期刊文献+
共找到261,390篇文章
< 1 2 250 >
每页显示 20 50 100
Three-dimensional transformation of magnetization direction and magnetic field component at low latitudes based on vertical relationship 被引量:6
1
作者 He Tao Xiong Sheng-Qing Wang Wan-Yin 《Applied Geophysics》 SCIE CSCD 2022年第1期91-106,145,共17页
The transformation of the magnetization direction and the magnetic fi eld component is one of the important methods in magnetic data processing and transformation,which can be conducted in both wavenumber and spatial ... The transformation of the magnetization direction and the magnetic fi eld component is one of the important methods in magnetic data processing and transformation,which can be conducted in both wavenumber and spatial domains.The transformation method in the wavenumber domain has simpler processing expression and higher processing effi ciency than in the spatial domain;however,they are unstable at low latitude.In this paper,the conclusion that the sum is 0 of two vertical magnetic fi eld components(magnetization inclinations are also perpendicular)in 2D is used for the 3D transformation of the magnetization direction and the magnetic field component.In addition,the transformation method at low latitudes based on vertical relationship(VMT)is proposed,which is an iterative algorithm that converts the transformation of the magnetization direction and the magnetic field component at the low latitude into the high latitude.This method restrains the instability of transformation of constant and variable magnetization direction and magnetic fi eld components in low latitudes.The accuracy,stability,and practicality are verifi ed from synthetic models and real data. 展开更多
关键词 the transformation of magnetization direction and magnetic field component wavenumber domain low latitudes vertical relationship iterative algorithm.
在线阅读 下载PDF
From the Perspective of the Three-dimensional Transformations of Eco-translatology to Analyse Movie Subtitle Translation:A Case Study of Changjin Lake 被引量:1
2
作者 SONG Dan-dan 《Journal of Literature and Art Studies》 2022年第2期143-149,共7页
With the swift development of China’s soft power and the Belt and Road initiative,the cultural interaction between China and the West become more and more frequent.As an art,the film plays a vital role in spreading C... With the swift development of China’s soft power and the Belt and Road initiative,the cultural interaction between China and the West become more and more frequent.As an art,the film plays a vital role in spreading Chinese culture,and meantime,the film also is a significant means of cross-cultural communication,while the movie subtitle is a carrier to convey the film content and inner spirit to the foreigners.The study analyses the movie subtitle translation of Changjin Lake from three-dimensional selection adaptive conversion perspectives through comparing its source target to its translation target to leave a deeper understanding of translation skills and inner Chinese culture,which will further promote the“going out”of Chinese culture. 展开更多
关键词 movie subtitle translation three-dimensional translation Changjin Lake
在线阅读 下载PDF
Ecological Three-Dimensional Cultivation and Digital Development Model of Xinjiashan Specialty Coffee Base
3
作者 Jiangnan WANG Yulian MA +3 位作者 Tingting YANG Caide DUAN Jin'e LI Guangxue YANG 《Plant Diseases and Pests》 2026年第1期22-25,29,共5页
Under the strategic framework of rural revitalization and agricultural modernization, Xinjiashan Specialty Coffee Base, located in Zaotang Village, Lujiang Town, Longyang District, Baoshan City, has been proactively i... Under the strategic framework of rural revitalization and agricultural modernization, Xinjiashan Specialty Coffee Base, located in Zaotang Village, Lujiang Town, Longyang District, Baoshan City, has been proactively investigating innovative models for agricultural development. Through extensive communication and collaboration, this base has established close partnerships with research institutions including Kunming University of Science and Technology, Baoshan University, and Yunnan Academy of Agricultural Sciences, with a commitment to thoroughly exploring the potential for resource recycling and ecological complementarity. An innovative four-in-one three-dimensional integrated planting system incorporating "coffee, bananas, green manure, and bees" has been implemented. Concurrently, technological and digital management strategies have been comprehensively integrated to improve planting efficiency. Under this model, the proportion of specialty coffee attains 71%, and the per-unit yield is 17% greater than that of the conventional planting model. This approach not only substantially enhances economic returns but also promotes the integrated development of ecological and social benefits, offering a valuable practical example and experiential reference for the specialty and sustainable advancement of the coffee industry in comparable regions. 展开更多
关键词 COFFEE three-dimensional planting DIGITALIZATION Ecological cycle Xinjiashan
在线阅读 下载PDF
Research on dynamic three-dimensional terrain correction methods of quantitative inversion for airborne gamma-ray spectrometer
4
作者 He-Xi Wu Wei-Cheng Li +6 位作者 Rui Qiu Chao Xiong Yi-Ming Lyu Yi-Qiang Xing De-Hao Zhang Zong-Shuo Tao Yang Wang 《Nuclear Science and Techniques》 2026年第5期199-214,共16页
Aerial surveys are dynamic and continuous processes,and there are different height distributions of the ground in the measurement area,which leads to problems such as overlapping measurement areas and inaccurate altit... Aerial surveys are dynamic and continuous processes,and there are different height distributions of the ground in the measurement area,which leads to problems such as overlapping measurement areas and inaccurate altitude correction during the survey process.Commonly used terrain correction methods are based on the concept of finite elementization of ground surface radioactive sources,using GPS coordinates,radar altitude,and ground elevation distribution information from aerial surveys,combined with the sourceless efficiency calibration method to construct a response matrix,which is then inverted for surface nuclide content.However,most of the sourceless efficiency calibration methods used are numerical calculations that consider the body detector as a point detector and do not consider the changes in intrinsic detection efficiency under different incident directions of gamma rays.Therefore,when the altitude of the measurement area varies significantly or the flight altitude of the aerial survey is relatively low,such sourceless efficiency calibration method calculations tend to have a large bias,which affects the accuracy of the terrain correction.To address the above problems,this study employs a novel sourceless efficiency calibration method based on the Boolean operation of the ray deposition process and simplifies the traditional body source measurement model to a surface source measurement model to achieve fast and accurate efficiency calibration.Then,through the discretization of the measurement process,the static measurement process is superposed as equivalent to the dynamic measurement process,and the dynamic measurement response matrix is built and optimized based on the calibration method.Finally,the PSO-MLEM algorithm was used to solve the dynamic measurement response matrix to achieve dynamic terrain correction of aerial survey data.Analysis of the Baiyun'ebo test area revealed that,after applying dynamic terrain correction,the inverted anomalies in uranium(eU),thorium(eTh),and potassium(K)concentrations were closer to ground measurements(within 5.72%-30.79%)and exhibited clearer anomaly boundaries compared to traditional height-based corrections.However,owing to the inherent statistical fluctuations and characteristics of matrix inversion,higher measurement values tend to absorb lower ones,potentially enlarging the anomalous regions.Nevertheless,the highanomaly regions after inversion largely coincided with the ground truth validation,demonstrating that the proposed method can effectively correct airborne gamma spectrometry data. 展开更多
关键词 Airborne gamma-ray spectrum Dynamic three-dimensional Terrain correction
在线阅读 下载PDF
Accurate closed-form flutter eigensolutions of three-dimensional composite laminates with shear deformation
5
作者 Dezhuang PAN Yufeng XING 《Chinese Journal of Aeronautics》 2026年第1期230-246,共17页
According to the Mindlin plate theory and the first-order piston theory,this work obtains accurate closed-form eigensolutions for the flutter problem of three-dimensional(3D)rectangular laminated panels.The governing ... According to the Mindlin plate theory and the first-order piston theory,this work obtains accurate closed-form eigensolutions for the flutter problem of three-dimensional(3D)rectangular laminated panels.The governing differential equations are derived by the Hamilton's variational principle,and then solved by the iterative Separation-of-Variable(i SOV)method,which are applicable to arbitrary combinations of homogeneous Boundary Conditions(BCs).However,only the simply-support,clamped and cantilever panels are considered in this work for the sake of clarity.With the closed-form eigensolutions,the flutter frequency,flutter mode and flutter boundary are presented,and the effect of shear deformation and aerodynamic damping on flutter frequencies is investigated.Besides,the relation between panel energy and the work of aerodynamic load is discussed.The numerical comparisons reveal the following.(A)The flutter eigenvalues obtained by the present method are accurate,validated by the Finite Element Method(FEM)and the Galerkin method.(B)When the span-chord ratio is larger than 3,simplifying a 3D panel to 2D(two-dimensional)panel is reasonable and the relative differences of the flutter points predicted by the two models are less than one percent.(C)The reciprocal relationship between the mechanical energy of the panel and the work done by aerodynamic load is verified by using the present flutter eigenvalues and modes,further indicating the high accuracy of the present solutions.(D)The coupling of shear deformation and aerodynamic damping prevents frequency coalescing. 展开更多
关键词 Closed-form eigensolutions The first-order piston theory The Mindlin plate theory three-dimensional panel flutter Separation-of-variable method
原文传递
Integrating Interdisciplinary Learning in Engineering Education:A Three-dimensional Framework for Cultivating Applied Talents Through Project-based Learning
6
作者 Yin Zhang Bin Zhang 《计算机教育》 2026年第3期54-60,共7页
In the rapidly evolving landscape of digital transformation and industrial integration,higher education faces the challenge of cultivating applied talents equipped with interdisciplinary knowledge,engineering skills,a... In the rapidly evolving landscape of digital transformation and industrial integration,higher education faces the challenge of cultivating applied talents equipped with interdisciplinary knowledge,engineering skills,and innovative thinking.Traditional teaching models often fail to bridge the gap between theoretical knowledge and practical application,resulting in passive learning and limited problem-solving capabilities.This paper proposes a three-dimensional integrated teaching model centered on“Information Technology-Domain Knowledge-Outcome Production”(the“2+2+2”credit framework)to address these challenges.Drawing on constructivist theories,Bloom’s Taxonomy,and the CDIO model,the framework uses real projects to drive learning,facilitating the seamless integration of theoretical teaching and practical innovation.The model emphasizes tiered teaching objectives and interdisciplinary pathways,supported by dynamic assessment systems that track students’growth in knowledge,skills,and abilities.Applied in smart health and financial technology domains,this approach enhances students’comprehensive capabilities,aligning educational outcomes with industry demands.This study offers replicable strategies for educational reform in new engineering disciplines,aiming to transform students into proactive innovators and versatile talents. 展开更多
关键词 Interdisciplinary education Problem-based learning(PBL) Project-based learning Engineering education Digital transformation Innovative thinking
在线阅读 下载PDF
Three-dimensional Thermal Network Modeling and Temperature Rise Prediction of Nanocrystalline High-frequency Transformer
7
作者 Baolu Wei Wenliang Zhao +1 位作者 Haibo Ding Haisen Zhao 《CES Transactions on Electrical Machines and Systems》 2025年第4期378-389,共12页
The internal hotspot temperature rise prediction in nanocrystalline high-frequency transformers(nanoHFTs) is essential to ensure reliable operation. This paper presents a three-dimensional thermal network(3DTN) model ... The internal hotspot temperature rise prediction in nanocrystalline high-frequency transformers(nanoHFTs) is essential to ensure reliable operation. This paper presents a three-dimensional thermal network(3DTN) model for epoxy resin encapsulated nano HFTs, which aims to precisely predict the temperature distribution inside the transformer in combination with the finite element method(FEM). A magnetothermal bidirectional coupling 3DTN model is established by analyzing the thermal conduction between the core, windings, and epoxy resin, while also considering the convection and radiation heat transfer mechanisms on the surface of the epoxy resin. The model considers the impact of loss distribution in the core and windings on the temperature field and adopts a simplified 1/2 thermal network model to reduce computational complexity. Furthermore, the results of FEM are compared with experimental results to verify the accuracy of the 3DTN model in predicting the temperature rise of nano HFT. The results show that the 3DTN model reduces errors by an average of 5.25% over the traditional two-dimensional thermal network(2DTN) model, particularly for temperature distributions in the windings and core. This paper provides a temperature rise prediction method for the thermal design and offers a theoretical basis and engineering guidance for the optimization of their thermal management systems. 展开更多
关键词 three-dimensional thermal network(3DTN) Nanocrystalline high-frequency transformer(nanoHFT) Thermal analysis Temperature rise Convection and radiative heat transfer
在线阅读 下载PDF
一种面向地图综合建筑多边形化简的Transformer模型
8
作者 刘鹏程 成晓强 +2 位作者 肖天元 杨敏 艾廷华 《测绘学报》 北大核心 2026年第1期124-137,共14页
针对地图综合中建筑多边形化简方法依赖人工规则、自动化程度低且难以利用已有化简成果的问题,本文提出了一种基于Transformer机制的建筑多边形化简模型。该模型首先把建筑多边形映射至一定范围的网格空间,将建筑多边形的坐标串表达为... 针对地图综合中建筑多边形化简方法依赖人工规则、自动化程度低且难以利用已有化简成果的问题,本文提出了一种基于Transformer机制的建筑多边形化简模型。该模型首先把建筑多边形映射至一定范围的网格空间,将建筑多边形的坐标串表达为网格序列,从而获取建筑多边形化简前后的Token序列,构建出建筑多边形化简样本对数据;随后采用Transformer架构建立模型,基于样本数据利用模型的掩码自注意力机制学习点序列之间的依赖关系,最终逐点生成新的简化多边形,从而实现建筑多边形的化简。在训练过程中,模型使用结构化的样本数据,设计了忽略特定索引的交叉熵损失函数以提升化简质量。试验设计包括主试验与泛化验证两部分。主试验基于洛杉矶1∶2000建筑数据集,分别采用0.2、0.3和0.5 mm 3种网格尺寸对多边形进行编码,实现了目标比例尺为1∶5000与1∶10000的化简。试验结果表明,在0.3 mm的网格尺寸下模型性能最优,验证集上的化简结果与人工标注的一致率超过92.0%,且针对北京部分区域的建筑多边形数据的泛化试验验证了模型的迁移能力;与LSTM模型的对比分析显示,在参数规模相近的条件下,LSTM模型无法形成有效收敛,并生成可用结果。本文证实了Transformer在处理空间几何序列任务中的潜力,且能够有效复用已有化简样本,为智能建筑多边形化简提供了具有工程实用价值的途径。 展开更多
关键词 地图综合 建筑多边形化简 TOKENIZATION transformer模型 上下文工程
在线阅读 下载PDF
融合视觉测量和Transformer的桥梁裂缝智能检测与三维映射
9
作者 余加勇 杨睿韬 +2 位作者 王昱东 彭志豪 周劲 《湖南大学学报(自然科学版)》 北大核心 2026年第3期108-118,共11页
无人机巡检方法已成为桥梁表观病害检测的重要手段.针对无人机(unmanned aerial vehicle,UVA)易受振动干扰、成像质量不稳定、卷积神经网络识别裂缝小目标效果差及裂缝定位困难等问题,提出了融合视觉测量与Transformer的桥梁裂缝智能检... 无人机巡检方法已成为桥梁表观病害检测的重要手段.针对无人机(unmanned aerial vehicle,UVA)易受振动干扰、成像质量不稳定、卷积神经网络识别裂缝小目标效果差及裂缝定位困难等问题,提出了融合视觉测量与Transformer的桥梁裂缝智能检测与三维映射方法,建立基于Real ESRGan图像超分辨率技术的航拍图像采集方法,复原运动模糊图像,实现对高质量桥梁图像的高效采集;在桥梁复杂背景下,通过具有全局注意力机制的Detection Transformer算法和数字图像处理技术,实现对裂缝病害的识别提取与高亮标识;利用多视角影像匹配法处理裂缝高亮标识图片,生成密集点云数据,构建桥梁病害面的精细模型,实现对裂缝病害的三维映射定位.以长沙市靳江河大桥为实验桥梁,使用无人机拍摄2316张桥梁表观图像用于生成三维实景模型,拍摄479张精细图像用于病害检测,使用Real ESRgan超分辨率重建算法对运动模糊图像进行复原,所建立的桥梁病害部位精细模型像素点分辨率达0.25 mm/pixel,裂缝宽度测量最小相对误差为1.37%,最大相对误差为9.90%.结果表明,融合视觉测量和Transformer的桥梁裂缝智能检测与三维映射方法,能够有效提升检测效率,保障人员安全,实现对桥梁裂缝的数字化、智能化、可视化检测,具备重要的研究价值与广阔的应用前景. 展开更多
关键词 桥梁 裂缝检测 无人机 三维建模 transformER
在线阅读 下载PDF
基于CNN-Transformer架构的电磁传播损耗预测算法
10
作者 万勇 李骏杰 +1 位作者 孙伟峰 戴永寿 《现代电子技术》 北大核心 2026年第6期43-48,共6页
为了解决传统经验传播损耗模型预测精度不足的问题,提出一种基于CNN-Transformer架构的电磁传播损耗预测算法,通过构建回归模型进行精准的传播损耗预测。通过斯皮尔曼系数法提取有效特征,利用CNN提取与传播损耗预测高度相关的浅层特征,... 为了解决传统经验传播损耗模型预测精度不足的问题,提出一种基于CNN-Transformer架构的电磁传播损耗预测算法,通过构建回归模型进行精准的传播损耗预测。通过斯皮尔曼系数法提取有效特征,利用CNN提取与传播损耗预测高度相关的浅层特征,将从卫星图像中获取的传播路径上地物特征序列进行位置编码,增强对传播路径中不同地物特征顺序对传播损耗影响的理解。最后将CNN提取的浅层特征与位置编码后的地物特征输入到Transformer模型,通过多头自注意力机制捕捉特征间的全局关联性,从而有效校正传播损耗的预测结果。实验结果表明,所提出的CNN-Transformer方法显著降低了传播损耗预测的均方根误差(RMSE),达到了3.3745 dB,同时保持了0.8956的较高确定性系数(R^(2))。所提的电磁传播损耗预测算法为无线通信传播特性研究领域提供了参考,具有一定的应用价值。 展开更多
关键词 电磁传播 损耗预测 transformER CNN 斯皮尔曼系数法 地物类型 位置编码
在线阅读 下载PDF
基于行列栅格感知Transformer的车道线检测方法
11
作者 陈广秋 刘枫铭 +1 位作者 段锦 黄丹丹 《光学精密工程》 北大核心 2026年第6期953-972,共20页
低光照或光线不均的夜间环境下,道路成像存在车道线可见性低、局部过曝和阴影,现有车道线检测算法多聚焦于提升正常光照环境下的检测能力,忽略了夜间光照环境下的道路特征退化问题,导致算法的精确性和鲁棒性差。针对上述问题,本文在编... 低光照或光线不均的夜间环境下,道路成像存在车道线可见性低、局部过曝和阴影,现有车道线检测算法多聚焦于提升正常光照环境下的检测能力,忽略了夜间光照环境下的道路特征退化问题,导致算法的精确性和鲁棒性差。针对上述问题,本文在编解码语义分割框架下,提出了一种基于行列栅格感知Transformer的车道线检测方法。该方法首先采用光增强曲线模块对输入图像进行光照归一化,通过生成对抗网络实现光照失衡图像到光照分布合理图像的映射,有效抑制噪声与过曝;编码器采用ResNet34网络提取多尺度特征;行列栅格感知Transformer模块通过行、列双向令牌编码显式建模车道线的空间结构与上下文关系,增强模型对几何形变与局部遮挡的鲁棒性;解码器由双边上采样模块与置信度评估模块构成,分别完成特征重建与车道线存在性预测。实验结果表明,本文方法在TuSimple数据集下准确率为96.86%;在CULane数据集下整体场景F1分数为77.5%,其中夜间场景下F1值达到76.7%。本文方法的检测精度优于当前主流车道线检测模型,能有效实现复杂夜间环境下的车道线精准检测。 展开更多
关键词 交通工程 车道线检测 语义分割 transformER 栅格感知
在线阅读 下载PDF
基于BSimilar优化PTransformer的光伏功率短期预测
12
作者 张文广 蔡浩 +1 位作者 刘科 孙盼荣 《动力工程学报》 北大核心 2026年第1期77-84,102,共9页
为提高光伏功率短期预测的精度,提出了考虑光伏设备性能退化因素的相似日算法优化的分时段多通道独立光伏功率短期预测方法。首先,在PTransformer模型中用分时段与通道独立的方法来处理光伏输入数据,以降低空间复杂度及提高长时间数据... 为提高光伏功率短期预测的精度,提出了考虑光伏设备性能退化因素的相似日算法优化的分时段多通道独立光伏功率短期预测方法。首先,在PTransformer模型中用分时段与通道独立的方法来处理光伏输入数据,以降低空间复杂度及提高长时间数据序列的关注度。其次,运用Transformer的编码器模型,通过自身注意力机制捕捉光伏序列特征之间的依赖关系,进行光伏功率的短期预测。最后,运用夹角余弦距离计算相似度并考虑光伏设备性能退化因素确定相似日,利用其功率数据优化PTransformer模型,以改善功率数据的滞后性。结果表明:相比典型的光伏功率短期预测方法,所提方法训练速度更快,预测精准度更高,并且对复杂天气状况下的光伏功率也有较好的预测结果。 展开更多
关键词 光伏功率 短期预测 性能退化 贝叶斯分析 transformER 相似日
在线阅读 下载PDF
Transformer架构驱动下的综采工作面矿压时序特征智能预测
13
作者 杜锋 陈博 +7 位作者 王文强 浦海 杜雪明 李国栋 乔瑞 李鑫磊 徐杰 曹煜 《煤田地质与勘探》 北大核心 2026年第2期1-13,共13页
【背景】矿压预测是顶板灾害预警和管理的重要手段,是智能化矿井安全生产的前提和基础。开采过程中综采工作面环境复杂多变,导致基于电液控制系统采集的支架压力数据分布差异较大,预测困难。【方法】基于Transformer的矿压预测模型,使... 【背景】矿压预测是顶板灾害预警和管理的重要手段,是智能化矿井安全生产的前提和基础。开采过程中综采工作面环境复杂多变,导致基于电液控制系统采集的支架压力数据分布差异较大,预测困难。【方法】基于Transformer的矿压预测模型,使用线性插值填补缺失的矿压值,并使用滑动窗口算法调整训练时的矿压数据结构;针对矿压数据的时序特性,构建融合时序特征的输入序列,利用多头注意力(multi-head-attention)机制动态计算权重,根据数据本身自适应地聚焦关键时间步,从而有效捕捉复杂的非线性时序依赖,显著提升特征表征与预测能力,最后使用迁移学习方法,完成对上、中、下工作面支架工作阻力预测,并搭建基于矿压大数据的智能分析及预测平台。【结果和结论】使用多头注意力机制代替神经网络捕捉全局矿压数据特征,比循环神经网络(recurrent neural network,RNN)和长短期记忆网络(long short-term memory,LSTM)具有更强长序列依赖能力和特征学习能力,能有效降低模型损失,更加适用于预测矿压,Transformer模型在测试集上的均方误差和平均绝对误差损失精度分别达到0.34%和2.57%。Transformer模型也具有较强的泛化能力,使用迁移学习方法微调后,能够有效降低模型损失,在迁移同工作面其他支架时具有更好的泛化效果,Transformer预测模型进一步验证在矿压预测问题的适用性和可行性。平台可视化显示系统可精准分析预测前后的来压次数、推进距离、来压判据和工作面矿压云图等关键参数,为顶板灾害预警乃至其他灾害预警提供新思路,也为矿井安全高效开采与智能化建设奠定了坚实基础。 展开更多
关键词 综采工作面 深度学习 transformer模型 时间序列 矿压显现 矿压预测
在线阅读 下载PDF
基于长短期记忆网络-Transformer模型参数优化的锂离子电池剩余使用寿命预测 被引量:1
14
作者 高建树 郝世宇 党一诺 《汽车工程师》 2026年第1期32-39,共8页
为提高锂离子电池剩余使用寿命(RUL)预测的准确性,提出了一种基于长短期记忆(LSTM)网络-Transformer模型参数优化的RUL预测方法,采用网格搜索法选取模型的超参数,利用LSTM网络提取锂离子电池时间序列中的长短期依赖关系,使用Transforme... 为提高锂离子电池剩余使用寿命(RUL)预测的准确性,提出了一种基于长短期记忆(LSTM)网络-Transformer模型参数优化的RUL预测方法,采用网格搜索法选取模型的超参数,利用LSTM网络提取锂离子电池时间序列中的长短期依赖关系,使用Transformer的自注意力机制处理全局信息并对超参数进行优化,通过全连接层进行最终的寿命预测。基于美国国家航空航天局(NASA)数据集和先进生命周期工程中心(CALCE)数据集的试验验证结果表明,模型在更短的序列长度、更少的隐藏层数量和训练次数等条件下,在多种评价指标上均优于LSTM网络模型、Transformer模型及其他神经网络模型,具有更高的预测精度和鲁棒性。最后,通过不同电池的对比试验进一步验证了模型在不同电池数据上的泛化能力。 展开更多
关键词 锂离子电池 剩余使用寿命预测 参数优化 长短期记忆神经网络 transformER 混合模型
在线阅读 下载PDF
融合群分解与Transformer-KAN的短期风速预测
15
作者 史加荣 张思怡 《南京信息工程大学学报》 北大核心 2026年第1期60-68,共9页
针对风速固有的不稳定性,通过融合群分解(Swarm Decomposition,SWD)、Transformer和Kolmogorov-Arnold网络(KAN),提出一种SWD-Transformer-KAN预测模型.首先,利用SWD对原始风速数据进行分解,以提取关键特征.其次,针对每个被分解的子序列... 针对风速固有的不稳定性,通过融合群分解(Swarm Decomposition,SWD)、Transformer和Kolmogorov-Arnold网络(KAN),提出一种SWD-Transformer-KAN预测模型.首先,利用SWD对原始风速数据进行分解,以提取关键特征.其次,针对每个被分解的子序列,建立Transformer-KAN模型,所建模型充分利用了Transformer的时序处理能力和KAN的非线性逼近能力.最后,对所有子序列的预测结果进行叠加,得到最终的风速预测值.为了验证所提出模型的有效性,将其与其他模型进行实验对比,结果表明,SWD-Transformer-KAN模型具有最优的预测性能,其决定系数(R^(2))高达99.91%. 展开更多
关键词 风速预测 群分解 transformER Kolmogorov-Arnold网络
在线阅读 下载PDF
一种基于时域融合Transformer的4D航迹预测方法
16
作者 孔建国 马珂昕 +2 位作者 梁海军 张向伟 常瀚文 《电讯技术》 北大核心 2026年第1期21-29,共9页
针对传统4D航迹预测方法在数据单一和特征选择上的局限,提出了一种基于时域融合Transformer(Temporal Fusion Transformer,TFT)模型的4D航迹预测方法。引入下降率、时序分量等多元特征,并将数据按是否随时间变化及数值属性进行分类,以... 针对传统4D航迹预测方法在数据单一和特征选择上的局限,提出了一种基于时域融合Transformer(Temporal Fusion Transformer,TFT)模型的4D航迹预测方法。引入下降率、时序分量等多元特征,并将数据按是否随时间变化及数值属性进行分类,以体现飞行过程中不同阶段的差异;采用TFT模型有效捕捉各特征之间的隐式相关性,从而提高了预测精度;同时,结合分位数回归实现不确定性量化,提供了具有置信区间的航迹预测结果。实验表明,所提方法在真实数据上优于传统模型:与CNNLSTM模型和LSTM模型相比,平均距离误差分别减少了22.7%和50.9%,纵向、横向和垂直误差分别为305.01 m、177.91 m和25.23 m,验证了模型在解决航迹预测问题上的有效性,能够为管制精细化调控提供有效支持。 展开更多
关键词 空中交通管制 4D航迹预测 自动相关监视系统数据 时域融合transformer 时间序列预测
在线阅读 下载PDF
自适应Transformer-LSTM的滚动轴承故障预测方法研究
17
作者 董辛旻 职帅轩 崔富源 《重庆理工大学学报(自然科学)》 北大核心 2026年第2期96-104,共9页
针对滚动轴承故障预测中,模型预测精度低、参数难以确定等问题,提出一种自适应Transformer编码器与长短期记忆神经网络(long short-term memory, LSTM)的滚动轴承故障预测方法。提取轴承全周期振动信号24维时频特征,并基于信息熵、鲁棒... 针对滚动轴承故障预测中,模型预测精度低、参数难以确定等问题,提出一种自适应Transformer编码器与长短期记忆神经网络(long short-term memory, LSTM)的滚动轴承故障预测方法。提取轴承全周期振动信号24维时频特征,并基于信息熵、鲁棒性和相关性构建综合指标对特征进行筛选。采用核主元分析将优选特征进行融合,构建能够反应轴承退化状态的退化指标。综合时间序列全局特性与长短期特性,构建Transformer编码器与LSTM结合的故障预测模型,并引入极光优化算法(polar lights optimization, PLO)进行参数自适应寻优,应用XJTU-SY与IMS滚动轴承数据集进行方法分析验证。结果表明:所提模型在轴承故障预测中表现出良好效果,相较于经典的时域卷积网络(temporal convolutional network, TCN)、双向门控循环神经网络(gate recurrent unit, GRU)等,预测精度有较大提升。 展开更多
关键词 滚动轴承 故障预测 数据驱动 transformER 优化算法
在线阅读 下载PDF
FDGformer:基于频域引导Transformer网络的红外小目标检测
18
作者 杜妮妮 叶文亚 +3 位作者 刘烨 卫莎莎 王建超 徐生 《红外技术》 北大核心 2026年第2期204-211,共8页
红外小目标检测旨在从背景复杂的红外图像中检测和识别出尺寸较小的目标,在军事、安防以及无人机等领域有着广泛的应用。该任务的挑战在于红外图像通常分辨率较低、目标对比度低以及纹理模糊,导致小目标很容易被包含噪声和杂波的背景中... 红外小目标检测旨在从背景复杂的红外图像中检测和识别出尺寸较小的目标,在军事、安防以及无人机等领域有着广泛的应用。该任务的挑战在于红外图像通常分辨率较低、目标对比度低以及纹理模糊,导致小目标很容易被包含噪声和杂波的背景中所淹没。因此,如何准确地检测红外小目标的外形信息仍是目前学术界探索的热点问题。为解决上述问题,提出了一种基于频域信息引导Transformer(FDGformer)网络的红外小目标检测算法。首先采用了流行的U-net架构实现目标掩码的生成,在此基础上基于对红外图像不同层级频率域信息的探索,构建了一种基于Transformer结构的频率信息提取(FIE)模块,能够基于频域计算特征的自注意力,从而对输入特征中的特定频率成分进行增强;接着,将得到的频域增强特征作为引导设计了一种频率信息引导的空间Transformer结构,能够同时整合红外特征的全局依赖关系以及频域显著信息,从而更加准确的识别小目标的外形特征。在公开数据集上的实验结果表明,该算法相比其他先进小目标检测算法有着更高的检测精度,同时参数量更少,有效推动检测任务的实际应用。 展开更多
关键词 红外图像 弱小目标检测 transformER 图像分割
在线阅读 下载PDF
基于BiLSTM-Transformer混合模型的丘陵地区履带式甘蔗收获机倾翻风险预测
19
作者 李尚平 宋家华 +3 位作者 文春明 李凯华 韦雨彤 程健华 《农业机械学报》 北大核心 2026年第4期213-223,共11页
针对履带式甘蔗收获机在丘陵地区作业时存在因车身重心高和轮距窄而易发生倾翻危险,且难以预测问题,本文通过样机测试,实时检测样机车架振动加速度变化,经频域处理分析,提取车架倾斜状态时振动特征,提出一种基于双向长短期记忆网络与Tra... 针对履带式甘蔗收获机在丘陵地区作业时存在因车身重心高和轮距窄而易发生倾翻危险,且难以预测问题,本文通过样机测试,实时检测样机车架振动加速度变化,经频域处理分析,提取车架倾斜状态时振动特征,提出一种基于双向长短期记忆网络与Transformer混合模型的倾翻预测方法。通过对振动加速度信号预处理,应用经验模态分解提取倾斜状态的时域与频域特征,重构去噪后信号。利用BiLSTM捕捉长期依赖关系,采用Transformer提取局部时序关系,有效提高了样机倾翻预测准确性。试验结果表明,在不同状态下履带式甘蔗收获机倾翻预测准确率达到95.39%,耗时11.87 ms。为进一步验证倾翻模型效果,对原始数据进行了t-SNE降维可视化,绘制了混淆矩阵图,为复杂环境下甘蔗收获机预警和调平系统的实时控制提供了依据。 展开更多
关键词 丘陵地区 甘蔗收获机 倾翻预测 BiLSTM transformER
在线阅读 下载PDF
上一页 1 2 250 下一页 到第
使用帮助 返回顶部