期刊文献+
共找到109篇文章
< 1 2 6 >
每页显示 20 50 100
复合高斯杂波下雷达目标自适应检测方法 被引量:1
1
作者 简涛 马颖亮 +2 位作者 谢梓铿 魏广芬 何佳 《信号处理》 北大核心 2025年第4期739-748,共10页
在高距离分辨率的宽带雷达探测场景下,背景杂波呈现出越来越强的非高斯特性,可用复合高斯分布进行合理建模;不同于传统窄带雷达的点目标,宽带雷达目标在径向距离维上展现距离扩展形式。针对复合高斯杂波下现有距离扩展目标检测方法对杂... 在高距离分辨率的宽带雷达探测场景下,背景杂波呈现出越来越强的非高斯特性,可用复合高斯分布进行合理建模;不同于传统窄带雷达的点目标,宽带雷达目标在径向距离维上展现距离扩展形式。针对复合高斯杂波下现有距离扩展目标检测方法对杂波纹理分量信息利用不足的问题,在未知协方差矩阵结构的复合高斯杂波背景下,将纹理分量建模为逆Gamma分布,进而研究了雷达距离扩展目标自适应子空间检测方法。根据两步法设计策略和不同统计检验理论,构建了三种自适应子空间检测器。首先,在杂波纹理分量和协方差矩阵结构已知的条件下,基于Rao检验、Wald检验和Gradient检验,推导了三种检测统计量。其次,通过求解未知纹理分量的最大后验估计和未知协方差矩阵结构的迭代估计,构建了距离扩展目标的三种自适应子空间检测器;其中,所提出的Rao检测器和Gradient检测器具有一致性。理论证明了所提三种检测器对未知协方差矩阵结构的渐进恒虚警率特性。仿真分析了目标散射模型、辅助数据量、杂波相关性等因素对所提检测器的性能影响;实验结果表明,针对均匀高斯环境设计的现有检测器在复合高斯环境下检测性能退化较为严重,所提检测器的检测性能均优于现有复合高斯环境下的对比检测器;其中所提出的Wald检测器略优于所提出的Rao检测器。 展开更多
关键词 复合高斯 距离扩展目标检测 Gradient检验 Rao检验 WALD检验
在线阅读 下载PDF
基于机器学习方法预测3D打印零件的性能
2
作者 洪学银 高尚 《中国塑料》 北大核心 2025年第7期72-79,共8页
采用拉丁超立方实验设计,研究了层高、壁厚、顶底厚、顶底线条方向、填充密度、填充线条方向、打印速度、挤出温度、床温、工作空间温度10种熔融沉积建模(FDM)工艺参数对丙烯腈-丁二烯-苯乙烯共聚物(ABS)零件拉伸性能的影响,对比了人工... 采用拉丁超立方实验设计,研究了层高、壁厚、顶底厚、顶底线条方向、填充密度、填充线条方向、打印速度、挤出温度、床温、工作空间温度10种熔融沉积建模(FDM)工艺参数对丙烯腈-丁二烯-苯乙烯共聚物(ABS)零件拉伸性能的影响,对比了人工神经元网络(ANN)、随机森林(RF)和梯度提升算法(GB)3种机器学习方法预测拉伸性能的准确性。结果表明,ANN预测拉伸强度和断裂伸长率的相关系数R仅为0.883 5和0.892 4,在训练和测试数据集上,预测的均方误差(MSE)在5~10和20~24之间;RF预测的R值为0.913 6和0.924 0,MSE在3~8和15~20之间;GB预测准确性最高,R值为0.975 9和0.981 2,MSE最低,在1~4和8~10之间。在10种工艺参数中,在采用RF模型时,拉伸性能的显著影响因素为填充密度、壁厚、填充线条方向和顶底厚,在采用GB模型时,拉伸性能的显著影响因素为填充密度、壁厚、层高和填充线条方向。填充密度是影响拉伸性能最显著的因素,对GB预测结果的影响显著性达到80%左右,远大于RF模型中的40%。 展开更多
关键词 熔融沉积建模 人工神经元网络 随机森林 Gradient Boosting 拉伸性能
在线阅读 下载PDF
基于机器学习的铜电解精炼电积过程电压及出液铜离子浓度预测模型研究
3
作者 闫哲祯 卢金成 +3 位作者 程寒 廖嘉琪 徐夫元 段宁 《有色金属(冶炼部分)》 北大核心 2025年第9期13-24,共12页
电积是目前最为常用的铜电解液净化工艺,其出口铜离子浓度波动大、人工调控难度高,易造成后续硫化单元处理负荷剧增及铜砷共沉淀产废量增大,而传统预测模型存在不可解释、稳态限制、低泛化能力等缺陷。为此,构建了企业电积生产过程电压... 电积是目前最为常用的铜电解液净化工艺,其出口铜离子浓度波动大、人工调控难度高,易造成后续硫化单元处理负荷剧增及铜砷共沉淀产废量增大,而传统预测模型存在不可解释、稳态限制、低泛化能力等缺陷。为此,构建了企业电积生产过程电压及出液铜离子浓度准确预测的多参数模型。通过对比研究10种机器学习模型,发现GBR在电压预测中表现最优(决定系数R^(2)=0.79,均方误差MSE=1.25),XGBoost对出液铜离子浓度的预测准确度最高(R^(2)=0.87,MSE=5.58)。SHAP解释性分析表明,电流和时间分别是影响电压和出液铜离子浓度变化的主控因素。模型决策机制与电化学原理及质量守恒定律一致,突破了传统模型对非线性关系的表征局限,为异常工况的预警诊断、关键参数动态优化控制及减少污染物产生提供依据。 展开更多
关键词 铜电积 机器学习 Gradient Boosting Regression(GBR) eXtreme Gradient Boosting(XGBoost) 解释性分析 Shapley Additive exPlanations(SHAP)
在线阅读 下载PDF
Design of a wideband non-uniform microstrip line for complex impedance matching in automotive radar frequencies
4
作者 ZHANG Shuang-Gen YU Tao +2 位作者 WANG Yu-Lan CHENG Zhi-Hua YAO Jian-Quan 《红外与毫米波学报》 北大核心 2025年第2期168-176,共9页
Microstrip transmission lines connecting to the millimeter wave radar chip and antenna significantly affect the radiation efficiency and bandwidth of the antenna.Here,a wideband non-uniform wavy microstrip line for co... Microstrip transmission lines connecting to the millimeter wave radar chip and antenna significantly affect the radiation efficiency and bandwidth of the antenna.Here,a wideband non-uniform wavy microstrip line for complex impedance in automotive radar frequency range is proposed.Unlike the gradient transmission line,the wavy structure is composed of periodically semi-circular segments.By adjusting the radius of the semi-circular,the surface current is varied and concentrated on the semi-circular segments,allowing a wider tunability range of the resonant frequency.The results reveal that the bandwidth of the loaded wavy transmission line antenna improves to 9.37 GHz,which is 5.81 GHz wider than that of the loaded gradient line.The gain and the half power beam width of the loaded antenna are about 14.69 dB and 9.58°,respectively.The proposed non-uniform microstrip line scheme may open up a route for realizing wideband millimeter-wave automotive radar applications. 展开更多
关键词 millimeter wave gradient line wavy transmission line broadband high gain array antenna
在线阅读 下载PDF
A Modified PRP-HS Hybrid Conjugate Gradient Algorithm for Solving Unconstrained Optimization Problems
5
作者 LI Xiangli WANG Zhiling LI Binglan 《应用数学》 北大核心 2025年第2期553-564,共12页
In this paper,we propose a three-term conjugate gradient method for solving unconstrained optimization problems based on the Hestenes-Stiefel(HS)conjugate gradient method and Polak-Ribiere-Polyak(PRP)conjugate gradien... In this paper,we propose a three-term conjugate gradient method for solving unconstrained optimization problems based on the Hestenes-Stiefel(HS)conjugate gradient method and Polak-Ribiere-Polyak(PRP)conjugate gradient method.Under the condition of standard Wolfe line search,the proposed search direction is the descent direction.For general nonlinear functions,the method is globally convergent.Finally,numerical results show that the proposed method is efficient. 展开更多
关键词 Conjugate gradient method Unconstrained optimization Sufficient descent condition Global convergence
在线阅读 下载PDF
Adjoint-based RCS surface sensitivity calculation for very large electrical size object
6
作者 Jun Deng Zhenghong Gao +3 位作者 Lin Zhou Ke Zhao Jiangtao Huang Wei Zhang 《Defence Technology(防务技术)》 2025年第5期164-179,共16页
The primary concern in stealth aircraft design is the very large electrical size objects.However,the computational and storage requirements of these objects present significant obstacles for current highfidelity desig... The primary concern in stealth aircraft design is the very large electrical size objects.However,the computational and storage requirements of these objects present significant obstacles for current highfidelity design methods,particularly when addressing high-dimensional complex engineering design problems.To address these challenges,we developed a surface sensitivity technique based on the multilevel fast multipole algorithm(MLFMA).An access and storage of sparse partial derivative tensor was improved to significantly enhanced the computation performance.The far-field interactions of the surface sensitivity equation were realized by differential the multipole expansion.In addition,we proposed a fast far-field multiplication method to accelerate the multiplication process.The surface mesh derivative with respect to the design variables was calculated by analytical and complex variable methods,substantially improving computational efficiency.These advancements enabled the MLFMAbased surface sensitivity method to millions meshes and large-scale gradients,extending gradientbased optimization for very large electrical size problems.Test cases have verified the effectiveness of this method in optimizing very large electrical objects in terms of both accuracy and efficiency. 展开更多
关键词 Surface sensitivity Gradient MLFMA Discrete adjoint Very large electrical size RCS
在线阅读 下载PDF
Research on the hazards of gas leakage and explosion in a full-scale residential building
7
作者 Chengjun Yue Li Chen +2 位作者 Zhan Li Bin Feng Ruizhi Xu 《Defence Technology(防务技术)》 2025年第1期168-181,共14页
The gas explosion in residential building has always been a highly concerned problem.Explosions in homogeneous mixtures have been extensively studied.However,mixtures are often inhomogeneous in the practical scenarios... The gas explosion in residential building has always been a highly concerned problem.Explosions in homogeneous mixtures have been extensively studied.However,mixtures are often inhomogeneous in the practical scenarios due to the differences in the densities of methane and air.In order to investigate the effects of gas explosions in inhomogeneous mixtures,experimental studies involving gas leakage and explosion are conducted in a full-scale residential building to reproduce the process of gas explosion.By fitting the dimensionless buoyancy as a function of dimensionless height and dimensionless time,a distribution model of gas in large-scale spaces is established,and the mechanism of inhomogeneous distribution of methane is also be revealed.Furthermore,the stratified reconstruction method(SRM)is introduced for efficiently setting up inhomogeneous concentration fields in FLACS.The simulation results highlight that for the internal overpressure,the distribution of methane has no effect on the first overpressure peak(ΔP1),while it significantly influences the subsequent overpressure peak(ΔP2),and the maximum difference between the overpressure of homogeneous and inhomogeneous distribution is174.3%.Moreover,the initial concentration distribution also has a certain impact on the external overpressure. 展开更多
关键词 Methane distribution Inhomogeneous mixture Gradient layer Gas explosion Explosive simulation
在线阅读 下载PDF
Stress gradient analytic solution and reasonable support prestress of roadway surrounding rock based on unified strength criterion:A case study
8
作者 JING Suo-lin WEN Zhi-jie +2 位作者 ZUO Yu-jun LI Qiu-ju HAO Peng 《Journal of Central South University》 2025年第2期449-468,共20页
The stress gradient of surrounding rock and reasonable prestress of support are the keys to ensuring the stability of roadways.The elastic-plastic analytical solution for surrounding rock was derived based on unified ... The stress gradient of surrounding rock and reasonable prestress of support are the keys to ensuring the stability of roadways.The elastic-plastic analytical solution for surrounding rock was derived based on unified strength theory.A model for solving the stress gradient of the surrounding rock with the intermediate principal stress parameter b was established.The correctness and applicability of the solution for the stress gradient in the roadway surrounding rock was verified via multiple methods.Furthermore,the laws of stress,displacement,and the plastic zone of the surrounding rock with different b values and prestresses were revealed.As b increases,the stress gradient in the plastic zone increases,and the displacement and plastic zone radius decrease.As the prestress increases,the peak stress shifts toward the sidewalls,and the stress and stress gradient increments decrease.In addition,the displacement increment and plastic zone increment were proposed to characterize the support effect.The balance point of the plastic zone area appears before that of the displacement zone.The relationship between the stress gradient compensation coefficient and the prestress is obtained.This study provides a research method and idea for determining the reasonable prestress of support in roadways. 展开更多
关键词 PRESTRESS support compensation surrounding rock damage stress gradient analytic solution unified strength theory
在线阅读 下载PDF
Research on three-dimensional attack area based on improved backtracking and ALPS-GP algorithms of air-to-air missile
9
作者 ZHANG Haodi WANG Yuhui HE Jiale 《Journal of Systems Engineering and Electronics》 2025年第1期292-310,共19页
In the field of calculating the attack area of air-to-air missiles in modern air combat scenarios,the limitations of existing research,including real-time calculation,accuracy efficiency trade-off,and the absence of t... In the field of calculating the attack area of air-to-air missiles in modern air combat scenarios,the limitations of existing research,including real-time calculation,accuracy efficiency trade-off,and the absence of the three-dimensional attack area model,restrict their practical applications.To address these issues,an improved backtracking algorithm is proposed to improve calculation efficiency.A significant reduction in solution time and maintenance of accuracy in the three-dimensional attack area are achieved by using the proposed algorithm.Furthermore,the age-layered population structure genetic programming(ALPS-GP)algorithm is introduced to determine an analytical polynomial model of the three-dimensional attack area,considering real-time requirements.The accuracy of the polynomial model is enhanced through the coefficient correction using an improved gradient descent algorithm.The study reveals a remarkable combination of high accuracy and efficient real-time computation,with a mean error of 91.89 m using the analytical polynomial model of the three-dimensional attack area solved in just 10^(-4)s,thus meeting the requirements of real-time combat scenarios. 展开更多
关键词 air combat three-dimensional attack area improved backtracking algorithm age-layered population structure genetic programming(ALPS-GP) gradient descent algorithm
在线阅读 下载PDF
Recognition for underground voids in C-scans based on GMM-HMM
10
作者 BAI Xu LI Yuhao +4 位作者 GUO Shizeng LIU Jinlong WEN Zhitao LI Hongrui ZHANG Jiayan 《Journal of Systems Engineering and Electronics》 2025年第1期82-94,共13页
Ground penetrating radar(GPR),as a fast,efficient,and non-destructive detection device,holds great potential for the detection of shallow subsurface environments,such as urban road subsurface monitoring.However,the in... Ground penetrating radar(GPR),as a fast,efficient,and non-destructive detection device,holds great potential for the detection of shallow subsurface environments,such as urban road subsurface monitoring.However,the interpretation of GPR echo images often relies on manual recognition by experienced engineers.In order to address the automatic interpretation of cavity targets in GPR echo images,a recognition-algorithm based on Gaussian mixed model-hidden Markov model(GMM-HMM)is proposed,which can recognize three dimensional(3D)underground voids automatically.First,energy detection on the echo images is performed,whereby the data is preprocessed and pre-filtered.Then,edge histogram descriptor(EHD),histogram of oriented gradient(HOG),and Log-Gabor filters are used to extract features from the images.The traditional method can only be applied to 2D images and pre-processing is required for C-scan images.Finally,the aggregated features are fed into the GMM-HMM for classification and compared with two other methods,long short-term memory(LSTM)and gate recurrent unit(GRU).By testing on a simulated dataset,an accuracy rate of 90%is obtained,demonstrating the effectiveness and efficiency of our proposed method. 展开更多
关键词 ground penetrating rader(GPR) RECOGNITION edge histogram descriptor(EHD) histogram of oriented gradient(HOG) Log-Gabor filter
在线阅读 下载PDF
Effect of post weld heat treatment on grain boundary character distribution and corrosion resistance of friction stir welded armourgrade nickel and molybdenum-free high-nitrogen austenitic stainless steel
11
作者 Arun Kumar Gurrala Raffi Mohammed G Madhusudhan Reddy 《Defence Technology(防务技术)》 2025年第9期246-261,共16页
This study examines the effects of friction stir welding(FSW)and post-weld heat treatment(PWHT)on the grain boundary character distribution and corrosion resistance of cross sectional(top and bottom)regions of nickel-... This study examines the effects of friction stir welding(FSW)and post-weld heat treatment(PWHT)on the grain boundary character distribution and corrosion resistance of cross sectional(top and bottom)regions of nickel-and molybdenum-free high-nitrogen austenitic stainless steel(HNASS).FSW at 400 rpm and 30 mm/min resulted in finer grains(4.18μm)and higher coincident site lattice(CSL)boundaries(32.3%)at the top of the stir zone(SZ)due to dynamic recrystallization(DRX).PWHT at 900℃for 1 h led to grain coarsening(12.91μm the bottom SZ)but enhanced CSL boundaries from 24.6%to 30.2%,improving grain boundary stability.PWHT reduced the kernel average misorientation(KAM)by 14.9%in the SZ-top layer and 20.4%in the SZ-bottom layer,accompanied by a 25%decrease in hardness in the SZ-top layer and 26.7%in the SZ-bottom layer,indicating strain recovery and reduced dislocation density.Potentiodynamic polarization tests(PDP)showed a 18%increase in pitting potential and a 76%reduction in corrosion rate after PWHT.The improvement in corrosion resistance is attributed to the increase inΣ3 twin boundaries,which enhance grain boundary stability and reduce susceptibility to localized corrosion.These findings highlight the role of PWHT in refining the microstructure and strengthening corrosion resistance,making HNASS a promising material for demanding applications. 展开更多
关键词 Nickel and molybdenum free high-nitrogen austenitic stainless steel Friction stir welding Post-weld heat treatment Electron backscattered diffraction Microstructural gradients Pitting corrosion resistance Coincident site lattice Grain boundary characteristic distribution
在线阅读 下载PDF
考虑环境因素的电动汽车充电站实时负荷预测模型 被引量:5
12
作者 李波 王宁 +1 位作者 吕叶林 陈宇 《同济大学学报(自然科学版)》 EI CAS CSCD 北大核心 2024年第6期962-969,共8页
为了减少电动汽车大规模集成到电网造成的不利影响,提出了一种能够实现充电站充电负荷精准预测的方法。该方法利用LightGBM(light gradient boosting machine)与XGBoost(eXtreme gradient boosting)模型构建线下-线上组合模型。考虑充... 为了减少电动汽车大规模集成到电网造成的不利影响,提出了一种能够实现充电站充电负荷精准预测的方法。该方法利用LightGBM(light gradient boosting machine)与XGBoost(eXtreme gradient boosting)模型构建线下-线上组合模型。考虑充电负荷、时间、温度、天气等历史数据,利用LightGBM模型初步建立充电负荷线下预测模型;基于XGBoost模型,以线下预测模型输出负荷和实际负荷的误差为优化目标,实时变化的交通流量为协变量,建立线上预测模型,并对初步预测结果进行误差修正。某市实际充电站预测结果表明,相比于随机森林(RF)、LightGBM模型、XGBoost模型、多层感知机(MLP)以及LightGBM-RF组合模型,该组合模型具有更高的预测精度,同时可以准确预测不同充电站的实时充电负荷。 展开更多
关键词 电动汽车 充电负荷预测 LightGBM(light gradient boosting machine) XGBoost(eXtreme gradient boosting) 在线学习
在线阅读 下载PDF
基于机器学习的透水混凝土耐磨性能预测 被引量:1
13
作者 白涛 罗小宝 邢国华 《硅酸盐通报》 CAS 北大核心 2024年第1期138-146,共9页
本研究旨在利用机器学习模型进行透水混凝土耐磨性能预测。收集了150组透水混凝土耐磨性能试验数据并构建了数据库,采用特征相关性分析确定了6个输入参数,分别为骨料最大粒径、水胶比、砂率、骨胶比、粉煤灰掺量和旋转圈数。利用多种机... 本研究旨在利用机器学习模型进行透水混凝土耐磨性能预测。收集了150组透水混凝土耐磨性能试验数据并构建了数据库,采用特征相关性分析确定了6个输入参数,分别为骨料最大粒径、水胶比、砂率、骨胶比、粉煤灰掺量和旋转圈数。利用多种机器学习算法(XGBoost、Gradient Boosting、AdaBoost、Decision Tree和Random Forest)建立了透水混凝土磨损率预测模型,通过决定系数(R^(2))、均方根误差(RMSE)和平均绝对误差(MAE)对模型性能进行表征。研究结果表明,Gradient Boosting模型在训练集和测试集上均具有较高的准确性和较小的预测误差,与现有理论模型的比较分析也证实了Gradient Boosting模型在预测透水混凝土磨损率方面的优势。研究成果可为透水混凝土的设计和应用提供参考,并有望降低相关工程的维护成本。 展开更多
关键词 透水混凝土 耐磨性能 磨损率 机器学习 Gradient Boosting模型
在线阅读 下载PDF
结合机器学习的SA湍流模型闭合系数修正
14
作者 徐向阳 胡冠男 +2 位作者 王良军 朱文浩 张武 《上海大学学报(自然科学版)》 CAS CSCD 北大核心 2024年第2期341-351,共11页
将修正Morris分类筛选法与极端梯度提升(extreme gradient boosting,XGBoost)相结合,在计算流体动力学(computational fluid dynamics,CFD)数据驱动下,用于SA(Spalart-Allmaras)湍流模型闭合系数的修正.利用分类筛选法有效缩小闭合系数... 将修正Morris分类筛选法与极端梯度提升(extreme gradient boosting,XGBoost)相结合,在计算流体动力学(computational fluid dynamics,CFD)数据驱动下,用于SA(Spalart-Allmaras)湍流模型闭合系数的修正.利用分类筛选法有效缩小闭合系数研究范围,同时依据XGBoost方法在小规模数据集下取得精度较高的拟合模型,有效提升系数修正效率.在三维DLR-F6-WB构型下进行了数值实验,实验结果显示利用本方法能够在三维复杂模型上基于小样本数据进行系数修正,修正后的升阻力系数计算精度得到了显著提升. 展开更多
关键词 SA(Spalart-Allmaras)湍流模型 敏感度 极端梯度提升(extreme gradient boosting XGBoost) 线性回归 系数修正
在线阅读 下载PDF
基于机器学习的热带气旋灾害等级评估模型构建及其活动特征分析 被引量:4
15
作者 刘淑贤 张立生 +3 位作者 刘扬 王维国 杨琨 张源达 《气象》 CSCD 北大核心 2024年第3期331-343,共13页
在全球变暖的背景下,热带气旋(TC)作为影响我国最严重的自然灾害之一,其活动特征及灾害损失评估研究受到了广泛关注。采用组合赋权和k-means等方法,分析了2000年以来登陆我国的TC及灾害损失特征,并构建了基于机器学习的TC灾害等级评估... 在全球变暖的背景下,热带气旋(TC)作为影响我国最严重的自然灾害之一,其活动特征及灾害损失评估研究受到了广泛关注。采用组合赋权和k-means等方法,分析了2000年以来登陆我国的TC及灾害损失特征,并构建了基于机器学习的TC灾害等级评估模型。结果表明:从总体趋势来看,登陆我国的TC频数在逐年减少,但登陆风速的最大值却在缓慢增加;广东、浙江、福建、广西受灾较为严重,但整体上全国综合灾情指数呈下降趋势;与传统的随机森林、支持向量机、朴素贝叶斯算法相比,LightGBM(Light Gradient Boosting Machine)在TC灾害评估中效果最佳,准确率值为0.91,其中致灾因子是模型中最关键的因素,其次是防灾减灾能力、暴露度和脆弱性指标。 展开更多
关键词 热带气旋 灾害等级评估 机器学习 LightGBM(Light Gradient Boosting Machine)
在线阅读 下载PDF
Mechanical property of cylindrical sandwich shell with gradient core of entangled wire mesh 被引量:1
16
作者 Xin Xue Chao Zheng +1 位作者 Fu-qiang Lai Xue-qian Wu 《Defence Technology(防务技术)》 SCIE EI CAS CSCD 2024年第1期510-522,共13页
To explore the wide-frequency damping and vibration-attenuation performances in the application of aerospace components,the cylindrical sandwich shell structure with a gradient core of entangled wire mesh was proposed... To explore the wide-frequency damping and vibration-attenuation performances in the application of aerospace components,the cylindrical sandwich shell structure with a gradient core of entangled wire mesh was proposed in this paper.Firstly,the gradient cores of entangled wire mesh in the axial and radial directions were prepared by using an in-house Numerical Control weaving machine,and the metallurgical connection between skin sheets and the gradient core was performed using vacuum brazing.Secondly,to investigate the mechanical properties of cylindrical sandwich shells with axial or radial gradient cores,quasi-static and dynamic mechanical experiments were carried out.The primary evaluations of mechanical properties include secant stiffness,natural frequency,Specific Energy Absorption(SEA),vibration acceleration level,and so on.The results suggest that the vibration-attenuation performance of the sandwich shell is remarkable when the high-density core layer is at the end of the shell or abuts the inner skin.The axial gradient material has almost no influence on the vibration frequencies of the shell,whereas the vibration frequencies increase dramatically when the high-density core layer approaches the skin.Moreover,compared to the conventional sandwich shells,the proposed functional grading cylindrical sandwich shell exhibits more potential in mass reduction,stiffness designing,and energy dissipation. 展开更多
关键词 Entangled wire mesh Gradient cylindrical sandwich shell Vacuum brazing Secant stiffness Damping
在线阅读 下载PDF
Adaptive detection of range-spread targets in homogeneous and partially homogeneous clutter plus subspace interference 被引量:1
17
作者 JIAN Tao HE Jia +3 位作者 WANG Bencai LIU Yu XU Congan XIE Zikeng 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2024年第1期43-54,共12页
Adaptive detection of range-spread targets is considered in the presence of subspace interference plus Gaussian clutter with unknown covariance matrix.The target signal and interference are supposed to lie in two line... Adaptive detection of range-spread targets is considered in the presence of subspace interference plus Gaussian clutter with unknown covariance matrix.The target signal and interference are supposed to lie in two linearly independent subspaces with deterministic but unknown coordinates.Relying on the two-step criteria,two adaptive detectors based on Gradient tests are proposed,in homogeneous and partially homogeneous clutter plus subspace interference,respectively.Both of the proposed detectors exhibit theoretically constant false alarm rate property against unknown clutter covariance matrix as well as the power level.Numerical results show that,the proposed detectors have better performance than their existing counterparts,especially for mismatches in the signal steering vectors. 展开更多
关键词 adaptive detection subspace interference constant false alarm rate Gradient test partially homogeneous environment
在线阅读 下载PDF
一种基于稀疏优化和Nesterov动量策略的模型剪枝算法 被引量:1
18
作者 周强 陈军 +1 位作者 鲍蕾 陶卿 《数据采集与处理》 CSCD 北大核心 2024年第3期659-667,共9页
随着深度学习快速发展,模型的参数量和计算复杂度爆炸式增长,在移动终端上部署面临挑战,模型剪枝成为深度学习模型落地应用的关键。目前,基于正则化的剪枝方法通常采用L2正则化并结合基于数量级的重要性标准,是一种经验性的方法,缺乏理... 随着深度学习快速发展,模型的参数量和计算复杂度爆炸式增长,在移动终端上部署面临挑战,模型剪枝成为深度学习模型落地应用的关键。目前,基于正则化的剪枝方法通常采用L2正则化并结合基于数量级的重要性标准,是一种经验性的方法,缺乏理论依据,精度难以保证。受Proximal梯度方法求解稀疏优化问题的启发,本文提出一种能够在深度神经网络上直接产生稀疏解的Prox⁃NAG优化方法,并设计了与之配套的迭代剪枝算法。该方法基于L1正则化,利用Nesterov动量求解优化问题,克服了原有正则化剪枝方法对L2正则化和数量级标准的依赖,是稀疏优化从传统机器学习向深度学习的自然推广。在CIFAR10数据集上对ResNet系列模型进行剪枝实验,实验结果证明Prox⁃NAG剪枝算法较原有剪枝算法性能有所提升。 展开更多
关键词 稀疏 优化 剪枝算法 Proximal梯度方法 Nesterov加速梯度(Nesterov accelerated gradient NAG)
在线阅读 下载PDF
Classification of aviation incident causes using LGBM with improved cross-validation 被引量:1
19
作者 NI Xiaomei WANG Huawei +1 位作者 CHEN Lingzi LIN Ruiguan 《Journal of Systems Engineering and Electronics》 SCIE CSCD 2024年第2期396-405,共10页
Aviation accidents are currently one of the leading causes of significant injuries and deaths worldwide. This entices researchers to investigate aircraft safety using data analysis approaches based on an advanced mach... Aviation accidents are currently one of the leading causes of significant injuries and deaths worldwide. This entices researchers to investigate aircraft safety using data analysis approaches based on an advanced machine learning algorithm.To assess aviation safety and identify the causes of incidents, a classification model with light gradient boosting machine (LGBM)based on the aviation safety reporting system (ASRS) has been developed. It is improved by k-fold cross-validation with hybrid sampling model (HSCV), which may boost classification performance and maintain data balance. The results show that employing the LGBM-HSCV model can significantly improve accuracy while alleviating data imbalance. Vertical comparison with other cross-validation (CV) methods and lateral comparison with different fold times comprise the comparative approach. Aside from the comparison, two further CV approaches based on the improved method in this study are discussed:one with a different sampling and folding order, and the other with more CV. According to the assessment indices with different methods, the LGBMHSCV model proposed here is effective at detecting incident causes. The improved model for imbalanced data categorization proposed may serve as a point of reference for similar data processing, and the model’s accurate identification of civil aviation incident causes can assist to improve civil aviation safety. 展开更多
关键词 aviation safety imbalance data light gradient boosting machine(LGBM) cross-validation(CV)
在线阅读 下载PDF
基于深度强化学习的IRS辅助NOMA-MEC通信资源分配优化 被引量:1
20
作者 方娟 刘珍珍 +1 位作者 陈思琪 李硕朋 《北京工业大学学报》 CAS CSCD 北大核心 2024年第8期930-938,共9页
为了解决无法与边缘服务器建立直连通信链路的盲区边缘用户卸载任务的问题,设计了一个基于深度强化学习(deep reinforcement learning, DRL)的智能反射面(intelligent reflecting surface, IRS)辅助非正交多址(non-orthogonal multiple ... 为了解决无法与边缘服务器建立直连通信链路的盲区边缘用户卸载任务的问题,设计了一个基于深度强化学习(deep reinforcement learning, DRL)的智能反射面(intelligent reflecting surface, IRS)辅助非正交多址(non-orthogonal multiple access, NOMA)通信的资源分配优化算法,以获得由系统和速率和能源效率(energy efficiency, EE)加权的最大系统收益,从而实现绿色高效通信。通过深度确定性策略梯度(deep deterministic policy gradient, DDPG)算法联合优化传输功率分配和IRS的反射相移矩阵。仿真结果表明,使用DDPG算法处理移动边缘计算(mobile edge computing, MEC)的通信资源分配优于其他几种对比实验算法。 展开更多
关键词 非正交多址(non-orthogonal multiple access NOMA) 智能反射面(intelligent reflecting surface IRS) 深度确定性策略梯度(deep deterministic policy gradient DDPG)算法 移动边缘计算(mobile edge computing MEC) 能源效率(energy efficiency EE) 系统收益
在线阅读 下载PDF
上一页 1 2 6 下一页 到第
使用帮助 返回顶部