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489篇文章
< 1 2 … 25 >
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：
Numerical simulation of the fluid and flexible rods interaction using a semi-resolved coupling model promoted by anisotropic Gaussian kernel function 认领 引用
1
作者 Caiping Jin Jingxin Zhang Yonglin Sun 《Theoretical & Applied Mechanics Letters》 EI CAS CSCD 2025年第1期5-8,共4页
The numerical simulation of the fluid flow and the flexible rod(s)interaction is more complicated and has lower efficiency due to the high computational cost.In this paper,a semi-resolved model coupling the computatio... The numerical simulation of the fluid flow and the flexible rod(s)interaction is more complicated and has lower efficiency due to the high computational cost.In this paper,a semi-resolved model coupling the computational fluid dynamics and the flexible rod dynamics is proposed using a two-way domain expansion method.The gov-erning equations of the flexible rod dynamics are discretized and solved by the finite element method,and the fluid flow is simulated by the finite volume method.The interaction between fluids and solid rods is modeled by introducing body force terms into the momentum equations.Referred to the traditional semi-resolved numerical model,an anisotropic Gaussian kernel function method is proposed to specify the interactive forces between flu-ids and solid bodies for non-circle rod cross-sections.A benchmark of the flow passing around a single flexible plate with a rectangular cross-section is used to validate the algorithm.Focused on the engineering applications,a test case of a finite patch of cylinders is implemented to validate the accuracy and efficiency of the coupled model. 展开更多
关键词 Semi-resolved coupling model Two-way domain expansion method Anisotropic Gaussian kernel function Flexible rod(s)
暂未订购 下载PDF
Online outcome weighted learning with varying Gaussians and non-identical distributions 认领 引用
2
作者 YANG Ao-li FAN Jun XIANG Dao-hong 《Applied Mathematics(A Journal of Chinese Universities)》 SCIE CSCD 2026年第2期480-508,共29页
Outcome weighted learning is one of the most promising data-driven methods developed for estimating optimal individualized treatment rules(ITR) in precision medicine by reweighting outcomes based on observed data. Thi... Outcome weighted learning is one of the most promising data-driven methods developed for estimating optimal individualized treatment rules(ITR) in precision medicine by reweighting outcomes based on observed data. This paper proposes a fully regularized online outcome weighted learning(ROOWL) algorithm to tackle sequential, independent but nonidentically distributed data in precision medicine. We consider a time-varying Gaussian kernel to enhance flexibility in dynamic environments, and a time-varying regularization parameter to better adapt to evolving data. Its generalization ability evaluated by the excess value function is studied for commonly used loss functions, including hinge loss, generalized DWD loss,least square loss, and q-norm SVM loss. Fast learning rates are derived under smoothness or geometric noise conditions on the target function for a broad class of loss functions. 展开更多
关键词 online learning outcome weighted learning varying Gaussian kernels sampling with non-identical distributions convergence rates
暂未订购 下载PDF
Non-iterative Cauchy kernel-based maximum correntropy cubature Kalman filter for non-Gaussian systems 认领 引用 被引量：3
3
作者 Aastha Dak Rahul Radhakrishnan 《Control Theory and Technology》 EI CSCD 2022年第4期465-474,共10页
This article addresses the nonlinear state estimation problem where the conventional Gaussian assumption is completely relaxed.Here,the uncertainties in process and measurements are assumed non-Gaussian,such that the ... This article addresses the nonlinear state estimation problem where the conventional Gaussian assumption is completely relaxed.Here,the uncertainties in process and measurements are assumed non-Gaussian,such that the maximum correntropy criterion(MCC)is chosen to replace the conventional minimum mean square error criterion.Furthermore,the MCC is realized using Gaussian as well as Cauchy kernels by defining an appropriate cost function.Simulation results demonstrate the superior estimation accuracy of the developed estimators for two nonlinear estimation problems. 展开更多
关键词 Maximum correntropy criterion Cubature Kalman filter Non-Gaussian noise Cauchy kernel Gaussian kernel
Theoretical convergence analysis of complex Gaussian kernel LMS algorithm 认领 引用 被引量：1
4
作者 Wei Gao Jianguo Huang +1 位作者 Jing Han Qunfei Zhang 《Journal of Systems Engineering and Electronics》 SCIE CSCD 2016年第1期39-50,共12页
With the vigorous expansion of nonlinear adaptive filtering with real-valued kernel functions,its counterpart complex kernel adaptive filtering algorithms were also sequentially proposed to solve the complex-valued no... With the vigorous expansion of nonlinear adaptive filtering with real-valued kernel functions,its counterpart complex kernel adaptive filtering algorithms were also sequentially proposed to solve the complex-valued nonlinear problems arising in almost all real-world applications.This paper firstly presents two schemes of the complex Gaussian kernel-based adaptive filtering algorithms to illustrate their respective characteristics.Then the theoretical convergence behavior of the complex Gaussian kernel least mean square(LMS)algorithm is studied by using the fixed dictionary strategy.The simulation results demonstrate that the theoretical curves predicted by the derived analytical models consistently coincide with the Monte Carlo simulation results in both transient and steady-state stages for two introduced complex Gaussian kernel LMS algonthms using non-circular complex data.The analytical models are able to be regard as a theoretical tool evaluating ability and allow to compare with mean square error(MSE)performance among of complex kernel LMS(KLMS)methods according to the specified kernel bandwidth and the length of dictionary. 展开更多
关键词 nonlinear adaptive filtering complex Gaussian kernel convergence analysis non-circular data kernel least mean square(KLMS).
暂未订购 下载PDF
Gaussian Kernel Based SVR Model for Short-Term Photovoltaic MPP Power Prediction 认领 引用 被引量：1
5
作者 Yasemin Onal 《Computer Systems Science & Engineering》 SCIE EI 2022年第4期141-156,共16页
Predicting the power obtained at the output of the photovoltaic(PV)system is fundamental for the optimum use of the PV system.However,it varies at different times of the day depending on intermittent and nonlinear env... Predicting the power obtained at the output of the photovoltaic(PV)system is fundamental for the optimum use of the PV system.However,it varies at different times of the day depending on intermittent and nonlinear environmen-tal conditions including solar irradiation,temperature and the wind speed,Short-term power prediction is vital in PV systems to reconcile generation and demand in terms of the cost and capacity of the reserve.In this study,a Gaussian kernel based Support Vector Regression(SVR)prediction model using multiple input variables is proposed for estimating the maximum power obtained from using per-turb observation method in the different irradiation and the different temperatures for a short-term in the DC-DC boost converter at the PV system.The performance of the kernel-based prediction model depends on the availability of a suitable ker-nel function that matches the learning objective,since an unsuitable kernel func-tion or hyper parameter tuning results in significantly poor performance.In this study for thefirst time in the literature both maximum power is obtained at max-imum power point and short-term maximum power estimation is made.While evaluating the performance of the suggested model,the PV power data simulated at variable irradiations and variable temperatures for one day in the PV system simulated in MATLAB were used.The maximum power obtained from the simu-lated system at maximum irradiance was 852.6 W.The accuracy and the perfor-mance evaluation of suggested forecasting model were identified utilizing the computing error statistics such as root mean square error(RMSE)and mean square error(MSE)values.MSE and RMSE rates which obtained were 4.5566*10-04 and 0.0213 using ANN model.MSE and RMSE rates which obtained were 13.0000*10-04 and 0.0362 using SWD-FFNN model.Using SVR model,1.1548*10-05 MSE and 0.0034 RMSE rates were obtained.In the short-term maximum power prediction,SVR gave higher prediction performance according to ANN and SWD-FFNN. 展开更多
关键词 Short term power prediction Gaussian kernel support vector regression photovoltaic system
暂未订购 下载PDF
Multi-output Gaussian Process Regression Model with Combined Kernel Function for Polyester Esterification Processes 认领 引用
6
作者 王恒骞 耿君先 陈磊 《Journal of Donghua University(English Edition)》 CAS 2023年第1期27-33,共7页
In polyester fiber industrial processes,the prediction of key performance indicators is vital for product quality.The esterification process is an indispensable step in the polyester polymerization process.It has the ... In polyester fiber industrial processes,the prediction of key performance indicators is vital for product quality.The esterification process is an indispensable step in the polyester polymerization process.It has the characteristics of strong coupling,nonlinearity and complex mechanism.To solve these problems,we put forward a multi-output Gaussian process regression(MGPR)model based on the combined kernel function for the polyester esterification process.Since the seasonal and trend decomposition using loess(STL)can extract the periodic and trend characteristics of time series,a combined kernel function based on the STL and the kernel function analysis is constructed for the MGPR.The effectiveness of the proposed model is verified by the actual polyester esterification process data collected from fiber production. 展开更多
关键词 seasonal and trend decomposition using loess(STL) multi-output Gaussian process regression combined kernel function polyester esterification process
暂未订购 下载PDF
Optimization of Extrusion-based Silicone Additive Manufacturing Process Parameters Based on Improved Kernel Extreme Learning Machine 认领 引用
7
作者 Zi-Ning Li Xiao-Qing Tian +3 位作者 Dingyifei Ma Shahid Hussain Lian Xia Jiang Han 《Chinese Journal of Polymer Science》 SCIE EI CAS CSCD 2025年第5期848-862,共15页
Silicone material extrusion(MEX)is widely used for processing liquids and pastes.Owing to the uneven linewidth and elastic extrusion deformation caused by material accumulation,products may exhibit geometric errors an... Silicone material extrusion(MEX)is widely used for processing liquids and pastes.Owing to the uneven linewidth and elastic extrusion deformation caused by material accumulation,products may exhibit geometric errors and performance defects,leading to a decline in product quality and affecting its service life.This study proposes a process parameter optimization method that considers the mechanical properties of printed specimens and production costs.To improve the quality of silicone printing samples and reduce production costs,three machine learning models,kernel extreme learning machine(KELM),support vector regression(SVR),and random forest(RF),were developed to predict these three factors.Training data were obtained through a complete factorial experiment.A new dataset is obtained using the Euclidean distance method,which assigns the elimination factor.It is trained with Bayesian optimization algorithms for parameter optimization,the new dataset is input into the improved double Gaussian extreme learning machine,and finally obtains the improved KELM model.The results showed improved prediction accuracy over SVR and RF.Furthermore,a multi-objective optimization framework was proposed by combining genetic algorithm technology with the improved KELM model.The effectiveness and reasonableness of the model algorithm were verified by comparing the optimized results with the experimental results. 展开更多
关键词 Silicone material extrusion Process parameter optimization Double Gaussian kernel extreme learning machine Euclidean distance assigned to the elimination factor Multi-objective optimization framework
暂未订购 下载PDF
Comparison of Uniform and Kernel Gaussian Weight Matrix in Generalized Spatial Panel Data Model 认领 引用
8
作者 Tuti Purwaningsih Erfiani   《Open Journal of Statistics》 2015年第1期90-95,共6页
Panel data combine cross-section data and time series data. If the cross-section is locations, there is a need to check the correlation among locations. ρ and λ are parameters in generalized spatial model to cover e... Panel data combine cross-section data and time series data. If the cross-section is locations, there is a need to check the correlation among locations. ρ and λ are parameters in generalized spatial model to cover effect of correlation between locations. Value of ρ or λ will influence the goodness of fit model, so it is important to make parameter estimation. The effect of another location is covered by making contiguity matrix until it gets spatial weighted matrix (W). There are some types of W—uniform W, binary W, kernel Gaussian W and some W from real case of economics condition or transportation condition from locations. This study is aimed to compare uniform W and kernel Gaussian W in spatial panel data model using RMSE value. The result of analysis showed that uniform weight had RMSE value less than kernel Gaussian model. Uniform W had stabil value for all the combinations. 展开更多
关键词 Component Uniform Weight Kernel Gaussian Weight Generalized Spatial Panel Data Model
暂未订购 下载PDF
结合深度核学习与高斯过程的边坡稳定性预测方法 认领 引用 被引量：1
9
作者 李书 喻国荣 +1 位作者 付兵杰 鲍海洲 《水力发电》 CAS 2026年第2期40-47,共8页
鉴于边坡特征之间、特征与稳定性判定之间的复杂非线性关系,经典的高斯过程边坡稳定性预测方法在复杂结构建模上表现有限且难以处理大规模的边坡数据,提出一种结合深度核学习与高斯过程的边坡稳定性预测方法。首先,利用多层前馈网络对... 鉴于边坡特征之间、特征与稳定性判定之间的复杂非线性关系,经典的高斯过程边坡稳定性预测方法在复杂结构建模上表现有限且难以处理大规模的边坡数据,提出一种结合深度核学习与高斯过程的边坡稳定性预测方法。首先,利用多层前馈网络对边坡特征进行深度提取,再将隐空间映射到带有径向基函数核的高斯过程,实现非参数不确定性量化。模型通过最大化边缘对数似然函数优化神经网络权重与核超参数,可端到端学习数据驱动的最优核。在公开的Kaggle数据集上的试验表明,所提方法较经典机器学习算法随机森林RF、支持向量机SVM、高斯过程回归GPR,以及深度学习方法门控循环单元GRU、深度神经网络DNN在均方根误差、平均绝对误差和决定系数等指标上均取得最佳结果,为边坡灾害智能预警提供了新的技术支撑。 展开更多
关键词 边坡稳定性 预测算法 深度核学习 高斯过程回归 经典机器学习算法
暂未订购 下载PDF
机器学习中核函数的隐私保护计算方法及应用 认领 引用
10
作者 张明武 黄子麒 王玉珠 《密码学报（中英文）》 CSCD 北大核心 2026年第1期28-42,共15页
核函数通过量化跨域样本间的相似性,将数据映射至高维空间以解决线性不可分问题,但其在传统明文上计算方式涉及多方数据交互,存在隐私泄露风险.本文针对该问题,提出半诚实模型下的隐私保护计算核函数框架.首先基于同态加密与随机扰乱因... 核函数通过量化跨域样本间的相似性,将数据映射至高维空间以解决线性不可分问题,但其在传统明文上计算方式涉及多方数据交互,存在隐私泄露风险.本文针对该问题,提出半诚实模型下的隐私保护计算核函数框架.首先基于同态加密与随机扰乱因子设计了三个交互式子协议,包括安全内积计算、安全幂函数计算与安全欧氏距离计算协议;通过将明文空间划分为正负数同余类并引入浮点数缩放因子,解决了传统加密算法在真实数据集上的兼容性问题;构建了基于交互式协议的非线性运算框架,在仅依赖加性同态加密的条件下,结合泰勒多项式逼近技术,通过两方计算与随机扰动技术实现了复杂核函数的安全计算,在单一密码系统内支持线性核函数、多项式核函数与高斯核函数;分析了方案的正确性、安全性、计算复杂性并说明了该方案的使用场景,利用公开数据集验证了此方案.实验结果表明,该方案在保证核函数模型精度的同时,有效实现了隐私保护目标,具备计算复杂度低与时间开销少的优势. 展开更多
关键词 线性可分 线性核 多项式核 高斯核 隐私保护
暂未订购 下载PDF
基于稀疏神经核的多保真度代理模型 认领 引用
11
作者 李欣然 连峰 贾家兴 《空气动力学学报》 CSCD 北大核心 2026年第2期37-49,共13页
在航空航天技术领域,代理模型发挥着关键作用。为平衡代理模型的训练成本与预测精度,需要发展能够有效挖掘多保真度数据间潜在相关性的建模方法。针对现有模型依赖预设核函数、缺乏数据自适应性的问题,提出了一种基于稀疏混合专家神经核... 在航空航天技术领域,代理模型发挥着关键作用。为平衡代理模型的训练成本与预测精度,需要发展能够有效挖掘多保真度数据间潜在相关性的建模方法。针对现有模型依赖预设核函数、缺乏数据自适应性的问题,提出了一种基于稀疏混合专家神经核(mixture of experts neural kernel,MoENK)的多保真度代理模型。MoENK通过线性混合和乘积混合基本单元构造新核函数,选择性屏蔽中间结果以过滤噪声,并应用于多任务高斯过程中。将该方法应用于3个函数示例和2个翼型算例中,结果表明该方法的预测精度有较大提升,尤其在NACA0012翼型阻力系数的预测中,相较于次佳方法LR-MFS,RMSE和MAE分别降低了40.42%和44.70%。证实了所提出的MoENK核函数能够不依赖预设核函数进行自适应预测,具有良好的泛化能力和鲁棒性,为工程系统的代理模型构建提供了新的工具。 展开更多
关键词 多保真度代理模型 多任务高斯过程 混合专家系统 神经网络 核函数
暂未订购 下载PDF
基于多尺度空间注意力机制与高斯核函数软标注的华山松大小蠹受害木遥感识别方法 认领 引用
12
作者 黄光体 林浩然 +4 位作者 佃袁勇 韩泽民 彭寿连 刘晓阳 肖箫 《湖北农业科学》 2026年第1期159-165,185,共7页
针对传统树冠边界标注耗时费力,且现有深度学习模型在复杂森林环境中易因下采样丢失空间细节而导致检测精度下降的问题,提出一种融合多尺度空间注意力机制卷积网络(MSSCN)与高斯核函数软标注的单木定位方法。以神农架林区2000、2200、24... 针对传统树冠边界标注耗时费力,且现有深度学习模型在复杂森林环境中易因下采样丢失空间细节而导致检测精度下降的问题,提出一种融合多尺度空间注意力机制卷积网络(MSSCN)与高斯核函数软标注的单木定位方法。以神农架林区2000、2200、2400 m 3个海拔梯度的高分辨率航空遥感影像为数据源,仅标注华山松大小蠹(Dendroctonus armandi)受害木树冠中心点,并采用二维高斯核函数置信图生成标签和制作训练数据集,将区域分割任务转化为单木定位问题。通过调整多尺度特征卷积模块的位置,构建MSSCN1模型、MSSCN2模型、MSSCN3模型,并与U-Net模型、FCN模型和DeepLabV3+模型进行对比。结果表明,高斯核函数软标注方法降低了人工标注成本,同时支持受害木的精确定位。MSSCN3模型在训练100 Epoch时即达到最优性能,测试区精确率、召回率和F1得分的平均值分别为91.97%、93.68%和0.93,优于其他对比模型。MSSCN3模型在神农架林区高海拔区域整体表现出更优的检测性能,且在高暴发密度区的检测精度普遍高于低暴发密度区,然而,在海拔2400 m的高暴发密度区,模型精度出现轻微下降,表明地形与生态因子可能对检测稳定性产生交互影响。MSSCN3模型能够准确识别神农架林区的华山松大小蠹受害木,为虫害防治提供了一种高效且鲁棒的技术路径。 展开更多
关键词 多尺度空间注意力机制 高斯核函数软标注 华山松大小蠹(Dendroctonus armandi) 受害木 遥感识别
暂未订购 下载PDF
基于变分Transformer的时间序列异常检测 认领 引用
13
作者 薛安荣 陈杰 《计算机工程与科学》 CSCD 北大核心 2026年第5期914-924,共11页
时间序列异常检测可以发现监测系统中的异常,及时采取必要措施可减少故障和保护系统安全。然而,现有的时序异常检测模型对时序数据之间非线性关联的处理效果不佳。为此,提出基于变分Transformer与高斯核的双分支学习模型,分别构建序列... 时间序列异常检测可以发现监测系统中的异常,及时采取必要措施可减少故障和保护系统安全。然而,现有的时序异常检测模型对时序数据之间非线性关联的处理效果不佳。为此,提出基于变分Transformer与高斯核的双分支学习模型,分别构建序列关联和局部关联,以重建误差与2种关联之间的差异度量为异常得分,并通过k-means算法自动确定异常阈值。此外,通过校正Transformer中位置编码以减少重构误差。在5个公开数据集上与9个基线模型的对比实验结果表明,所提模型在大多数情况下优于基线模型,而且是唯一在5个数据集上的F1值均超过90%的模型,其在各数据集上F1的平均值比最好的基线模型高2.27个百分点。实验结果表明,所提模型在准确性上具有显著优势,能够有效提高时间序列异常检测的准确性和可靠性。 展开更多
关键词 异常检测 多维时间序列分析 Transformer模型 高斯核函数 变分自动编码器
暂未订购 下载PDF
基于翘曲高斯过程与JAYA-KELM的指纹定位算法 认领 引用
14
作者 周军 张英汉 《现代电子技术》 北大核心 2026年第16期54-61,共8页
针对WiFi指纹定位中指纹库扩展误差与在线定位精度不足的问题,提出一种基于翘曲高斯过程回归(WGPR)与JAYA优化核极限学习机(KELM)的指纹定位算法。在离线阶段,首先采用MaxMean筛选高信息量接入点,以减少冗余并提升特征质量;然后引入WGP... 针对WiFi指纹定位中指纹库扩展误差与在线定位精度不足的问题,提出一种基于翘曲高斯过程回归(WGPR)与JAYA优化核极限学习机(KELM)的指纹定位算法。在离线阶段,首先采用MaxMean筛选高信息量接入点,以减少冗余并提升特征质量;然后引入WGPR模型,通过非线性翘曲函数将接收信号强度(RSS)从非高斯空间映射至潜在高斯空间,并融合复合核函数以增强对多尺度信号变化的建模能力,构建高鲁棒性的指纹库。在在线阶段,采用JAYA算法对KELM模型的超参数进行调优,提升其非线性拟合能力与泛化性能,最终实现RSS与位置坐标的高精度映射。在室内区域的实验结果表明,WGPR-JAYA-KELM模型在复杂环境下的平均定位误差为0.9881 m,相较于其他算法,显著提升了系统的定位精度与鲁棒性。 展开更多
关键词 WiFi指纹定位 翘曲高斯过程回归 极限学习机 JAYA算法 接收信号强度 定位精度
暂未订购 下载PDF
高端旋转机械剩余使用寿命预测及其不确定性量化评估方法 认领 引用 被引量：2
15
作者 崔硕 刘秀丽 +1 位作者 李相杰 吴国新 《中国机械工程》 EI CAS CSCD 北大核心 2026年第1期209-222,共14页
针对高端旋转机械剩余使用寿命预测中的准确性和不确定性量化问题,提出了基于变分深度高斯过程(VDGP)的预测方法。通过构建深度高斯过程更新模型实现不确定性的递推量化,并采用诱导点和变分推断提高大数据的处理能力。C-MAPSS和风机行... 针对高端旋转机械剩余使用寿命预测中的准确性和不确定性量化问题,提出了基于变分深度高斯过程(VDGP)的预测方法。通过构建深度高斯过程更新模型实现不确定性的递推量化,并采用诱导点和变分推断提高大数据的处理能力。C-MAPSS和风机行星齿轮数据集的实验表明,VDGP比高斯过程方法具有更高的预测准确度和更窄的置信区间,在C-MAPSS的FD002数据集上,均方根误差、评分函数分别比现有最佳的对比方法减小0.21%和45.3%。 展开更多
关键词 剩余使用寿命预测 变分深度高斯过程 不确定性量化 旋转机械 核函数
暂未订购 下载PDF
基于知识度量的模糊粗糙c-均值算法 认领 引用 被引量：1
16
作者 李文焱 李丽红 王洪欣 《山东大学学报（理学版）》 CAS CSCD 北大核心 2026年第1期49-64,共16页
提出基于知识度量的模糊粗糙c-均值聚类(fuzzy rough c-means based on the knowledge measure,KFRCM)算法。传统聚类算法在处理具有模糊边界的数据时存在一定的局限性,表现为对初始聚类中心较为敏感且在高维空间中效率较低。为解决上... 提出基于知识度量的模糊粗糙c-均值聚类(fuzzy rough c-means based on the knowledge measure,KFRCM)算法。传统聚类算法在处理具有模糊边界的数据时存在一定的局限性,表现为对初始聚类中心较为敏感且在高维空间中效率较低。为解决上述问题,引入特征加权的知识度量,结合模糊隶属度函数与粗糙集近似算子,采用高斯核相似度以增强边界特性。实验采用14个数据集,实验结果表明,KFRCM算法的聚类准确性、稳定性和计算效率均优于6种主流聚类算法。该研究首次将知识度量与模糊粗糙聚类相结合,为开发更为可靠和适应性更强的聚类算法提供了新的思路和算法。 展开更多
关键词 模糊粗糙集 知识度量 聚类分析 高斯核函数 上下近似集
暂未订购 下载PDF
A physics-guided explainable machine learning framework for residual-based performance deviation detection and probabilistic severity assessment in photovoltaic systems 认领 引用
17
作者 Roby Mohajon Shuva Chandra Sarker +5 位作者 Md Amzad Sadik Abid Simanta Datta Ronobir Abid Kamal Rumi Shimul Chakraborty Adiba Juoairia Nur Mohammad 《Clean Energy》 EI CSCD 2026年第3期143-163,共21页
Monitoring photovoltaic plants entails the use of techniques that are physically meaningful for detecting deviations in the observed behavior from what is expected.Data-driven methods frequently suffer from poor physi... Monitoring photovoltaic plants entails the use of techniques that are physically meaningful for detecting deviations in the observed behavior from what is expected.Data-driven methods frequently suffer from poor physical consistency,whereas physics-based models may fail to account for practical variations in operational behavior.In this study,we present a physics-driven machine learning methodology for estimating fault severity in grid-connected photovoltaic systems.The proposed methodology combines a calibrated PVsyst-based expected power generation model and supervisory control and data acquisition data collected from two 56.32 kilowatt-peak photovoltaic plants.Linear bias correction of the simulation results enhanced the correlation between the predicted and actual power generation levels,with coefficient of determination values of 0.685 and 0.566 for Plants 1 and 2,respectively.The Gaussian mixture model approach coupled with Bayesian information criterion tuning revealed the statistical fault-severity threshold,Rnorm=−0.161,for the discrimination between normal and severe states.For the prediction task,a random forest classifier was trained on seven physics-aware variables and achieved accuracy and macro-F1 scores of 0.920 and 0.907,respectively,through walk-forward validation.Comparative benchmarking with other classifiers,including XGBoost,support vector machine,and decision tree algorithms,showed a better classification performance balance.In addition,the explainability study verified the importance of irradiance,expected power,and conversion efficiency metrics. 展开更多
关键词 photovoltaic performance monitoring physics-Guided machine learning bias-Corrected residual analysis Gaussian mixture model walk-Forward cross-Validation SHAP explainability MDI feature importance kernel density estimation
暂未订购 下载PDF
预测扇形孔气膜分布的“核”参数模型 认领 引用
18
作者 傅奕融 李月茹 +1 位作者 陈榴 戴韧 《动力工程学报》 CAS CSCD 北大核心 2026年第1期51-58,共8页
在离散孔群(群孔)覆盖区域的气膜冷却效率计算中,常规计算流体动力学(CFD)模拟面临建模网格复杂与计算资源耗费大的问题。因此,提出了一种参数形式的核函数,以描述单个气膜孔的冷却效率分布特征,预测气膜冷却效率,并结合数据驱动的机器... 在离散孔群(群孔)覆盖区域的气膜冷却效率计算中,常规计算流体动力学(CFD)模拟面临建模网格复杂与计算资源耗费大的问题。因此,提出了一种参数形式的核函数,以描述单个气膜孔的冷却效率分布特征,预测气膜冷却效率,并结合数据驱动的机器学习技术和Sellers气膜冷却效率叠加方法,实现对群孔覆盖域冷却效率分布的高效预测。基于该“核”参数模型,成功复现了7-7-7扇形气膜孔的单孔和三列顺排群孔的冷却效率分布,并在给定区域内,利用整数规划方法获得了区域面平均冷却效率最高的顺排群孔布局。结果表明:“核”参数模型能够准确反映气膜孔覆盖域内冷却效率的分布特征,克服了传统关联式仅预测展向平均冷却效率的局限性,而且显著减少了机器学习所需的样本数量,可适用于不同工况下的气膜冷却效率预测。 展开更多
关键词 气膜冷却 高斯核 人工神经网络 全覆盖预测
暂未订购 下载PDF
自适应核带宽最大相关熵无迹卡尔曼滤波 认领 引用
19
作者 赵逸飞 殷利平 +1 位作者 陆亚舒 徐国育 《兵器装备工程学报》 CAS CSCD 北大核心 2026年第5期186-193,共8页
最大相关熵无迹卡尔曼滤波(maximum correntropy unscented Kalman filter,MCUKF)在处理具有非高斯噪声的非线性状态估计时具有很强的鲁棒性。通过对滤波更新步骤引入一个新的代价函数,提出了一种基于自适应核带宽的最大相关熵无迹卡尔... 最大相关熵无迹卡尔曼滤波(maximum correntropy unscented Kalman filter,MCUKF)在处理具有非高斯噪声的非线性状态估计时具有很强的鲁棒性。通过对滤波更新步骤引入一个新的代价函数,提出了一种基于自适应核带宽的最大相关熵无迹卡尔曼滤波算法。相较于传统的最大相关熵无迹卡尔曼滤波使用统计线性化技术,直接利用非线性测量函数能够有效解决得到的近似线性测量方程不够准确的问题;同时,针对滤波更新步骤的代价函数无法有效降低估计误差离群值对滤波性能影响的问题,引入新的代价函数,通过设定加权因子,降低估计误差离群值对系统的负面影响。为了进一步提高滤波器性能,设计了一种自适应核带宽算法,利用测量误差自动选择每个时间步长的核带宽值。最后通过模拟导航过程,证明了这种滤波方法的有效性。 展开更多
关键词 无迹卡尔曼滤波 最大相关熵 非高斯噪声 自适应核带宽
暂未订购 下载PDF
大兴安岭雷击火时空聚集性及其驱动因素 认领 引用
20
作者 高博洋 徐健楠 +3 位作者 李伟克 王明玉 宁吉彬 杨光 《林业科学》 EI CAS CSCD 北大核心 2026年第6期56-70,共15页
【目的】全球气候变暖、极端天气频发,导致雷击火灾的规模更大、强度更高、破坏性更强。探究大兴安岭雷击火灾的时空分布及聚集性演变规律,并识别其关键驱动因素,为雷击火灾的防控和管理提供科学依据。【方法】基于2013—2024年大兴安... 【目的】全球气候变暖、极端天气频发,导致雷击火灾的规模更大、强度更高、破坏性更强。探究大兴安岭雷击火灾的时空分布及聚集性演变规律,并识别其关键驱动因素,为雷击火灾的防控和管理提供科学依据。【方法】基于2013—2024年大兴安岭雷击火灾历史数据,综合运用统计分析、二维高斯核密度分析、地理探测器等方法,分析雷击火灾的动态演化规律、空间聚集特征及关键驱动因素的解释力。【结果】1)12年间共发生雷击火灾791次,2019年达到峰值。雷击火灾主要集中在4—10月,尤其是春季防火期和夏季生长期,最早记录为4月24日,最晚为9月19日。春季防火期结束后雷击火灾数量回落,但于7月中旬再次达到高峰。每日13:00—17:00(不含17:00时刻)为雷击火灾的高发时段,占总发生次数的50%以上。2)12年间雷击火灾整体在研究区西北部呈明显聚集。逐年分析显示,聚集区呈现年度差异。采用自然断裂法将雷击火灾核密度值划分为5个风险等级,南部地区通常为极低风险区域(仅2022年出现少量雷击火灾)。Getis-Ord Gi*显著性检验显示,极高风险区具有稳定的空间聚集特征。3)前3日平均气温、月最高气温、海拔、月平均气温、0~7 cm土层土壤湿度和归一化植被指数是各年份中解释力最强的核心驱动因素。相对湿度和月平均气温(较高解释力出现次数9次)、海拔和归一化植被指数(7次)等组合在历年数据中解释力普遍较强,表明其对雷击火灾的发生影响较为显著。此外,月平均气温、月最高气温和海拔与其他驱动因素的组合亦具有较高解释力。【结论】近年来大兴安岭雷击火灾发生整体呈波动趋势,建议在夏季(特别是午后14:00时左右)加强对重点林区的防范。12年间雷击火灾在乌玛、永安山、图强和阿木尔地区持续呈显著聚集特征,部分年份(2015和2018年)雷击火灾事件分布较散,呈随机分布特征,无显著聚集。不同类型因子的交互作用存在差异,其中气象因子之间的交互效应较为明显,在雷击火灾的发生机制中占据主导作用。本研究揭示了雷击火灾的时空演化规律及关键驱动机制,为防火决策的精细化和区域化管理提供了科学依据。 展开更多
关键词 雷击火灾 驱动因素 二维高斯核密度 地理探测器 大兴安岭
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 … 25 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈