced into our model to exploit the correlation between hand bone images of different ages,which can obtain stable age estimates.Extensive experiments confirm that our model can converge more efficiently and obtain a mean absolute error(MAE)of 4.64 months,outperforming some state-of-the-art BAA methods.展开更多
11.US20220389814A1。摘要:A system includes a pipe string;a wireline cable run through the pipe string;and a downhole tool for formation testing,wherein the downhole tool comprises,an upper assembly,an impeller unit co...11.US20220389814A1。摘要:A system includes a pipe string;a wireline cable run through the pipe string;and a downhole tool for formation testing,wherein the downhole tool comprises,an upper assembly,an impeller unit connected to a downhole end of the upper assembly,wherein the impeller unit comprises a first impeller coupled to a second impeller by a shaf,a first flowline having a first end that is open to the formation,a packer unit that isolates a portion of a borehole surrounding the first end of the first flowline from the rest of the borehole,and a tool string connected to the first flowline,wherein the tool string hydraulically connects the packing device to the upper assembly.展开更多
以往关于学校联结与抑郁关系的理论和实证研究结果均不一致。为明确两者间的整体关系,探索造成分歧的原因,对纳入的87项研究进行了三水平元分析。结果发现,学校联结与抑郁存在显著负相关(r=-0.39, df=205, p <0.001)。此外,学校联结...以往关于学校联结与抑郁关系的理论和实证研究结果均不一致。为明确两者间的整体关系,探索造成分歧的原因,对纳入的87项研究进行了三水平元分析。结果发现,学校联结与抑郁存在显著负相关(r=-0.39, df=205, p <0.001)。此外,学校联结和抑郁的关系受被试性别、年龄、抑郁测量工具、研究数据属性的调节,但不受学校联结测量工具、文化类型、发表年份的调节。本研究首次使用三水平元分析技术整合了学校联结与抑郁的关系,理论上为两者关系提供了阶段性定论,实践上为预防和干预个体抑郁提供了参考依据。展开更多
Pig breeding is generally conducted among many herds, so EBV comparisons across populationsare necessary. Genetic connectedness is required for reliable between-farm animal EBV comparisons.Five quantitative overall co...Pig breeding is generally conducted among many herds, so EBV comparisons across populationsare necessary. Genetic connectedness is required for reliable between-farm animal EBV comparisons.Five quantitative overall connectedness measures among populations have been proposed so far,coefficient of connectedness(γ*), coefficient of determination (CD) and overall indices ofprecision, connectedness rating, number of direct genetic links between subpopulations due tocommon sires and dams (GLt), and average genetic covariance (AGC) are reviewed and theirproperties are discussed in this paper. It is recommended to use AGC at present for measuringgenetic connectedness between herds.展开更多
This study investigates the dynamic connectedness between stock indices and the effect of economic policy uncertainty(EPU)in eight countries where COVID-19 was most widespread(China,Italy,France,Germany,Spain,Russia,t...This study investigates the dynamic connectedness between stock indices and the effect of economic policy uncertainty(EPU)in eight countries where COVID-19 was most widespread(China,Italy,France,Germany,Spain,Russia,the US,and the UK)by implementing the time-varying VAR(TVP-VAR)model for daily data over the period spanning from 01/01/2015 to 05/18/2020.Results showed that stock markets were highly connected during the entire period,but the dynamic spillovers reached unprecedented heights during the COVID-19 pandemic in the first quarter of 2020.Moreover,we found that the European stock markets(except Italy)transmitted more spillovers to all other stock markets than they received,primarily during the COVID-19 outbreak.Further analysis using a nonlinear framework showed that the dynamic connectedness was more pronounced for negative than for positive returns.Also,findings showed that the direction of the EPU effect on net connectedness changed during the pandemic onset,indicating that information spillovers from a given market may signal either good or bad news for other markets,depending on the prevailing economic situation.These results have important implications for individual investors,portfolio managers,policymakers,investment banks,and central banks.展开更多
基金The authors greatly thanked the financial support from the National Key Research and Development Program of China(funded by National Natural Science Foundation of China,No.2019YFA0708300)the Strategic Cooperation Technology Projects of CNPC and CUPB(funded by China National Petroleum Corporation,No.ZLZX2020-03)+1 种基金the National Science Fund for Distinguished Young Scholars(funded by National Natural Science Foundation of China,No.52125401)Science Foundation of China University of Petroleum,Beijing(funded by China University of petroleum,Beijing,No.2462022SZBH002).
文摘Accurate prediction of the rate of penetration(ROP)is significant for drilling optimization.While the intelligent ROP prediction model based on fully connected neural networks(FNN)outperforms traditional ROP equations and machine learning algorithms,its lack of interpretability undermines its credibility.This study proposes a novel interpretation and characterization method for the FNN ROP prediction model using the Rectified Linear Unit(ReLU)activation function.By leveraging the derivative of the ReLU function,the FNN function calculation process is transformed into vector operations.The FNN model is linearly characterized through further simplification,enabling its interpretation and analysis.The proposed method is applied in ROP prediction scenarios using drilling data from three vertical wells in the Tarim Oilfield.The results demonstrate that the FNN ROP prediction model with ReLU as the activation function performs exceptionally well.The relative activation frequency curve of hidden layer neurons aids in analyzing the overfitting of the FNN ROP model and determining drilling data similarity.In the well sections with similar drilling data,averaging the weight parameters enables linear characterization of the FNN ROP prediction model,leading to the establishment of a corresponding linear representation equation.Furthermore,the quantitative analysis of each feature's influence on ROP facilitates the proposal of drilling parameter optimization schemes for the current well section.The established linear characterization equation exhibits high precision,strong stability,and adaptability through the application and validation across multiple well sections.
基金the financial support from the Natural Sciences and Engineering Research Council of Canada(NSERC)。
文摘This study investigates resilient platoon control for constrained intelligent and connected vehicles(ICVs)against F-local Byzantine attacks.We introduce a resilient distributed model-predictive platooning control framework for such ICVs.This framework seamlessly integrates the predesigned optimal control with distributed model predictive control(DMPC)optimization and introduces a unique distributed attack detector to ensure the reliability of the transmitted information among vehicles.Notably,our strategy uses previously broadcasted information and a specialized convex set,termed the“resilience set”,to identify unreliable data.This approach significantly eases graph robustness prerequisites,requiring only an(F+1)-robust graph,in contrast to the established mean sequence reduced algorithms,which require a minimum(2F+1)-robust graph.Additionally,we introduce a verification algorithm to restore trust in vehicles under minor attacks,further reducing communication network robustness.Our analysis demonstrates the recursive feasibility of the DMPC optimization.Furthermore,the proposed method achieves exceptional control performance by minimizing the discrepancies between the DMPC control inputs and predesigned platoon control inputs,while ensuring constraint compliance and cybersecurity.Simulation results verify the effectiveness of our theoretical findings.
基金supported by the National Natural Science Foundation of China(No.62271109)。
文摘In this paper,a control scheme based on current optimization is proposed for dual three-phase permanent-magnet synchronous motor(DTP-PMSM)drive to reduce the low-frequency temperature swing.The reduction of temperature swing can be equivalent to reducing maximum instantaneous phase copper loss in this paper.First,a two-level optimization aiming at minimizing maximum instantaneous phase copper loss at each electrical angle is proposed.Then,the optimization is transformed to a singlelevel optimization by introducing the auxiliary variable for easy solving.Considering that singleobjective optimization trades a great total copper loss for a small reduction of maximum phase copper loss,the optimization considering both instantaneous total copper loss and maximum phase copper loss is proposed,which has the same performance of temperature swing reduction but with lower total loss.In this way,the proposed control scheme can reduce maximum junction temperature by 11%.Both simulation and experimental results are presented to prove the effectiveness and superiority of the proposed control scheme for low-frequency temperature swing reduction.
文摘Generative artificial intelligence(AI),as an emerging paradigm in content generation,has demonstrated its great potentials in creating high-fidelity data including images,texts,and videos.Nowadays wireless networks and applications have been rapidly evolving from achieving“connected things”to embracing“connected intelligence”.Generative AI has been recognized as a fundamentally innovative technology to drive the advancement of intelligent wireless communications and networks.
基金This research is partially supported by grant from the National Natural Science Foundation of China(No.72071019)grant from the Natural Science Foundation of Chongqing(No.cstc2021jcyj-msxmX0185)grant from the Chongqing Graduate Education and Teaching Reform Research Project(No.yjg193096).
文摘Bone age assessment(BAA)helps doctors determine how a child’s bones grow and develop in clinical medicine.Traditional BAA methods rely on clinician expertise,leading to time-consuming predictions and inaccurate results.Most deep learning-based BAA methods feed the extracted critical points of images into the network by providing additional annotations.This operation is costly and subjective.To address these problems,we propose a multi-scale attentional densely connected network(MSADCN)in this paper.MSADCN constructs a multi-scale dense connectivity mechanism,which can avoid overfitting,obtain the local features effectively and prevent gradient vanishing even in limited training data.First,MSADCN designs multi-scale structures in the densely connected network to extract fine-grained features at different scales.Then,coordinate attention is embedded to focus on critical features and automatically locate the regions of interest(ROI)without additional annotation.In addition,to improve the model’s generalization,transfer learning is applied to train the proposed MSADCN on the public dataset IMDB-WIKI,and the obtained pre-trained weights are loaded onto the Radiological Society of North America(RSNA)dataset.Finally,label distribution learning(LDL)and expectation regression techniques are introduced into our model to exploit the correlation between hand bone images of different ages,which can obtain stable age estimates.Extensive experiments confirm that our model can converge more efficiently and obtain a mean absolute error(MAE)of 4.64 months,outperforming some state-of-the-art BAA methods.
文摘11.US20220389814A1。摘要:A system includes a pipe string;a wireline cable run through the pipe string;and a downhole tool for formation testing,wherein the downhole tool comprises,an upper assembly,an impeller unit connected to a downhole end of the upper assembly,wherein the impeller unit comprises a first impeller coupled to a second impeller by a shaf,a first flowline having a first end that is open to the formation,a packer unit that isolates a portion of a borehole surrounding the first end of the first flowline from the rest of the borehole,and a tool string connected to the first flowline,wherein the tool string hydraulically connects the packing device to the upper assembly.
文摘以往关于学校联结与抑郁关系的理论和实证研究结果均不一致。为明确两者间的整体关系,探索造成分歧的原因,对纳入的87项研究进行了三水平元分析。结果发现,学校联结与抑郁存在显著负相关(r=-0.39, df=205, p <0.001)。此外,学校联结和抑郁的关系受被试性别、年龄、抑郁测量工具、研究数据属性的调节,但不受学校联结测量工具、文化类型、发表年份的调节。本研究首次使用三水平元分析技术整合了学校联结与抑郁的关系,理论上为两者关系提供了阶段性定论,实践上为预防和干预个体抑郁提供了参考依据。
基金supported by Natural Science Foundation of Guangdong Province of China(990732)Science and Technology Research Foundation of Guangdong Province(2KM03508N)+1 种基金Major Scientific Research Project of Guangdong Province(2003A2010601)21 Century Talented Person Foundation of Educational Ministry,China
文摘Pig breeding is generally conducted among many herds, so EBV comparisons across populationsare necessary. Genetic connectedness is required for reliable between-farm animal EBV comparisons.Five quantitative overall connectedness measures among populations have been proposed so far,coefficient of connectedness(γ*), coefficient of determination (CD) and overall indices ofprecision, connectedness rating, number of direct genetic links between subpopulations due tocommon sires and dams (GLt), and average genetic covariance (AGC) are reviewed and theirproperties are discussed in this paper. It is recommended to use AGC at present for measuringgenetic connectedness between herds.
文摘This study investigates the dynamic connectedness between stock indices and the effect of economic policy uncertainty(EPU)in eight countries where COVID-19 was most widespread(China,Italy,France,Germany,Spain,Russia,the US,and the UK)by implementing the time-varying VAR(TVP-VAR)model for daily data over the period spanning from 01/01/2015 to 05/18/2020.Results showed that stock markets were highly connected during the entire period,but the dynamic spillovers reached unprecedented heights during the COVID-19 pandemic in the first quarter of 2020.Moreover,we found that the European stock markets(except Italy)transmitted more spillovers to all other stock markets than they received,primarily during the COVID-19 outbreak.Further analysis using a nonlinear framework showed that the dynamic connectedness was more pronounced for negative than for positive returns.Also,findings showed that the direction of the EPU effect on net connectedness changed during the pandemic onset,indicating that information spillovers from a given market may signal either good or bad news for other markets,depending on the prevailing economic situation.These results have important implications for individual investors,portfolio managers,policymakers,investment banks,and central banks.