Low Earth orbit(LEO)satellite networks exhibit distinct characteristics,e.g.,limited resources of individual satellite nodes and dynamic network topology,which have brought many challenges for routing algorithms.To sa...Low Earth orbit(LEO)satellite networks exhibit distinct characteristics,e.g.,limited resources of individual satellite nodes and dynamic network topology,which have brought many challenges for routing algorithms.To satisfy quality of service(QoS)requirements of various users,it is critical to research efficient routing strategies to fully utilize satellite resources.This paper proposes a multi-QoS information optimized routing algorithm based on reinforcement learning for LEO satellite networks,which guarantees high level assurance demand services to be prioritized under limited satellite resources while considering the load balancing performance of the satellite networks for low level assurance demand services to ensure the full and effective utilization of satellite resources.An auxiliary path search algorithm is proposed to accelerate the convergence of satellite routing algorithm.Simulation results show that the generated routing strategy can timely process and fully meet the QoS demands of high assurance services while effectively improving the load balancing performance of the link.展开更多
Since the concept of quantum information masking was proposed by Modi et al(2018 Phys.Rev.Lett.120,230501),many interesting and significant results have been reported,both theoretically and experimentally.However,desi...Since the concept of quantum information masking was proposed by Modi et al(2018 Phys.Rev.Lett.120,230501),many interesting and significant results have been reported,both theoretically and experimentally.However,designing a quantum information masker is not an easy task,especially for larger systems.In this paper,we propose a variational quantum algorithm to resolve this problem.Specifically,our algorithm is a hybrid quantum-classical model,where the quantum device with adjustable parameters tries to mask quantum information and the classical device evaluates the performance of the quantum device and optimizes its parameters.After optimization,the quantum device behaves as an optimal masker.The loss value during optimization can be used to characterize the performance of the masker.In particular,if the loss value converges to zero,we obtain a perfect masker that completely masks the quantum information generated by the quantum information source,otherwise,the perfect masker does not exist and the subsystems always contain the original information.Nevertheless,these resulting maskers are still optimal.Quantum parallelism is utilized to reduce quantum state preparations and measurements.Our study paves the way for wide application of quantum information masking,and some of the techniques used in this study may have potential applications in quantum information processing.展开更多
This paper investigates the optimization of data sampling and target labeling techniques to enhance algorithmic trading strategies in cryptocurrency markets,focusing on Bitcoin(BTC)and Ethereum(ETH).Traditional data s...This paper investigates the optimization of data sampling and target labeling techniques to enhance algorithmic trading strategies in cryptocurrency markets,focusing on Bitcoin(BTC)and Ethereum(ETH).Traditional data sampling methods,such as time bars,often fail to capture the nuances of the continuously active and highly volatile cryptocurrency market and force traders to wait for arbitrary points in time.To address this,we propose an alternative approach using information-driven sampling methods,including the CUSUM filter,range bars,volume bars,and dollar bars,and evaluate their performance using tick-level data from January 2018 to June 2023.Additionally,we introduce the Triple Barrier method for target labeling,which offers a solution tailored for algorithmic trading as opposed to the widely used next-bar prediction.We empirically assess the effectiveness of these data sampling and labeling methods to craft profitable trading strategies.The results demonstrate that the innovative combination of CUSUM-filtered data with Triple Barrier labeling outperforms traditional time bars and next-bar prediction,achieving consistently positive trading performance even after accounting for transaction costs.Moreover,our system enables making trading decisions at any point in time on the basis of market conditions,providing an advantage over traditional methods that rely on fixed time intervals.Furthermore,the paper contributes to the ongoing debate on the applicability of Transformer models to time series classification in the context of algorithmic trading by evaluating various Transformer architectures—including the vanilla Transformer encoder,FEDformer,and Autoformer—alongside other deep learning architectures and classical machine learning models,revealing insights into their relative performance.展开更多
Low earth orbit (LEO) satellite networkscan provide wider service coverage and lower latencythan traditional terrestrial networks, which haveattracted considerable attention. However, the unevendistribution of human p...Low earth orbit (LEO) satellite networkscan provide wider service coverage and lower latencythan traditional terrestrial networks, which haveattracted considerable attention. However, the unevendistribution of human population and data trafficon the ground incurs unbalanced traffic load inLEO satellite networks. To this end, we proposea load-balancing routing algorithm for LEO satellitenetworks based on ant colony optimization and reinforcementlearning. In the ant colony algorithm,we improve the pheromone update rule by introducingload-aware heuristic information, e.g., the currentnode transmission overhead, delay and load status, andreinforcement learning-based link quality evaluation.It enables the routing algorithm to select the lightlyloaded node as the next hop to balance the networkload. We simulate and verify the proposed algorithmusing the NS2 simulation platform, and the resultsshow that our algorithm improves the data delivery ratioand throughput while ensuring lower latency andtransmission overhead.展开更多
Challenges in stratigraphic modeling arise from underground uncertainty.While borehole exploration is reliable,it remains sparse due to economic and site constraints.Electrical resistivity tomography(ERT)as a cost-eff...Challenges in stratigraphic modeling arise from underground uncertainty.While borehole exploration is reliable,it remains sparse due to economic and site constraints.Electrical resistivity tomography(ERT)as a cost-effective geophysical technique can acquire high-density data;however,uncertainty and nonuniqueness inherent in ERT impede its usage for stratigraphy identification.This paper integrates ERT and onsite observations for the first time to propose a novel method for characterizing stratigraphic profiles.The method consists of two steps:(1)ERT for prior knowledge:ERT data are processed by soft clustering using the Gaussian mixture model,followed by probability smoothing to quantify its depthdependent uncertainty;and(2)Observations for calibration:a spatial sequential Bayesian updating(SSBU)algorithm is developed to update the prior knowledge based on likelihoods derived from onsite observations,namely topsoil and boreholes.The effectiveness of the proposed method is validated through its application to a real slope site in Foshan,China.Comparative analysis with advanced borehole-driven methods highlights the superiority of incorporating ERT data in stratigraphic modeling,in terms of prediction accuracy at borehole locations and sensitivity to borehole data.Informed by ERT,reduced sensitivity to boreholes provides a fundamental solution to the longstanding challenge of sparse measurements.The paper further discusses the impact of ERT uncertainty on the proposed model using time-lapse measurements,the impact of model resolution,and applicability in engineering projects.This study,as a breakthrough in stratigraphic modeling,bridges gaps in combining geophysical and geotechnical data to address measurement sparsity and paves the way for more economical geotechnical exploration.展开更多
The estimation of the probability of informed trading(PIN)model and its extensions poses significant challenges owing to various computational problems.To address these issues,we propose a novel estimation method call...The estimation of the probability of informed trading(PIN)model and its extensions poses significant challenges owing to various computational problems.To address these issues,we propose a novel estimation method called the expectation-conditional-maximization(ECM)algorithm,which can serve as an alternative to the existing methods for estimating PIN models.Our method provides optimal estimates for the original PIN model as well as two of its extensions:the multilayer PIN model and the adjusted PIN model,along with its restricted versions.Our results indicate that estimations using the ECM algorithm are generally faster,more accurate,and more memory-efficient than the standard methods used in the literature,making it a robust alternative.More importantly,the ECM algorithm is not limited to the models discussed and can be easily adapted to estimate future extensions of the PIN model.展开更多
针对齿轮箱振动信号复杂多变,导致现有的齿轮箱故障诊断方法诊断精度不高、较弱故障特征容易被噪声淹没等问题,提出了一种基于向量加权平均优化算法(weighted mean of vectors,INFO)、变分模态分解(variational mode decomposition,VMD...针对齿轮箱振动信号复杂多变,导致现有的齿轮箱故障诊断方法诊断精度不高、较弱故障特征容易被噪声淹没等问题,提出了一种基于向量加权平均优化算法(weighted mean of vectors,INFO)、变分模态分解(variational mode decomposition,VMD)和卷积神经网络(convolutional neural network,CNN)的齿轮故障诊断方法。该方法首先采用熵权法将不同位置的振动传感器信号信息进行融合,利用INFO对VMD算法中参数进行优化,并设计一个复合评价指标作为参数优化的评价标准,使用奇异峭度差分谱的方法对敏感分量进行重构;其次,从重构的信号中提取时域、频域特征并输入到CNN模型中进行分类;最后通过Shap(Shapley additive explanations)值法对模型输入特征的重要性进行排序,分析不同特征组合对模型分类和特定故障识别的影响。在东南大学行星齿轮数据集上进行验证,结果表明,利用所提特征组合进行故障诊断,CNN模型故障诊断准确率为98.24%,高于其他特征组合,为行星齿轮箱的故障诊断提供了一组有效的特征指标。展开更多
The unmanned warehouse dispatching system of the‘goods to people’model uses a structure mainly based on a handling robot,which saves considerable manpower and improves the efficiency of the warehouse picking operati...The unmanned warehouse dispatching system of the‘goods to people’model uses a structure mainly based on a handling robot,which saves considerable manpower and improves the efficiency of the warehouse picking operation.However,the optimal performance of the scheduling system algorithm has high requirements.This study uses a deep Q-network(DQN)algorithm in a deep reinforcement learning algorithm,which combines the Q-learning algorithm,an empirical playback mechanism,and the volume-based technology of productive neural networks to generate target Q-values to solve the problem of multi-robot path planning.The aim of the Q-learning algorithm in deep reinforcement learning is to address two shortcomings of the robot path-planning problem:slow convergence and excessive randomness.Preceding the start of the algorithmic process,prior knowledge and prior rules are used to improve the DQN algorithm.Simulation results show that the improved DQN algorithm converges faster than the classic deep reinforcement learning algorithm and can more quickly learn the solutions to path-planning problems.This improves the efficiency of multi-robot path planning.展开更多
The information transmission path optimization(ITPO) can often a ect the e ciency and accuracy of remanufactur?ing service. However, there is a greater degree of uncertainty and complexity in information transmission ...The information transmission path optimization(ITPO) can often a ect the e ciency and accuracy of remanufactur?ing service. However, there is a greater degree of uncertainty and complexity in information transmission of remanu?facturing service system, which leads to a critical need for designing planning models to deal with this added uncer?tainty and complexity. In this paper, a three?dimensional(3D) model of remanufacturing service information network for information transmission is developed, which combines the physic coordinate and the transmitted properties of all the devices in the remanufacturing service system. In order to solve the basic ITPO in the 3D model, an improved 3D ant colony algorithm(Improved AC) was put forward. Moreover, to further improve the operation e ciency of the algorithm, an improved ant colony?genetic algorithm(AC?GA) that combines the improved AC and genetic algorithm was developed. In addition, by taking the transmission of remanufacturing service demand information of certain roller as example, the e ectiveness of AC?GA algorithm was analyzed and compared with that of improved AC, and the results demonstrated that AC?GA algorithm was superior to AC algorithm in aspects of information transmission delay, information transmission cost, and rate of information loss.展开更多
An aero-engine maintenance policy plays a crucial role in reasonably reducing maintenance cost. An aero-engine is a type of complex equipment with long service-life. In engineering,a hybrid maintenance strategy is ado...An aero-engine maintenance policy plays a crucial role in reasonably reducing maintenance cost. An aero-engine is a type of complex equipment with long service-life. In engineering,a hybrid maintenance strategy is adopted to improve the aero-engine operational reliability. Thus,the long service-life and the hybrid maintenance strategy should be considered synchronously in aero-engine maintenance policy optimization. This paper proposes an aero-engine life-cycle maintenance policy optimization algorithm that synchronously considers the long service-life and the hybrid maintenance strategy. The reinforcement learning approach was adopted to illustrate the optimization framework, in which maintenance policy optimization was formulated as a Markov decision process. In the reinforcement learning framework, the Gauss–Seidel value iteration algorithm was adopted to optimize the maintenance policy. Compared with traditional aero-engine maintenance policy optimization methods, the long service-life and the hybrid maintenance strategy could be addressed synchronously by the proposed algorithm. Two numerical experiments and algorithm analyses were performed to illustrate the optimization algorithm in detail.展开更多
A kind of single linked lists named aggregative chain is introduced to the algorithm, thus improving the architecture of FP tree. The new FP tree is a one-way tree and only the pointers that point its parent at each n...A kind of single linked lists named aggregative chain is introduced to the algorithm, thus improving the architecture of FP tree. The new FP tree is a one-way tree and only the pointers that point its parent at each node are kept. Route information of different nodes in a same item are compressed into aggregative chains so that the frequent patterns will be produced in aggregative chains without generating node links and conditional pattern bases. An example of Web key words retrieval is given to analyze and verify the frequent pattern algorithm in this paper.展开更多
Using similar single-difference methodology(SSDM) to solve the deformation values of the monitoring points, there is unstability of the deformation information series, at sometimes.In order to overcome this shortcomin...Using similar single-difference methodology(SSDM) to solve the deformation values of the monitoring points, there is unstability of the deformation information series, at sometimes.In order to overcome this shortcoming, Kalman filtering algorithm for this series is established,and its correctness and validity are verified with the test data obtained on the movable platform in plane. The results show that Kalman filtering can improve the correctness, reliability and stability of the deformation information series.展开更多
To aim at the multimode character of the data from the airplane detecting system, the paper combines Dempster- Shafer evidence theory and subjective Bayesian algorithm and makes to propose a mixed structure multimode ...To aim at the multimode character of the data from the airplane detecting system, the paper combines Dempster- Shafer evidence theory and subjective Bayesian algorithm and makes to propose a mixed structure multimode data fusion algorithm. The algorithm adopts a prorated algorithm relate to the incertitude evaluation to convert the probability evaluation into the precognition probability in an identity frame, and ensures the adaptability of different data from different source to the mixed system. To guarantee real time fusion, a combination of time domain fusion and space domain fusion is established, this not only assure the fusion of data chain in different time of the same sensor, but also the data fusion from different sensors distributed in different platforms and the data fusion among different modes. The feasibility and practicability are approved through computer simulation.展开更多
This paper provides an attempt to utilize machine learning algorithm,explicitly random-forest algorithm,to optimize the performance of dye sensitized solar cells(DSSCs)in terms of conversion efficiency.The optimizatio...This paper provides an attempt to utilize machine learning algorithm,explicitly random-forest algorithm,to optimize the performance of dye sensitized solar cells(DSSCs)in terms of conversion efficiency.The optimization is implemented with respect to both the mesoporous TiO_(2) active layer thickness and porosity.Herein,the porosity impact is reflected to the model as a variation in the effective refractive index and dye absorption.Database set has been established using our data in the literature as well as numerical data extracted from our numerical model.The random-forest model is used for model regression,prediction,and optimization,reaching 99.87%accuracy.Perfect agreement with experimental data was observed,with 4.17%conversion efficiency.展开更多
As a typical technology for optical encryption,phase retrieval algorithms have been widely used in optical information encryption and authentication systems.This paper presents three applications of two-dimensional(2D...As a typical technology for optical encryption,phase retrieval algorithms have been widely used in optical information encryption and authentication systems.This paper presents three applications of two-dimensional(2D)phase retrieval for optical encryption and authentication:first,a hierarchical image encryption system,by which multiple images can be hidden into cascaded multiple phase masks;second,a multilevel image authentication system,which combines(t,n)threshold secret sharing(both t and n are positive integers,and t≤n)and phase retrieval,and provides both high-level and low-level authentication;and finally,a hierarchical multilevel authentication system that combines the secret sharing scheme based on basic vector operations and the phase retrieval,by which more certification images can be encoded into multiple cascaded phase masks of different hierarchical levels.These three phase retrieval algorithms can effectively illustrate phase-retrievalbased optical information security.The principles and features of each phase-retrieval-based optical security method are analyzed and discussed.It is hoped that this review will illustrate the current development of phase retrieval algorithms for optical information security and will also shed light on the future development of phase retrieval algorithms for optical information security.展开更多
Fiber reinforced polymers (FRPs), unlike steel, are corrosion-resistant and therefore are of interest;however, their use is hindered because their brittle shear is formulated in most specifications using limited data ...Fiber reinforced polymers (FRPs), unlike steel, are corrosion-resistant and therefore are of interest;however, their use is hindered because their brittle shear is formulated in most specifications using limited data available at the time. We aimed to predict the shear strength of concrete beams reinforced with FRP bars and without stirrups by compiling a relatively large database of 198 previously published test results (available in appendix). To model shear strength, an artificial neural network was trained by an ensemble of Levenberg-Marquardt and imperialist competitive algorithms. The results suggested superior accuracy of model compared to equations available in specifications and literature.展开更多
In this paper, the diversity information included by dominating number is analyzed, and the probabilistic relationship between dominating number and diversity in the space of objective function is proved. A ranking me...In this paper, the diversity information included by dominating number is analyzed, and the probabilistic relationship between dominating number and diversity in the space of objective function is proved. A ranking method based on dominating number is proposed to build the Pareto front. Without increasing basic Pareto method’s computation complexity and introducing new parameters, a new multiobjective genetic algorithm based on proposed ranking method (MOGA-DN) is presented. Simulation results on function optimization and parameters optimization of control system verify the efficiency of MOGA-DN.展开更多
The concepts of information fusion and the basic principles of neural networks are introduced. Neural net-works were introduced as a way of building an information fusion model in a coal mine monitoring system. This a...The concepts of information fusion and the basic principles of neural networks are introduced. Neural net-works were introduced as a way of building an information fusion model in a coal mine monitoring system. This assures the accurate transmission of the multi-sensor information that comes from the coal mine monitoring systems. The in-formation fusion mode was analyzed. An algorithm was designed based on this analysis and some simulation results were given. Finally,conclusions that could provide auxiliary decision making information to the coal mine dispatching officers were presented.展开更多
The main thrust of this paper is application of a novel data mining approach on the log of user' s feedback to improve web multimedia information retrieval performance. A user space model was constructed based...The main thrust of this paper is application of a novel data mining approach on the log of user' s feedback to improve web multimedia information retrieval performance. A user space model was constructed based on data mining, and then integrated into the original information space model to improve the accuracy of the new information space model. It can remove clutter and irrelevant text information and help to eliminate mismatch between the page author' s expression and the user' s understanding and expectation. User spacemodel was also utilized to discover the relationship between high-level and low-level features for assigning weight. The authors proposed improved Bayesian algorithm for data mining. Experiment proved that the au-thors' proposed algorithm was efficient.展开更多
基金National Key Research and Development Program(2021YFB2900604)。
文摘Low Earth orbit(LEO)satellite networks exhibit distinct characteristics,e.g.,limited resources of individual satellite nodes and dynamic network topology,which have brought many challenges for routing algorithms.To satisfy quality of service(QoS)requirements of various users,it is critical to research efficient routing strategies to fully utilize satellite resources.This paper proposes a multi-QoS information optimized routing algorithm based on reinforcement learning for LEO satellite networks,which guarantees high level assurance demand services to be prioritized under limited satellite resources while considering the load balancing performance of the satellite networks for low level assurance demand services to ensure the full and effective utilization of satellite resources.An auxiliary path search algorithm is proposed to accelerate the convergence of satellite routing algorithm.Simulation results show that the generated routing strategy can timely process and fully meet the QoS demands of high assurance services while effectively improving the load balancing performance of the link.
基金Supported by the National Natural Science Foundation of China(under Grant Nos.12105090 and 12074107)the Program of Outstanding Young and Middle-aged Scientific and Technological Innovation Team of Colleges and Universities in Hubei Province of China(under Grant No.T2020001)the Innovation Group Project of the Natural Science Foundation of Hubei Province of China(under Grant No.2022CFA012)。
文摘Since the concept of quantum information masking was proposed by Modi et al(2018 Phys.Rev.Lett.120,230501),many interesting and significant results have been reported,both theoretically and experimentally.However,designing a quantum information masker is not an easy task,especially for larger systems.In this paper,we propose a variational quantum algorithm to resolve this problem.Specifically,our algorithm is a hybrid quantum-classical model,where the quantum device with adjustable parameters tries to mask quantum information and the classical device evaluates the performance of the quantum device and optimizes its parameters.After optimization,the quantum device behaves as an optimal masker.The loss value during optimization can be used to characterize the performance of the masker.In particular,if the loss value converges to zero,we obtain a perfect masker that completely masks the quantum information generated by the quantum information source,otherwise,the perfect masker does not exist and the subsystems always contain the original information.Nevertheless,these resulting maskers are still optimal.Quantum parallelism is utilized to reduce quantum state preparations and measurements.Our study paves the way for wide application of quantum information masking,and some of the techniques used in this study may have potential applications in quantum information processing.
基金support of the University of Warsaw under’New Ideas 3B’competition in POB Ⅲ implemented under the’Excellence Initiative-Research University’Programme.
文摘This paper investigates the optimization of data sampling and target labeling techniques to enhance algorithmic trading strategies in cryptocurrency markets,focusing on Bitcoin(BTC)and Ethereum(ETH).Traditional data sampling methods,such as time bars,often fail to capture the nuances of the continuously active and highly volatile cryptocurrency market and force traders to wait for arbitrary points in time.To address this,we propose an alternative approach using information-driven sampling methods,including the CUSUM filter,range bars,volume bars,and dollar bars,and evaluate their performance using tick-level data from January 2018 to June 2023.Additionally,we introduce the Triple Barrier method for target labeling,which offers a solution tailored for algorithmic trading as opposed to the widely used next-bar prediction.We empirically assess the effectiveness of these data sampling and labeling methods to craft profitable trading strategies.The results demonstrate that the innovative combination of CUSUM-filtered data with Triple Barrier labeling outperforms traditional time bars and next-bar prediction,achieving consistently positive trading performance even after accounting for transaction costs.Moreover,our system enables making trading decisions at any point in time on the basis of market conditions,providing an advantage over traditional methods that rely on fixed time intervals.Furthermore,the paper contributes to the ongoing debate on the applicability of Transformer models to time series classification in the context of algorithmic trading by evaluating various Transformer architectures—including the vanilla Transformer encoder,FEDformer,and Autoformer—alongside other deep learning architectures and classical machine learning models,revealing insights into their relative performance.
基金supported in part by the National Natural Science Foundation of China(Grant No.62273107,61702127,62272113)Science and Technology Program of Guangzhou(Grant No.201804010461).
文摘Low earth orbit (LEO) satellite networkscan provide wider service coverage and lower latencythan traditional terrestrial networks, which haveattracted considerable attention. However, the unevendistribution of human population and data trafficon the ground incurs unbalanced traffic load inLEO satellite networks. To this end, we proposea load-balancing routing algorithm for LEO satellitenetworks based on ant colony optimization and reinforcementlearning. In the ant colony algorithm,we improve the pheromone update rule by introducingload-aware heuristic information, e.g., the currentnode transmission overhead, delay and load status, andreinforcement learning-based link quality evaluation.It enables the routing algorithm to select the lightlyloaded node as the next hop to balance the networkload. We simulate and verify the proposed algorithmusing the NS2 simulation platform, and the resultsshow that our algorithm improves the data delivery ratioand throughput while ensuring lower latency andtransmission overhead.
基金the financial support from the National Key R&D Program of China(Grant No.2021YFC3001003)Science and Technology Development Fund,Macao SAR(File No.0056/2023/RIB2)Guangdong Provincial Department of Science and Technology(Grant No.2022A0505030019).
文摘Challenges in stratigraphic modeling arise from underground uncertainty.While borehole exploration is reliable,it remains sparse due to economic and site constraints.Electrical resistivity tomography(ERT)as a cost-effective geophysical technique can acquire high-density data;however,uncertainty and nonuniqueness inherent in ERT impede its usage for stratigraphy identification.This paper integrates ERT and onsite observations for the first time to propose a novel method for characterizing stratigraphic profiles.The method consists of two steps:(1)ERT for prior knowledge:ERT data are processed by soft clustering using the Gaussian mixture model,followed by probability smoothing to quantify its depthdependent uncertainty;and(2)Observations for calibration:a spatial sequential Bayesian updating(SSBU)algorithm is developed to update the prior knowledge based on likelihoods derived from onsite observations,namely topsoil and boreholes.The effectiveness of the proposed method is validated through its application to a real slope site in Foshan,China.Comparative analysis with advanced borehole-driven methods highlights the superiority of incorporating ERT data in stratigraphic modeling,in terms of prediction accuracy at borehole locations and sensitivity to borehole data.Informed by ERT,reduced sensitivity to boreholes provides a fundamental solution to the longstanding challenge of sparse measurements.The paper further discusses the impact of ERT uncertainty on the proposed model using time-lapse measurements,the impact of model resolution,and applicability in engineering projects.This study,as a breakthrough in stratigraphic modeling,bridges gaps in combining geophysical and geotechnical data to address measurement sparsity and paves the way for more economical geotechnical exploration.
基金supported by the Scientific and Technological Research Council of Turkey(TUBITAK)[grant no 122K637].
文摘The estimation of the probability of informed trading(PIN)model and its extensions poses significant challenges owing to various computational problems.To address these issues,we propose a novel estimation method called the expectation-conditional-maximization(ECM)algorithm,which can serve as an alternative to the existing methods for estimating PIN models.Our method provides optimal estimates for the original PIN model as well as two of its extensions:the multilayer PIN model and the adjusted PIN model,along with its restricted versions.Our results indicate that estimations using the ECM algorithm are generally faster,more accurate,and more memory-efficient than the standard methods used in the literature,making it a robust alternative.More importantly,the ECM algorithm is not limited to the models discussed and can be easily adapted to estimate future extensions of the PIN model.
文摘针对齿轮箱振动信号复杂多变,导致现有的齿轮箱故障诊断方法诊断精度不高、较弱故障特征容易被噪声淹没等问题,提出了一种基于向量加权平均优化算法(weighted mean of vectors,INFO)、变分模态分解(variational mode decomposition,VMD)和卷积神经网络(convolutional neural network,CNN)的齿轮故障诊断方法。该方法首先采用熵权法将不同位置的振动传感器信号信息进行融合,利用INFO对VMD算法中参数进行优化,并设计一个复合评价指标作为参数优化的评价标准,使用奇异峭度差分谱的方法对敏感分量进行重构;其次,从重构的信号中提取时域、频域特征并输入到CNN模型中进行分类;最后通过Shap(Shapley additive explanations)值法对模型输入特征的重要性进行排序,分析不同特征组合对模型分类和特定故障识别的影响。在东南大学行星齿轮数据集上进行验证,结果表明,利用所提特征组合进行故障诊断,CNN模型故障诊断准确率为98.24%,高于其他特征组合,为行星齿轮箱的故障诊断提供了一组有效的特征指标。
基金This research has been supported by Yueqi Youth Scholar Funding of China University of Mining and Technology(Beijing)the Major Programme of the National Natural Science Foundation of China(No.71831001).
文摘The unmanned warehouse dispatching system of the‘goods to people’model uses a structure mainly based on a handling robot,which saves considerable manpower and improves the efficiency of the warehouse picking operation.However,the optimal performance of the scheduling system algorithm has high requirements.This study uses a deep Q-network(DQN)algorithm in a deep reinforcement learning algorithm,which combines the Q-learning algorithm,an empirical playback mechanism,and the volume-based technology of productive neural networks to generate target Q-values to solve the problem of multi-robot path planning.The aim of the Q-learning algorithm in deep reinforcement learning is to address two shortcomings of the robot path-planning problem:slow convergence and excessive randomness.Preceding the start of the algorithmic process,prior knowledge and prior rules are used to improve the DQN algorithm.Simulation results show that the improved DQN algorithm converges faster than the classic deep reinforcement learning algorithm and can more quickly learn the solutions to path-planning problems.This improves the efficiency of multi-robot path planning.
基金National Natural Science Foundation of China(Grant Nos.51805385,71471143)Hubei Provincial Natural Science Foundation of China(Grant No.2018CFB265)Center for Service Science and Engineering of Wuhan University of Science and Technology(Grant No.CSSE2017KA04)
文摘The information transmission path optimization(ITPO) can often a ect the e ciency and accuracy of remanufactur?ing service. However, there is a greater degree of uncertainty and complexity in information transmission of remanu?facturing service system, which leads to a critical need for designing planning models to deal with this added uncer?tainty and complexity. In this paper, a three?dimensional(3D) model of remanufacturing service information network for information transmission is developed, which combines the physic coordinate and the transmitted properties of all the devices in the remanufacturing service system. In order to solve the basic ITPO in the 3D model, an improved 3D ant colony algorithm(Improved AC) was put forward. Moreover, to further improve the operation e ciency of the algorithm, an improved ant colony?genetic algorithm(AC?GA) that combines the improved AC and genetic algorithm was developed. In addition, by taking the transmission of remanufacturing service demand information of certain roller as example, the e ectiveness of AC?GA algorithm was analyzed and compared with that of improved AC, and the results demonstrated that AC?GA algorithm was superior to AC algorithm in aspects of information transmission delay, information transmission cost, and rate of information loss.
基金co-supported by the Key National Natural Science Foundation of China (No. U1533202)the Civil Aviation Administration of China (No. MHRD20150104)the Shandong Independent Innovation and Achievements Transformation Fund, China (No. 2014CGZH1101)
文摘An aero-engine maintenance policy plays a crucial role in reasonably reducing maintenance cost. An aero-engine is a type of complex equipment with long service-life. In engineering,a hybrid maintenance strategy is adopted to improve the aero-engine operational reliability. Thus,the long service-life and the hybrid maintenance strategy should be considered synchronously in aero-engine maintenance policy optimization. This paper proposes an aero-engine life-cycle maintenance policy optimization algorithm that synchronously considers the long service-life and the hybrid maintenance strategy. The reinforcement learning approach was adopted to illustrate the optimization framework, in which maintenance policy optimization was formulated as a Markov decision process. In the reinforcement learning framework, the Gauss–Seidel value iteration algorithm was adopted to optimize the maintenance policy. Compared with traditional aero-engine maintenance policy optimization methods, the long service-life and the hybrid maintenance strategy could be addressed synchronously by the proposed algorithm. Two numerical experiments and algorithm analyses were performed to illustrate the optimization algorithm in detail.
基金Supported by the Natural Science Foundation ofLiaoning Province (20042020)
文摘A kind of single linked lists named aggregative chain is introduced to the algorithm, thus improving the architecture of FP tree. The new FP tree is a one-way tree and only the pointers that point its parent at each node are kept. Route information of different nodes in a same item are compressed into aggregative chains so that the frequent patterns will be produced in aggregative chains without generating node links and conditional pattern bases. An example of Web key words retrieval is given to analyze and verify the frequent pattern algorithm in this paper.
文摘Using similar single-difference methodology(SSDM) to solve the deformation values of the monitoring points, there is unstability of the deformation information series, at sometimes.In order to overcome this shortcoming, Kalman filtering algorithm for this series is established,and its correctness and validity are verified with the test data obtained on the movable platform in plane. The results show that Kalman filtering can improve the correctness, reliability and stability of the deformation information series.
文摘To aim at the multimode character of the data from the airplane detecting system, the paper combines Dempster- Shafer evidence theory and subjective Bayesian algorithm and makes to propose a mixed structure multimode data fusion algorithm. The algorithm adopts a prorated algorithm relate to the incertitude evaluation to convert the probability evaluation into the precognition probability in an identity frame, and ensures the adaptability of different data from different source to the mixed system. To guarantee real time fusion, a combination of time domain fusion and space domain fusion is established, this not only assure the fusion of data chain in different time of the same sensor, but also the data fusion from different sensors distributed in different platforms and the data fusion among different modes. The feasibility and practicability are approved through computer simulation.
文摘This paper provides an attempt to utilize machine learning algorithm,explicitly random-forest algorithm,to optimize the performance of dye sensitized solar cells(DSSCs)in terms of conversion efficiency.The optimization is implemented with respect to both the mesoporous TiO_(2) active layer thickness and porosity.Herein,the porosity impact is reflected to the model as a variation in the effective refractive index and dye absorption.Database set has been established using our data in the literature as well as numerical data extracted from our numerical model.The random-forest model is used for model regression,prediction,and optimization,reaching 99.87%accuracy.Perfect agreement with experimental data was observed,with 4.17%conversion efficiency.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61775121,61605165,61307003,61405122,and 11574311)the Key Research and Development Program of Shandong Province,China(Grant No.2018GGX101002)+1 种基金the Natural Science Foundation of Shandong Province,China(Grant No.ZR2019QF006)the Fundamental Research Funds of Shandong University,China(Grant No.2015GN031)
文摘As a typical technology for optical encryption,phase retrieval algorithms have been widely used in optical information encryption and authentication systems.This paper presents three applications of two-dimensional(2D)phase retrieval for optical encryption and authentication:first,a hierarchical image encryption system,by which multiple images can be hidden into cascaded multiple phase masks;second,a multilevel image authentication system,which combines(t,n)threshold secret sharing(both t and n are positive integers,and t≤n)and phase retrieval,and provides both high-level and low-level authentication;and finally,a hierarchical multilevel authentication system that combines the secret sharing scheme based on basic vector operations and the phase retrieval,by which more certification images can be encoded into multiple cascaded phase masks of different hierarchical levels.These three phase retrieval algorithms can effectively illustrate phase-retrievalbased optical information security.The principles and features of each phase-retrieval-based optical security method are analyzed and discussed.It is hoped that this review will illustrate the current development of phase retrieval algorithms for optical information security and will also shed light on the future development of phase retrieval algorithms for optical information security.
文摘Fiber reinforced polymers (FRPs), unlike steel, are corrosion-resistant and therefore are of interest;however, their use is hindered because their brittle shear is formulated in most specifications using limited data available at the time. We aimed to predict the shear strength of concrete beams reinforced with FRP bars and without stirrups by compiling a relatively large database of 198 previously published test results (available in appendix). To model shear strength, an artificial neural network was trained by an ensemble of Levenberg-Marquardt and imperialist competitive algorithms. The results suggested superior accuracy of model compared to equations available in specifications and literature.
基金supported by the Academic Outstanding Youth Talented Person Fund of Anhui Province (No.2009SQR2014)
文摘In this paper, the diversity information included by dominating number is analyzed, and the probabilistic relationship between dominating number and diversity in the space of objective function is proved. A ranking method based on dominating number is proposed to build the Pareto front. Without increasing basic Pareto method’s computation complexity and introducing new parameters, a new multiobjective genetic algorithm based on proposed ranking method (MOGA-DN) is presented. Simulation results on function optimization and parameters optimization of control system verify the efficiency of MOGA-DN.
基金project BK2001073 supported by Jiangsu Province Natural Science Foundation
文摘The concepts of information fusion and the basic principles of neural networks are introduced. Neural net-works were introduced as a way of building an information fusion model in a coal mine monitoring system. This assures the accurate transmission of the multi-sensor information that comes from the coal mine monitoring systems. The in-formation fusion mode was analyzed. An algorithm was designed based on this analysis and some simulation results were given. Finally,conclusions that could provide auxiliary decision making information to the coal mine dispatching officers were presented.
文摘The main thrust of this paper is application of a novel data mining approach on the log of user' s feedback to improve web multimedia information retrieval performance. A user space model was constructed based on data mining, and then integrated into the original information space model to improve the accuracy of the new information space model. It can remove clutter and irrelevant text information and help to eliminate mismatch between the page author' s expression and the user' s understanding and expectation. User spacemodel was also utilized to discover the relationship between high-level and low-level features for assigning weight. The authors proposed improved Bayesian algorithm for data mining. Experiment proved that the au-thors' proposed algorithm was efficient.
