The ammunition loading system manipulator is susceptible to gear failure due to high-frequency,heavyload reciprocating motions and the absence of protective gear components.After a fault occurs,the distribution of fau...The ammunition loading system manipulator is susceptible to gear failure due to high-frequency,heavyload reciprocating motions and the absence of protective gear components.After a fault occurs,the distribution of fault characteristics under different loads is markedly inconsistent,and data is hard to label,which makes it difficult for the traditional diagnosis method based on single-condition training to generalize to different conditions.To address these issues,the paper proposes a novel transfer discriminant neural network(TDNN)for gear fault diagnosis.Specifically,an optimized joint distribution adaptive mechanism(OJDA)is designed to solve the distribution alignment problem between two domains.To improve the classification effect within the domain and the feature recognition capability for a few labeled data,metric learning is introduced to distinguish features from different fault categories.In addition,TDNN adopts a new pseudo-label training strategy to achieve label replacement by comparing the maximum probability of the pseudo-label with the test result.The proposed TDNN is verified in the experimental data set of the artillery manipulator device,and the diagnosis can achieve 99.5%,significantly outperforming other traditional adaptation methods.展开更多
Kerosene-alumina nanofluid flow and heat transfer in the presence of magnetic field are studied. The basic partial differential equations are reduced to ordinary differential equations which are solved semi analytical...Kerosene-alumina nanofluid flow and heat transfer in the presence of magnetic field are studied. The basic partial differential equations are reduced to ordinary differential equations which are solved semi analytically using differential transformation method. Velocity and temperature profiles as well as the skin friction coefficient and the Nusselt number are determined analytically. The influence of pertinent parameters such as magnetic parameter, nanofluid volume fraction, viscosity parameter and Eckert number on the flow and heat transfer characteristics is discussed. Results indicate that skin friction coefficient decreases with increase of magnetic parameter, nanofluid volume fraction and viscosity parameter. Nusselt number increases with increase of magnetic parameter and nanofluid volume fraction while it decreases with increase of Eckert number and viscosity parameter.展开更多
The high precision assemblies with considerable radial interference should be accompanied by heating and cooling processes.However,the mechanical properties of metals are greatly affected by thermal operations.So,for ...The high precision assemblies with considerable radial interference should be accompanied by heating and cooling processes.However,the mechanical properties of metals are greatly affected by thermal operations.So,for evaluating the stress distribution and distortion of teeth profiles in a gear/shaft assembly,a transient thermal analysis is necessary for finding the change in mechanical properties.The friction on the contact surface is another important parameter in interaction of the gear with the shaft.Evaluating the gear stress and deformation fields for several modes of heat transfer and friction coefficients showed that the maximum radial or tangential stresses on contact surface of the joint may have more than 8%increase by increasing friction coefficient;while the intensity of heat transfer at cooling stage has lower effect on stress distribution.展开更多
Markov random fields(MRF) have potential for predicting and simulating petroleum reservoir facies more accurately from sample data such as logging, core data and seismic data because they can incorporate interclass re...Markov random fields(MRF) have potential for predicting and simulating petroleum reservoir facies more accurately from sample data such as logging, core data and seismic data because they can incorporate interclass relationships. While, many relative studies were based on Markov chain, not MRF, and using Markov chain model for 3D reservoir stochastic simulation has always been the difficulty in reservoir stochastic simulation. MRF was proposed to simulate type variables(for example lithofacies) in this work. Firstly, a Gibbs distribution was proposed to characterize reservoir heterogeneity for building 3-D(three-dimensional) MRF. Secondly, maximum likelihood approaches of model parameters on well data and training image were considered. Compared with the simulation results of MC(Markov chain), the MRF can better reflect the spatial distribution characteristics of sand body.展开更多
This investigation numerically examined the combined impacts of different turbulator shapes,Al_(2)O_(3)/water nanofluid,and inclined magnetic field on the thermal behavior of micro-scale inclined forward-facing step(M...This investigation numerically examined the combined impacts of different turbulator shapes,Al_(2)O_(3)/water nanofluid,and inclined magnetic field on the thermal behavior of micro-scale inclined forward-facing step(MSIFFS).The length and height for all turbulators were considered 0.0979 and 0.5 mm,respectively,and the Reynolds number varied from 5000 to 10000.In order to compare the skin friction coefficient(SFC) and the heat transfer rate(HTR)simultaneously,the thermal performance factor parameter(TPF) was selected.The results show that all considered cases equipped with turbulators were thermodynamically more advantageous over the simple MSIFFS.Besides,using Al_(2)O_(3)/water nanofluid with different nanoparticles volume fractions(NVF) in the presence of inclined magnetic field(IMF)increased HTR.With an increment of NVF from 1% to 4% and magnetic field density(MFD) from 0.002 to 0.008 T,HTR and subsequently TPF improved.The best result was observed for MSIFFS equipped with a trapezoidal-shaped turbulator with 4% Al_(2)O_(3) in the presence of IMF(B=0.008 T).The TPF increased with the augmentation of Re,and the maximum value of it was 5.2366 for MSIFFS equipped with a trapezoidal-shaped turbulator with 4% Al_(2)O_(3),B=0.008 T,and Re=10000.展开更多
This article investigates the colloidal study for water and ethylene glycol based nanofluids.The effects of Lorentz forces and thermal radiation are considered.The process of non-dimensionalities of governing equation...This article investigates the colloidal study for water and ethylene glycol based nanofluids.The effects of Lorentz forces and thermal radiation are considered.The process of non-dimensionalities of governing equations is carried out successfully by means of similarity variables.Then,the resultant nonlinear nature of flow model is treated numerically via Runge-Kutta scheme.The characteristics of various pertinent flow parameters on the velocity,temperature,streamlines and isotherms are discussed graphically.It is inspected that the Lorentz forces favors the rotational velocity and rotational parameter opposes it.Intensification in the nanofluids temperature is observed for volumetric fraction and thermal radiation parameter and dominating trend is noted for γ-aluminum nanofluid.Furthermore,for higher rotational parameter,reverse flow is investigated.To provoke the validity of the present work,comparison between current and literature results is presented which shows an excellent agreement.It is examined that rotation favors the velocity of the fluid and more radiative fluid enhances the fluid temperature.Moreover,it is inspected that upturns in volumetric fraction improves the thermal and electrical conductivities.展开更多
A study on knowledge transfer in a mutli-agent organization is performed by applying the basic principle in physics such as the kinetic theory.Based on the theoretical analysis of the knowledge accumulation process an...A study on knowledge transfer in a mutli-agent organization is performed by applying the basic principle in physics such as the kinetic theory.Based on the theoretical analysis of the knowledge accumulation process and knowledge transfer attributes,a special type of knowledge field(KF)is introduced and the knowledge diffusion equation(KDE)is developed.The evolution of knowledge potential is modeled by lattice kinetic equation and verified by numerical experiments.The new equation-based modeling developed in this paper is meaningful to simulate and predict the knowledge transfer process in firms.The development of the lattice kinetic model(LKM)for knowledge transfer can contribute to the knowledge management theory,and the managers can also simulate the knowledge accumulation process by using the LKM.展开更多
输电线路巡检中采集的螺栓图像有分辨率低、视觉信息不足的特点。针对传统图像分类模型难以从螺栓图像中学习到语义丰富的视觉表征问题,提出了一种基于多模态对比学习的输电线路螺栓缺陷分类方法。首先,为了将文本中螺栓相关的语义信息...输电线路巡检中采集的螺栓图像有分辨率低、视觉信息不足的特点。针对传统图像分类模型难以从螺栓图像中学习到语义丰富的视觉表征问题,提出了一种基于多模态对比学习的输电线路螺栓缺陷分类方法。首先,为了将文本中螺栓相关的语义信息和先验知识以跨模态的方式注入视觉表征,提出了一种结合多模态对比预训练和监督式微调的二阶段训练算法;其次,为了缓解多模态对比预训练中的过拟合问题,提出了标签平滑的信息噪声对比估计损失(info noise contrastive estimation loss with label smoothing,infoNCE-LS),以提高预训练视觉表征的泛化性能;最后,针对上下游任务的不匹配问题,设计了3种基于文本提示的分类头,以改善预训练视觉表征在监督式微调阶段的迁移学习效果。实验结果表明:该文基于Res Net50和ViT构建的两种模型在螺栓缺陷分类数据集上的准确率分别为92.3%和97.4%,相比基线分别提高了2.4%和5.8%。研究实现了从文本到图像的语义信息跨模态补充,为螺栓缺陷识别的研究提供了新的思路。展开更多
文摘The ammunition loading system manipulator is susceptible to gear failure due to high-frequency,heavyload reciprocating motions and the absence of protective gear components.After a fault occurs,the distribution of fault characteristics under different loads is markedly inconsistent,and data is hard to label,which makes it difficult for the traditional diagnosis method based on single-condition training to generalize to different conditions.To address these issues,the paper proposes a novel transfer discriminant neural network(TDNN)for gear fault diagnosis.Specifically,an optimized joint distribution adaptive mechanism(OJDA)is designed to solve the distribution alignment problem between two domains.To improve the classification effect within the domain and the feature recognition capability for a few labeled data,metric learning is introduced to distinguish features from different fault categories.In addition,TDNN adopts a new pseudo-label training strategy to achieve label replacement by comparing the maximum probability of the pseudo-label with the test result.The proposed TDNN is verified in the experimental data set of the artillery manipulator device,and the diagnosis can achieve 99.5%,significantly outperforming other traditional adaptation methods.
文摘Kerosene-alumina nanofluid flow and heat transfer in the presence of magnetic field are studied. The basic partial differential equations are reduced to ordinary differential equations which are solved semi analytically using differential transformation method. Velocity and temperature profiles as well as the skin friction coefficient and the Nusselt number are determined analytically. The influence of pertinent parameters such as magnetic parameter, nanofluid volume fraction, viscosity parameter and Eckert number on the flow and heat transfer characteristics is discussed. Results indicate that skin friction coefficient decreases with increase of magnetic parameter, nanofluid volume fraction and viscosity parameter. Nusselt number increases with increase of magnetic parameter and nanofluid volume fraction while it decreases with increase of Eckert number and viscosity parameter.
文摘The high precision assemblies with considerable radial interference should be accompanied by heating and cooling processes.However,the mechanical properties of metals are greatly affected by thermal operations.So,for evaluating the stress distribution and distortion of teeth profiles in a gear/shaft assembly,a transient thermal analysis is necessary for finding the change in mechanical properties.The friction on the contact surface is another important parameter in interaction of the gear with the shaft.Evaluating the gear stress and deformation fields for several modes of heat transfer and friction coefficients showed that the maximum radial or tangential stresses on contact surface of the joint may have more than 8%increase by increasing friction coefficient;while the intensity of heat transfer at cooling stage has lower effect on stress distribution.
基金Project(2011ZX05002-005-006)supported by the National "Twelveth Five Year" Science and Technology Major Research Program,China
文摘Markov random fields(MRF) have potential for predicting and simulating petroleum reservoir facies more accurately from sample data such as logging, core data and seismic data because they can incorporate interclass relationships. While, many relative studies were based on Markov chain, not MRF, and using Markov chain model for 3D reservoir stochastic simulation has always been the difficulty in reservoir stochastic simulation. MRF was proposed to simulate type variables(for example lithofacies) in this work. Firstly, a Gibbs distribution was proposed to characterize reservoir heterogeneity for building 3-D(three-dimensional) MRF. Secondly, maximum likelihood approaches of model parameters on well data and training image were considered. Compared with the simulation results of MC(Markov chain), the MRF can better reflect the spatial distribution characteristics of sand body.
文摘This investigation numerically examined the combined impacts of different turbulator shapes,Al_(2)O_(3)/water nanofluid,and inclined magnetic field on the thermal behavior of micro-scale inclined forward-facing step(MSIFFS).The length and height for all turbulators were considered 0.0979 and 0.5 mm,respectively,and the Reynolds number varied from 5000 to 10000.In order to compare the skin friction coefficient(SFC) and the heat transfer rate(HTR)simultaneously,the thermal performance factor parameter(TPF) was selected.The results show that all considered cases equipped with turbulators were thermodynamically more advantageous over the simple MSIFFS.Besides,using Al_(2)O_(3)/water nanofluid with different nanoparticles volume fractions(NVF) in the presence of inclined magnetic field(IMF)increased HTR.With an increment of NVF from 1% to 4% and magnetic field density(MFD) from 0.002 to 0.008 T,HTR and subsequently TPF improved.The best result was observed for MSIFFS equipped with a trapezoidal-shaped turbulator with 4% Al_(2)O_(3) in the presence of IMF(B=0.008 T).The TPF increased with the augmentation of Re,and the maximum value of it was 5.2366 for MSIFFS equipped with a trapezoidal-shaped turbulator with 4% Al_(2)O_(3),B=0.008 T,and Re=10000.
文摘This article investigates the colloidal study for water and ethylene glycol based nanofluids.The effects of Lorentz forces and thermal radiation are considered.The process of non-dimensionalities of governing equations is carried out successfully by means of similarity variables.Then,the resultant nonlinear nature of flow model is treated numerically via Runge-Kutta scheme.The characteristics of various pertinent flow parameters on the velocity,temperature,streamlines and isotherms are discussed graphically.It is inspected that the Lorentz forces favors the rotational velocity and rotational parameter opposes it.Intensification in the nanofluids temperature is observed for volumetric fraction and thermal radiation parameter and dominating trend is noted for γ-aluminum nanofluid.Furthermore,for higher rotational parameter,reverse flow is investigated.To provoke the validity of the present work,comparison between current and literature results is presented which shows an excellent agreement.It is examined that rotation favors the velocity of the fluid and more radiative fluid enhances the fluid temperature.Moreover,it is inspected that upturns in volumetric fraction improves the thermal and electrical conductivities.
基金supported by the National Natural Science Foundation of China(71472055 71871007)+2 种基金National Social Science Foundation of China(16AZD0006)Heilongjiang Philosophy and Social Science Research Project(19GLB087)the Fundamental Research Funds for the Central Universities(HIT.NSRIF.2019033)
文摘A study on knowledge transfer in a mutli-agent organization is performed by applying the basic principle in physics such as the kinetic theory.Based on the theoretical analysis of the knowledge accumulation process and knowledge transfer attributes,a special type of knowledge field(KF)is introduced and the knowledge diffusion equation(KDE)is developed.The evolution of knowledge potential is modeled by lattice kinetic equation and verified by numerical experiments.The new equation-based modeling developed in this paper is meaningful to simulate and predict the knowledge transfer process in firms.The development of the lattice kinetic model(LKM)for knowledge transfer can contribute to the knowledge management theory,and the managers can also simulate the knowledge accumulation process by using the LKM.
文摘输电线路巡检中采集的螺栓图像有分辨率低、视觉信息不足的特点。针对传统图像分类模型难以从螺栓图像中学习到语义丰富的视觉表征问题,提出了一种基于多模态对比学习的输电线路螺栓缺陷分类方法。首先,为了将文本中螺栓相关的语义信息和先验知识以跨模态的方式注入视觉表征,提出了一种结合多模态对比预训练和监督式微调的二阶段训练算法;其次,为了缓解多模态对比预训练中的过拟合问题,提出了标签平滑的信息噪声对比估计损失(info noise contrastive estimation loss with label smoothing,infoNCE-LS),以提高预训练视觉表征的泛化性能;最后,针对上下游任务的不匹配问题,设计了3种基于文本提示的分类头,以改善预训练视觉表征在监督式微调阶段的迁移学习效果。实验结果表明:该文基于Res Net50和ViT构建的两种模型在螺栓缺陷分类数据集上的准确率分别为92.3%和97.4%,相比基线分别提高了2.4%和5.8%。研究实现了从文本到图像的语义信息跨模态补充,为螺栓缺陷识别的研究提供了新的思路。
