期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到874篇文章
< 1 2 … 44 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Multi-Kernel Bandwidth Based Maximum Correntropy Extended Kalman Filter for GPS Navigation 认领 引用 被引量：1
1
作者 Amita Biswal Dah-Jing Jwo 《Computer Modeling in Engineering & Sciences》 SCIE EI 2025年第7期927-944,共18页
The extended Kalman filter(EKF)is extensively applied in integrated navigation systems that combine the global navigation satellite system(GNSS)and strap-down inertial navigation system(SINS).However,the performance o... The extended Kalman filter(EKF)is extensively applied in integrated navigation systems that combine the global navigation satellite system(GNSS)and strap-down inertial navigation system(SINS).However,the performance of the EKF can be severely impacted by non-Gaussian noise and measurement noise uncertainties,making it difficult to achieve optimal GNSS/INS integration.Dealing with non-Gaussian noise remains a significant challenge in filter development today.Therefore,the maximum correntropy criterion(MCC)is utilized in EKFs to manage heavytailed measurement noise.However,its capability to handle non-Gaussian process noise and unknown disturbances remains largely unexplored.In this paper,we extend correntropy from using a single kernel to a multi-kernel approach.This leads to the development of a multi-kernel maximum correntropy extended Kalman filter(MKMC-EKF),which is designed to effectively manage multivariate non-Gaussian noise and disturbances.Further,theoretical analysis,including advanced stability proofs,can enhance understanding,while hybrid approaches integrating MKMC-EKF with particle filters may improve performance in nonlinear systems.The MKMC-EKF enhances estimation accuracy using a multi-kernel bandwidth approach.As bandwidth increases,the filter’s sensitivity to non-Gaussian features decreases,and its behavior progressively approximates that of the iterated EKF.The proposed approach for enhancing positioning in navigation is validated through performance evaluations,which demonstrate its practical applications in real-world systems like GPS navigation and measuring radar targets. 展开更多
关键词 Extended Kalman filter maximum correntropy criterion(MCC) multi-kernel maximum correntropy(MKMC) non-Gaussian noise
暂未订购 下载PDF
Lithofacies identi cation using support vector machine based on local deep multi-kernel learning 认领 引用 被引量：21
2
作者 Xing-Ye Liu Lin Zhou +1 位作者 Xiao-Hong Chen Jing-Ye Li 《Petroleum Science》 SCIE CAS CSCD 2020年第4期954-966,共13页
Lithofacies identification is a crucial work in reservoir characterization and modeling.The vast inter-well area can be supplemented by facies identification of seismic data.However,the relationship between lithofacie... Lithofacies identification is a crucial work in reservoir characterization and modeling.The vast inter-well area can be supplemented by facies identification of seismic data.However,the relationship between lithofacies and seismic information that is affected by many factors is complicated.Machine learning has received extensive attention in recent years,among which support vector machine(SVM) is a potential method for lithofacies classification.Lithofacies classification involves identifying various types of lithofacies and is generally a nonlinear problem,which needs to be solved by means of the kernel function.Multi-kernel learning SVM is one of the main tools for solving the nonlinear problem about multi-classification.However,it is very difficult to determine the kernel function and the parameters,which is restricted by human factors.Besides,its computational efficiency is low.A lithofacies classification method based on local deep multi-kernel learning support vector machine(LDMKL-SVM) that can consider low-dimensional global features and high-dimensional local features is developed.The method can automatically learn parameters of kernel function and SVM to build a relationship between lithofacies and seismic elastic information.The calculation speed will be expedited at no cost with respect to discriminant accuracy for multi-class lithofacies identification.Both the model data test results and the field data application results certify advantages of the method.This contribution offers an effective method for lithofacies recognition and reservoir prediction by using SVM. 展开更多
关键词 Lithofacies discriminant Support vector machine Multi-kernel learning Reservoir prediction Machine learning
暂未订购 下载PDF
Nonlinear Model Predictive Control Based on Support Vector Machine with Multi-kernel 认领 引用 被引量：25
3
作者 包哲静 皮道映 孙优贤 《Chinese Journal of Chemical Engineering》 SCIE EI CAS 2007年第5期691-697,共7页
Multi-kernel-based support vector machine （SVM） model structure of nonlinear systems and its specific identification method is proposed, which is composed of a SVM with linear kernel function followed in series by a... Multi-kernel-based support vector machine （SVM） model structure of nonlinear systems and its specific identification method is proposed, which is composed of a SVM with linear kernel function followed in series by a SVM with spline kernel function. With the help of this model, nonlinear model predictive control can be transformed to linear model predictive control, and consequently a unified analytical solution of optimal input of multi-step-ahead predictive control is possible to derive. This algorithm does not require online iterative optimization in order to be suitable for real-time control with less calculation. The simulation results of pH neutralization process and CSTR reactor show the effectiveness and advantages of the presented algorithm. 展开更多
关键词 nonlinear model predictive control support vector machine with multi-kernel nonlinear system identification kernel function
暂未订购 下载PDF
Multi-channel differencing adaptive noise cancellation with multi-kernel method 认领 引用 被引量：1
4
作者 Wei Gao Jianguo Huang Jing Han 《Journal of Systems Engineering and Electronics》 SCIE CSCD 2015年第3期421-430,共10页
Although a various of existing techniques are able to improve the performance of detection of the weak interesting sig- nal, how to adaptively and efficiently attenuate the intricate noises especially in the case of n... Although a various of existing techniques are able to improve the performance of detection of the weak interesting sig- nal, how to adaptively and efficiently attenuate the intricate noises especially in the case of no available reference noise signal is still the bottleneck to be overcome. According to the characteristics of sonar arrays, a multi-channel differencing method is presented to provide the prerequisite reference noise. However, the ingre- dient of obtained reference noise is too complicated to be used to effectively reduce the interference noise only using the clas- sical linear cancellation methods. Hence, a novel adaptive noise cancellation method based on the multi-kernel normalized least- mean-square algorithm consisting of weighted linear and Gaussian kernel functions is proposed, which allows to simultaneously con- sider the cancellation of linear and nonlinear components in the reference noise. The simulation results demonstrate that the out- put signal-to-noise ratio （SNR） of the novel multi-kernel adaptive filtering method outperforms the conventional linear normalized least-mean-square method and the mono-kernel normalized least- mean-square method using the realistic noise data measured in the lake experiment. 展开更多
关键词 adaptive noise cancellation multi-channel differencing multi-kernel learning array signal processing.
暂未订购 下载PDF
基于Multi-kernel和KRR的数据还原算法 认领 引用 被引量：1
5
作者 刘剑 龚志恒 吴成东 《控制与决策》 EI CSCD 北大核心 2014年第5期821-826,共6页
由于数据被核化后不能还原,使核方法的应用受到局限.对此,提出一种基于Multi-kernel和KRR的数据还原算法.首先,通过同类数据中已知数据进行多次核化迭代,使已知数据在超高维欧氏空间中呈线性;然后,利用已知数据对同类未知数据进行线性表... 由于数据被核化后不能还原,使核方法的应用受到局限.对此,提出一种基于Multi-kernel和KRR的数据还原算法.首先,通过同类数据中已知数据进行多次核化迭代,使已知数据在超高维欧氏空间中呈线性;然后,利用已知数据对同类未知数据进行线性表示,并以Kernel ridge regression(KRR)算法进行未知数据的回归;最后实现数据还原.选取Iris flower和JAFFE两类数据集进行还原实验,实验结果表明,所提出的算法可以有效地还原未知数据,而且在其他领域的应用也有较好的效果. 展开更多
关键词 多核 数据还原 核岭回归 迭代 超高维欧氏空间
暂未订购 下载PDF
Multi-kernel Collaborative Graph Convolution Neural Network for Operational Reliability Assessment Considering Varying Topologies 认领 引用
6
作者 Xinyu Liu Maosheng Gao +2 位作者 Juan Yu Zhifang Yang Wenyuan Li 《Journal of Modern Power Systems and Clean Energy》 SCIE EI CSCD 2026年第1期187-198,共12页
Operational reliability assessment (ORA),which evaluates the risk level of power systems,is hindered by accumulated computational burdens and thus cannot meet the demands of real-time assessment.Recently,data-driven m... Operational reliability assessment (ORA),which evaluates the risk level of power systems,is hindered by accumulated computational burdens and thus cannot meet the demands of real-time assessment.Recently,data-driven methods with fast calculation speeds have emerged as a research focus for online ORA.However,the diverse contingencies of transformers,power lines,and other components introduce numerous topologies,posing significant challenges to the learning capabilities of neural networks.To this end,this paper proposes a multi-kernel collaborative graph convolution neural network (GCNN) for ORA considering varying topologies.Specifically,a physics law-informed graph convolution kernel derived from the Gaussian-Seidel iteration is introduced.It effectively aggregates node features across different topologies.By integrating additional advanced graph convolution kernels with a novel self-attention mechanism,the multi-kernel collaborative GCNN is constructed,which enables the extraction of diverse features and the construction of representative node feature vectors,thereby facilitating high-precision reliability assessments.Furthermore,to enhance the robustness of multi-kernel collaborative GCNN,the inherent pattern of the load-shedding model is analyzed and utilized to design a specialized supervised loss function,which allows the neural network to explore a broader feature space.Compared with the existing data-driven methods,the multi-kernel collaborative GCNN,combined with supervised exploration,can accommodate a wider range of contingencies and achieve superior assessment accuracy. 展开更多
关键词 Reliability assessment multi-kernel collaborative design self-attention graph convolution neural network(GCNN) topology
An AUC-based multi-kernel weighted support vector machine ensemble algorithm for breast cancer diagnosis 认领 引用
7
作者 Mushuang Cheng Lintong Liu +1 位作者 Haixiang Lin Guoqiang Wang 《Statistical Theory and Related Fields》 CSCD 2026年第2期251-267,共17页
Machine learning algorithms have demonstrated outstanding performance for disease diagnosis.Kernel function selection plays a crucial role in effectively transforming the nonlinear nature of input data.To enhance brea... Machine learning algorithms have demonstrated outstanding performance for disease diagnosis.Kernel function selection plays a crucial role in effectively transforming the nonlinear nature of input data.To enhance breast cancer diagnosis,we propose a novel ensemble algorithm,namely,AUC-Ada-L1 MKL-WSVM,which integrates Weighted Support Vector Machines(WSVM),AdaBoost,and Multi-Kernel Learning(MKL).This ensemble algorithm introduces two main innovations.First,it simultaneously updates the weights of training samples and the combined kernel function during classification.Second,it incorporates an AUC-based approach to adjust training sample weights,effectively controlling the growth rate of misclassified sample weights in AdaBoost.Experimental results are provided to demonstrate the effectiveness of our method,which achieves an AUC score of 97.21%and an accuracy of 97.64%on the WDBC dataset,and an AUC of 97.53%and an accuracy of 97.46%on the WBC dataset.Comparative analysis further confirms that our ensemble algorithm outperforms four benchmark models in classification accuracy. 展开更多
关键词 Weighted support vector machine breast cancer diagnosis ensemble algorithm multi-kernel learning AdaBoost
An Ensemble Approach for Emotion Cause Detection with Event Extraction and Multi-Kernel SVMs 认领 引用 被引量：10
8
作者 Ruifeng Xu Jiannan Hu +2 位作者 Qin Lu Dongyin Wu Lin Gui 《Tsinghua Science and Technology》 SCIE EI CAS CSCD 2017年第6期646-659,共14页
In this paper, we present a new challenging task for emotion analysis, namely emotion cause extraction.In this task, we focus on the detection of emotion cause a.k.a the reason or the stimulant of an emotion, rather t... In this paper, we present a new challenging task for emotion analysis, namely emotion cause extraction.In this task, we focus on the detection of emotion cause a.k.a the reason or the stimulant of an emotion, rather than the regular emotion classification or emotion component extraction. Since there is no open dataset for this task available, we first designed and annotated an emotion cause dataset which follows the scheme of W3 C Emotion Markup Language. We then present an emotion cause detection method by using event extraction framework,where a tree structure-based representation method is used to represent the events. Since the distribution of events is imbalanced in the training data, we propose an under-sampling-based bagging algorithm to solve this problem. Even with a limited training set, the proposed approach may still extract sufficient features for analysis by a bagging of multi-kernel based SVMs method. Evaluations show that our approach achieves an F-measure 7.04%higher than the state-of-the-art methods. 展开更多
关键词 emotion cause detection event extraction multi-kernel SVMs bagging
暂未订购 下载PDF
智慧电厂区域门禁内多模态生物特征识别仿真 认领 引用 被引量：2
9
作者 孙中华 陈峰 王鲁君 《计算机仿真》 2026年第2期210-214,共5页
在智慧电厂门禁场景中,受化学腐蚀干扰与瞳孔动态调节的耦合作用,使得工人指纹磨损程度与虹膜反光强度的时变非线性关系,忽略多模态间时变相关性,会导致识别准确率较低。为此,提出一种智慧电厂区域门禁多模态生物特征识别方法。采集虹... 在智慧电厂门禁场景中,受化学腐蚀干扰与瞳孔动态调节的耦合作用,使得工人指纹磨损程度与虹膜反光强度的时变非线性关系,忽略多模态间时变相关性,会导致识别准确率较低。为此,提出一种智慧电厂区域门禁多模态生物特征识别方法。采集虹膜和结构光指纹,基于分类距离分数的特征融合算法,计算各生物特征样本的匹配度评分,获取指纹与虹膜特征间的关联系数与特征权重系数,实现多模态生物特征自适应融合;通过引入间隔约束多核学习方法,将融合后的多模态生物特征映射至高维空间,有效解决电厂环境下因化学腐蚀和强光辐射导致的时变特征退化问题,推算生物融合特征数据的高维核函数,明确不同模态特征的时变相关性,采用支持向量机算法完成多模态生物特征识别。实验结果表明,所提方法多模态生物特征识别准确率高,显著提升了复杂环境下的识别鲁棒性。 展开更多
关键词 智慧电厂 门禁管理 多模态识别 生物特征 多核学习
暂未订购 下载PDF
Multi-kernel dictionary learning for classifying maize varieties 认领 引用 被引量：2
10
作者 Hua Zhu Jun Yue +1 位作者 Zhenbo Li Zhiwang Zhang 《International Journal of Agricultural and Biological Engineering》 SCIE 2018年第3期183-189,共7页
The automatic classification and identification of maize varieties is one of the important research contents in agriculture.A multi-kernel maize varieties classification approach was proposed in this paper in order to... The automatic classification and identification of maize varieties is one of the important research contents in agriculture.A multi-kernel maize varieties classification approach was proposed in this paper in order to improve the recognition rate of maize varieties.In this approach,four kinds of maize varieties were selected,in each variety 200 grains were selected randomly as the samples,and in each sample 160 grains were taken as the training samples randomly;the characteristics of maize grain were extracted as the typical characteristics to distinguish maize varieties,by which the dictionary required by K-SVD was constructed;for the test samples,the feature-matrixes were extracted by dimension reduction method which were mapped to the high-dimension space by muti-kernel function mapping.The high-dimension characteristic matrixes were trained by K-SVD method and the corresponding feature dictionary was obtained respectively.Finally,the test samples representing were trained and classified by l2,1 minimization sparse coefficient.The experiment results showed that recognition rate was improved obviously through this approach,and the poor-effect to maize variety identification from partial occlusion can be eliminated effectively. 展开更多
关键词 multi-kernel sparse representation dictionary learning maize classification
多尺度核随机配置网络的多目标回归算法 认领 引用
11
作者 代伟 吴尚 +1 位作者 南静 刘鑫 《控制理论与应用》 EI CAS CSCD 北大核心 2026年第4期915-926,共12页
多目标回归通过将多个回归任务的相关性纳入建模中以提高模型表现,但是当前方法对于多目标内在更加普遍且复杂的非线性结构关系建模效果并不理想.本文提出多尺度核随机配置网络(MSK-SCN)构建高维输入与多目标之间的映射以及多目标内在... 多目标回归通过将多个回归任务的相关性纳入建模中以提高模型表现,但是当前方法对于多目标内在更加普遍且复杂的非线性结构关系建模效果并不理想.本文提出多尺度核随机配置网络(MSK-SCN)构建高维输入与多目标之间的映射以及多目标内在的非线性关系.通过设计隔离建模机制,使得每个子模型根据其负责的目标误差状态完成隐含层参数配置,进而避免多个回归任务共享模型参数导致建模质量下降;建立多尺度核空间,利用不同尺度参数的核函数将低维空间数据映射到高维特征空间以增强数据的表达能力,进而提高模型挖掘多目标间非线性关系的能力.基于虚拟数据集和真实数据集进行实验验证,结果表明MSK-SCN的表现优于当前的多目标算法,证实了其在多目标回归问题上的有效性. 展开更多
关键词 随机配置网络 多目标回归 多核学习 多尺度核
暂未订购 下载PDF
融合先验特征与多核残差注意力网络的矿尘浓度图像识别模型 认领 引用
12
作者 徐剑坤 苏毅 +4 位作者 王和堂 王恩元 李阳 王珂 徐玉姣 《中国矿业大学学报》 EI CAS CSCD 北大核心 2026年第2期419-434,共16页
矿尘浓度实时可靠检测是保障煤矿安全生产的关键问题.针对现有基于图像的矿尘浓度检测方法存在可解释性差、准确性不高等问题,本文提出一种融合先验特征与可解释多核残差注意力网络的矿尘浓度图像识别模型.首先,构建涵盖颜色、纹理、几... 矿尘浓度实时可靠检测是保障煤矿安全生产的关键问题.针对现有基于图像的矿尘浓度检测方法存在可解释性差、准确性不高等问题,本文提出一种融合先验特征与可解释多核残差注意力网络的矿尘浓度图像识别模型.首先,构建涵盖颜色、纹理、几何等多维特征的图像特征库,结合皮尔逊相关系数与互信息系数,筛选出与矿尘浓度显著相关的线性和非线性可解释特征子集;进而,设计多核学习框架,采用径向基核函数分别映射线性与非线性特征,通过加权融合策略兼顾特征表达能力与可解释性;引入残差连接促进梯度传播,结合通道注意力机制实现关键图像特征的动态强化,提升模型对复杂井下环境的适应性.结果表明:模型在数据集上性能表现优异,均方误差(EMSE)、平均绝对误差(EMAE)和平均相对误差(EMRE)分别达到0.90 mg2/m6,0.74 mg/m3和1.76%,拟合优度R2为0.9160,显著优于支持向量机回归、随机森林等对比模型.消融试验验证了多核融合、残差结构与注意力机制对模型性能的提升贡献.本研究实现了模型可解释性与识别准确性的统一,为矿井粉尘浓度的智能检测提供了一种可靠、透明的高精度解决方案,对提升煤矿安全监测水平具有重要意义. 展开更多
关键词 矿尘浓度 图像识别 先验特征 深度学习 多核学习 注意力机制
暂未订购 下载PDF
基于VMD与MKCNN的固定式架车机齿轮箱故障分类方法 认领 引用
13
作者 李愿望 付亚超 +3 位作者 贾晓宏 史时喜 张建华 宋国义 《铁道标准设计》 北大核心 2026年第4期202-210,共9页
旨在解决固定式架车机齿轮箱故障分类中因原始振动信号信噪比低、振动信号特征提取困难而导致的分类准确度不足问题。提出一种融合变分模态分解(Variational Mode Decomposition,VMD)与多核卷积神经网络(Multi-Kernel Convolutional Neu... 旨在解决固定式架车机齿轮箱故障分类中因原始振动信号信噪比低、振动信号特征提取困难而导致的分类准确度不足问题。提出一种融合变分模态分解(Variational Mode Decomposition,VMD)与多核卷积神经网络(Multi-Kernel Convolutional Neural Network,MKCNN)的新型故障分类方法。首先,利用VMD算法对原始振动信号进行分解,将其转化为多个固有模态函数(Intrinsic Mode Function,IMF),有效提取信号中的关键频率和模态信息,并通过重构IMF显著提升信号的信噪比,减少噪声对特征识别的干扰。随后,构建基于MKCNN的故障分类模型,该模型通过多核函数提取信号特征,实现特征的多尺度分析,并自动学习故障特征间的内在关联,以增强分类性能。试验结果表明,VMD信号重构方法能够有效分离出原始信号中的有用模态分量,显著提高重构信号的信噪比。与单核卷积神经网络(CNN)相比,MKCNN模型在故障分类中展现出更高的精度,故障分类模型的分类准确率提升至95%以上。 展开更多
关键词 架车机 信号重构 故障 分类 多核卷积神经网络
暂未订购 下载PDF
LDD-YOLO:改进YOLOv8的轻量级密集行人检测算法 认领 引用 被引量：4
14
作者 杨迪 张喜龙 王鹏 《计算机科学与探索》 CSCD 北大核心 2026年第1期251-265,共15页
针对当前行人检测算法在密集场景中由于遮挡和尺度变化导致的漏检、误检,以及模型计算复杂度高等问题,提出了一种基于YOLOv8的轻量级密集行人检测方法(LDD-YOLO),以实现检测效率与精度的平衡。设计了一种重参数化层聚合网络RELAN,融合... 针对当前行人检测算法在密集场景中由于遮挡和尺度变化导致的漏检、误检,以及模型计算复杂度高等问题,提出了一种基于YOLOv8的轻量级密集行人检测方法(LDD-YOLO),以实现检测效率与精度的平衡。设计了一种重参数化层聚合网络RELAN,融合了重参数化卷积和多分支结构,分别在训练阶段和推理阶段强化特征表达能力与模型推理效率。引入了分离式大卷积核注意力机制的空间金字塔池化模块SPPF-LSKA,结合分离式大卷积核操作以扩大感受野,增强对密集目标的特征捕获能力,抑制背景干扰。为解决YOLOv8在特征处理中未能充分挖掘局部与全局信息的局限性,提出了一种改进的多尺度特征融合模块FFDM,通过融合多尺度特征信息,提升模型密集行人检测的特征表达能力。设计了一种轻量化的特征对齐检测头LSCSBD,利用不同特征层级之间的共享卷积层,提高参数利用效率并减少冗余计算。在CrowdHuman与WiderPerson数据集上的对比实验结果表明,LDD-YOLO在总体性能上优于对比模型,实现了精度与效率的平衡。 展开更多
关键词 密集行人检测 YOLO 重参数化 可分离大核注意力机制 多尺度特征融合 轻量化
暂未订购 下载PDF
基于多任务孪生核矩阵机的机械故障诊断方法 认领 引用
15
作者 潘海洋 陈春安 +2 位作者 郑近德 童靳于 程健 《机械工程学报》 EI CAS CSCD 北大核心 2026年第9期191-200,共10页
在进行机械设备多目标诊断时,往往需要建立多个具有独立性的单任务模型,其忽略了多目标任务间的关联性信息,致使诊断模型不准确。基于此,提出了一种基于多任务孪生核矩阵机(Multi-task twin kernel matrix machine,MTTKMM)的机械故障诊... 在进行机械设备多目标诊断时,往往需要建立多个具有独立性的单任务模型,其忽略了多目标任务间的关联性信息,致使诊断模型不准确。基于此,提出了一种基于多任务孪生核矩阵机(Multi-task twin kernel matrix machine,MTTKMM)的机械故障诊断方法。在MTTKMM中,首先设计核增强项,实现对多任务间数据的同步处理,有助于挖掘不同任务间的关联性特征,从而提高模型利用共性信息的能力;然后,利用内置偏移量描述数据间的非线性关系,使模型在处理多目标数据时更具灵活性,提高模型分类的稳定性;最后,考虑不同任务间数据具有较大差异问题,设计了泛化损失项,优化模型在多任务数据间的拟合能力,减少过拟合现象。为了验证MTTKMM在多任务机械故障诊断中的有效性,采用滚动轴承、齿轮等数据集进行实验验证,实验结果表明:MTTKMM在多目标诊断中具有优越的分类性能。 展开更多
关键词 故障诊断 多任务孪生核矩阵机 多任务学习 滚动轴承 齿轮
暂未订购 下载PDF
一种结合多小波核卷积层与DCN-BiGRU的域适应滚动轴承故障诊断方法 认领 引用
16
作者 董绍江 吕智明 +2 位作者 朱孙科 罗家元 孙世政 《振动工程学报》 EI CSCD 北大核心 2026年第6期1827-1835,共9页
针对传统故障诊断方法在变工况与噪声干扰下难以有效提取信号有用特征的问题,提出了一种首层多小波核卷积层结合双路卷积(dual path convolution,DCN)和双向门控循环单元(bidirectional gated recurrent unit,BiGRU)的域适应故障诊断方... 针对传统故障诊断方法在变工况与噪声干扰下难以有效提取信号有用特征的问题,提出了一种首层多小波核卷积层结合双路卷积(dual path convolution,DCN)和双向门控循环单元(bidirectional gated recurrent unit,BiGRU)的域适应故障诊断方法。通过多小波核卷积的多级动态感受野提取振动信号的时频域特征,并通过自适应加权策略动态地为不同通道分配权重,完成自适应加权融合;利用DCN和BiGRU挖掘样本的多频多尺度和时空特征;将最大均方差异(MMSD)与对数相关对齐(logCORAL)结合起来作为度量融合差异(MFD)来增强域混淆;在公开滚动轴承数据集与实际滚动轴承数据集上进行对比试验验证,证明了所提方法的有效性及优越性。 展开更多
关键词 滚动轴承故障诊断 多小波核卷积层 自适应加权 度量融合差异
暂未订购 下载PDF
基于异常数据特征高斯-拉普拉斯多核融合的GNSS干扰影响区划分方法 认领 引用
17
作者 何炜琨 席越 陈敏 《信号处理》 CSCD 北大核心 2026年第8期1273-1288,共16页
全球导航卫星系统(Global Navigation Satellite System,GNSS)作为现代航空运输体系的关键基础设施,其易受到干扰的特性可能造成航班延误、运行效率下降等问题,威胁航空飞行的安全。本文利用接收的广播式自动相关监视(Automatic Depende... 全球导航卫星系统(Global Navigation Satellite System,GNSS)作为现代航空运输体系的关键基础设施,其易受到干扰的特性可能造成航班延误、运行效率下降等问题,威胁航空飞行的安全。本文利用接收的广播式自动相关监视(Automatic Dependent Surveillance-Broadcast,ADS-B)数据,针对当前需求,提出一种基于ADS-B异常数据特征高斯-拉普拉斯多核融合方法,以实现对GNSS干扰影响区的划分。为提取异常数据,本文重点分析了受GNSS干扰的ADS-B数据在导航质量指标与航迹信息方面的变化特征,基于此特征识别异常数据进而获取对应航班的完整航迹信息,构建用于分析干扰影响区的数据集。本文所提方法采用高斯核与拉普拉斯核密度估计加权求和的思想构建多核融合算法,兼顾了数据间局部分布与中远距离分布的特征,能够自适应地捕捉数据的多尺度特征与结构关系。基于提取的异常数据,利用所提多核融合算法对网格化划分后的空域单元进行分析,定量评估各网格单元的异常风险系数,并通过与预设阈值进行对比,实现对干扰影响区的识别与划分。此外,本文还系统分析了核函数权重、核函数带宽等关键参数对干扰影响区划分结果的影响。实验结果表明,本文所提多核融合的核密度估计方法在整体性能上的表现优于单一核密度估计方法,可协助空管部门定位受干扰的空域范围,及时启动应对和缓解措施,为航空领域应对GNSS干扰提供了技术支持。 展开更多
关键词 全球导航卫星系统 干扰影响区分析 广播式自动相关监视 异常数据分析 多核融合
暂未订购 下载PDF
基于平面核感知与多尺度结构嵌入的刚性罐道故障诊断 认领 引用
18
作者 苏树智 徐志龙 +2 位作者 马天兵 朱彦敏 李长鹏 《科学技术与工程》 EI 北大核心 2026年第11期4669-4679,共11页
矿井提升系统中,刚性罐道的故障诊断对于保障设备运行安全具有重要意义。传统基于一维振动信号的分析方法在处理非线性、高维度且噪声干扰强的信号时,存在特征提取能力不足、空间结构信息丢失以及诊断精度不高等问题,难以适应复杂工况... 矿井提升系统中,刚性罐道的故障诊断对于保障设备运行安全具有重要意义。传统基于一维振动信号的分析方法在处理非线性、高维度且噪声干扰强的信号时,存在特征提取能力不足、空间结构信息丢失以及诊断精度不高等问题,难以适应复杂工况下的实际需求。针对这些问题,提出了一种基于平面核感知与多尺度结构嵌入(planar kernel perception and multi-scale structural embedding,PKP-MSSE)的刚性罐道故障诊断方法。该方法引入基于核映射的相似性建模与多尺度结构嵌入机制,构建能够同时表征样本局部与全局几何关系的多尺度核空间结构表达,从而增强对非线性高维特征的提取能力;同时通过在平面图像的两个方向上提取判别性特征,有效保留空间结构信息,避免传统方法中因向量化处理带来的结构丢失;最后,联合优化局部保持与全局散度目标函数,在实现有效降维的同时提升故障识别精度。实验结果表明,PKP-MSSE在刚性罐道模拟实验数据集上表现出优异的识别率和鲁棒性,具有优秀的抗噪能力。该方法有效增强了故障特征的类可分性,为刚性罐道的故障识别提供了可靠手段。 展开更多
关键词 故障诊断 核感知 多尺度结构嵌入 刚性罐道 特征提取
暂未订购 下载PDF
MSCNet:多尺度级联编码与动态空间上下文增强的冠状动脉分割网络 认领 引用
19
作者 曾安 程贤航 +1 位作者 潘丹 叶嘉宇 《生物医学工程学杂志》 EI CAS 北大核心 2026年第3期479-486,共8页
冠状动脉分割是冠心病临床诊断的关键环节。针对冠脉血管细小复杂以及计算机断层扫描血管造影影像前景-背景失衡导致的分割断裂、误分割问题,本文提出多尺度级联编码与动态空间上下文增强的冠状动脉分割网络——MSCNet。该网络以Swin Tr... 冠状动脉分割是冠心病临床诊断的关键环节。针对冠脉血管细小复杂以及计算机断层扫描血管造影影像前景-背景失衡导致的分割断裂、误分割问题,本文提出多尺度级联编码与动态空间上下文增强的冠状动脉分割网络——MSCNet。该网络以Swin Transformer与大核卷积构建多尺度级联编码器,通过远距离依赖与局部细节依次建模融合多尺度特征,结合空间频率矩阵实现大核卷积重参数化以强化细节捕捉;同时设计空间转换器模块,动态指导多头注意力学习以优化解码性能。在ImageCAS数据集上,MSCNet平均Dice系数达81.24%,较3D UX-Net、SwinUNETR、SegMamba分别提升3.57%、3.78%、3.85%,可有效提升冠脉分割精度,为临床评估提供支撑。 展开更多
关键词 冠状动脉疾病 分割 多尺度级联 大核卷积 空间频率矩阵 重参数化
暂未订购 下载PDF
基于机车构架动力学响应的轮径差智能识别方法 认领 引用
20
作者 谢博 牙爽东 +2 位作者 马久明 蒋常升 伍四海 《中国工程机械学报》 北大核心 2026年第1期172-177,共6页
针对铁路机车轮径差威胁列车运行安全,且在运营过程中难以准确识别的问题,提出基于构架多通道振动响应的轮径差类型智能识别方法。该方法首先结合变分模态分解(VMD)与奇异值分解(SVD)在信号分解、深度特征提取等方面的优势,将信号分解... 针对铁路机车轮径差威胁列车运行安全,且在运营过程中难以准确识别的问题,提出基于构架多通道振动响应的轮径差类型智能识别方法。该方法首先结合变分模态分解(VMD)与奇异值分解(SVD)在信号分解、深度特征提取等方面的优势,将信号分解为多个固有模态分量(IMF)后提取各分量奇异值特征,充分挖掘多通道信号的潜在特征信息;然后通过构建核极限学习机(KELM)识别模型,将多通道特征向量作为模型输入,实现轮径差类型的智能识别。通过动力学仿真分析和现场试验,验证提出的轮径差类型识别方法的有效性。实验结果表明:所提方法在仿真不同组合工况场景和实测数据分析中,均可实现95%以上的高精度诊断,验证了本文所提方法的有效性和优势,可为机车轮径差的车载检测方法研究提供基础。 展开更多
关键词 铁路机车安全 轮径差 多通道数据融合 核极限学习机 智能识别
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 44 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈