期刊文献+
共找到401篇文章
< 1 2 21 >
每页显示 20 50 100
Spatio-temporal evolution and topographic gradient effect of land use and ecosystem service value in the Lhasa River Basin
1
作者 ZHOU Jianwei FENG Bin +8 位作者 WU Hua XU Tong CHEN Linna ZHAO Xinyong GUO Qiyun LI Jiatong ZHANG Chenguang ZHU Kangcheng KONG Yuzhong 《Journal of Mountain Science》 SCIE CSCD 2024年第6期2059-2074,共16页
The Lhasa River Basin forms an essential human settlement area in the southern part of the Qinghai-Tibet Plateau.This study employed ecosystem service value(ESV)evaluation model,terrain gradient grading,and Geodetecto... The Lhasa River Basin forms an essential human settlement area in the southern part of the Qinghai-Tibet Plateau.This study employed ecosystem service value(ESV)evaluation model,terrain gradient grading,and Geodetector to analyze land use and ESV in the Lhasa River Basin from 1985 to 2020.The findings reveal that:(1)From 1985 to 2020,grassland was the dominant land use.There was a trend of grassland reduction and the expansion of other land types.(2)ESV has increased over the research period(with a total increase of 0.84%),with higher values in the southeast and lower values in the northwest.Grassland contributed the most to ESV,and climate regulation and hydrological regulation were the ecosystem services that contribute the most to ESV.(3)Natural factors like NDVI and altitude,as well as economic factors like population density and distance from roads,influenced the spatial differentiation of ESV,the explanatory power of NDVI reached up to 0.47.The interaction between factors had a greater impact than individual factors.These research results can provide theoretical support for national spatial planning and ecological environment protection in the Lhasa River Basin and other similar areas. 展开更多
关键词 Ecosystem services value Land use Terrain gradient effect Lhasa River Basin Driving factors
原文传递
Spatiotemporal evolution of ecosystem service value and topographic gradient effect in the Da-Xiao Liangshan Mountains in Sichuan Province,China 被引量:2
2
作者 JIN Tao CHEN Yang +2 位作者 SHU Bo GAO Min QIU Jian 《Journal of Mountain Science》 SCIE CSCD 2023年第8期2344-2357,共14页
The Da-Xiao Liangshan mountains are critical ecological function areas and essential ecological barriers in the upper reaches of the Yangtze River in China.This study selected a total of six periods of land use land c... The Da-Xiao Liangshan mountains are critical ecological function areas and essential ecological barriers in the upper reaches of the Yangtze River in China.This study selected a total of six periods of land use land cover(LULC)data from 1995 to 2020,to estimate the ecosystem service value(ESV)and analyzed its spatiotemporal evolution and topographic gradient divergence.The results showed that:(1)The ESV increased by 1.1 billion yuan,with an increase rate of 1.47%from 1995 to 2020.Two time periods,2005–2010 and 2015–2020,showed more significant increases than other periods.(2)The elevation and slope of mountainous areas determine the type of land use and further influence the spatial pattern of ESV.(3)Although woodland and grassland are the main land use types of the study area(more than 90%),the hydrological regulation function of the water area partially compensated for the impact of the encroachment of the built-up area on the ESV of grassland.(4)The spatial distribution of ESVs showed an inverted V-shaped characteristic as the topographic gradient increased,with the dominant position being the 5th topographic gradient zone.Finally,this study provided relevant recommendations for ecosystem protection and optimization.The findings of this study clarified the influence of topographical factors on the spatial differentiation of ESV and provided novel insights into ecosystem protection. 展开更多
关键词 Ecosystem service value(ESV) Dynamic evolution Terrain gradient effect Spatial pattern Liangshan Yi region
原文传递
Variations of population structure and important value of the main edificators along the elevation gradient on the northern slope of Changbai Mountain 被引量:1
3
作者 姜萍 叶吉 +1 位作者 郝占庆 邓红兵 《Journal of Forestry Research》 SCIE CAS CSCD 2003年第2期117-121,共5页
From 700 m to 1900 m on the northern slope of Changbai Mountain, 13 plots with an interval of 100 m in elevation were investigated to study the variations of population structure and important value of the main edific... From 700 m to 1900 m on the northern slope of Changbai Mountain, 13 plots with an interval of 100 m in elevation were investigated to study the variations of population structure and important value of the main edificators along the elevation gradient. In their core distribution areas, most of the edificators had healthy population structure and could regenerate smoothly except Larix olgensis, but important value of Larix olgensis had no obvious variations with elevation changes, which showed that Larix olgensis had its own particularity and strong adaptability. At high elevation above 1800 m, Betula ermanii was the only species that could form a mono-dominant community. Important values of Pinus koraiensis and Acer mono had similar changing trends, and they had the similar ecological adaptabilities. 展开更多
关键词 Edificator POPULATION Important value STRUCTURE Elevation gradient Changbai Mountain
下载PDF
Mapping landslide susceptibility at the Three Gorges Reservoir, China, using gradient boosting decision tree,random forest and information value models 被引量:9
4
作者 CHEN Tao ZHU Li +3 位作者 NIU Rui-qing TRINDER C John PENG Ling LEI Tao 《Journal of Mountain Science》 SCIE CSCD 2020年第3期670-685,共16页
This work was to generate landslide susceptibility maps for the Three Gorges Reservoir(TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely, gradient boosting de... This work was to generate landslide susceptibility maps for the Three Gorges Reservoir(TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely, gradient boosting decision tree(GBDT), random forest(RF) and information value(InV) models, were used, and the performances were assessed and compared. In total, 202 landslides were mapped by using a series of field surveys, aerial photographs, and reviews of historical and bibliographical data. Nine causative factors were then considered in landslide susceptibility map generation by using the GBDT, RF and InV models. All of the maps of the causative factors were resampled to a resolution of 28.5 m. Of the 486289 pixels in the area,28526 pixels were landslide pixels, and 457763 pixels were non-landslide pixels. Finally, landslide susceptibility maps were generated by using the three machine learning models, and their performances were assessed through receiver operating characteristic(ROC) curves, the sensitivity, specificity,overall accuracy(OA), and kappa coefficient(KAPPA). The results showed that the GBDT, RF and In V models in overall produced reasonable accurate landslide susceptibility maps. Among these three methods, the GBDT method outperforms the other two machine learning methods, which can provide strong technical support for producing landslide susceptibility maps in TGR. 展开更多
关键词 MAPPING LANDSLIDE SUSCEPTIBILITY gradient BOOSTING decision tree Random FOREST Information value model Three Gorges Reservoir
原文传递
Effect of pH Value on Nano-Al_2O_3/Ni+Co Gradient Bionic Composite Coating by Electrodeposition
5
作者 刘燕 任露泉 《Journal of Wuhan University of Technology(Materials Science)》 SCIE EI CAS 2009年第S1期50-53,共4页
The metal and nano-ceramic composite coatings were formed on gray cast iron surface by electrodepositon method.The Ni-Co was used as metal matrix,and the nano-Al2O3 was chosen as second-phase particulates.The gradient... The metal and nano-ceramic composite coatings were formed on gray cast iron surface by electrodepositon method.The Ni-Co was used as metal matrix,and the nano-Al2O3 was chosen as second-phase particulates.The gradient structure of biology material was the model to avoid bad interface bonding and stress distribution,therefore the gradient composite coating was prepared.The morphology of composite coatings was flatter and the microstructure was more com-pact than the pure Ni-Co coatings.Effect of pH value on surface morphology was analyzed,which some microcracks appeared when pH value was greater than 5.The content of codeposition na-no-Al2O3 reached a maximum value at pH value of 3-4,at the same time the properties including mi-crohardness and wear-resistance were analyzed.The result indicated that the mirohardness reached a maximum value and the wear loss volume was less at pH value 3-4. 展开更多
关键词 pH value ELECTRODEPOSITION gradient composite coating microstructure PROPERTY
原文传递
Wavelet multiresolution interpolation Galerkin method for nonlinear boundary value problems with localized steep gradients
6
作者 Xiaojing LIU Youhe ZHOU Jizeng WANG 《Applied Mathematics and Mechanics(English Edition)》 SCIE EI CSCD 2022年第6期863-882,共20页
The wavelet multiresolution interpolation for continuous functions defined on a finite interval is developed in this study by using a simple alternative of transformation matrix.The wavelet multiresolution interpolati... The wavelet multiresolution interpolation for continuous functions defined on a finite interval is developed in this study by using a simple alternative of transformation matrix.The wavelet multiresolution interpolation Galerkin method that applies this interpolation to represent the unknown function and nonlinear terms independently is proposed to solve the boundary value problems with the mixed Dirichlet-Robin boundary conditions and various nonlinearities,including transcendental ones,in which the discretization process is as simple as that in solving linear problems,and only common two-term connection coefficients are needed.All matrices are independent of unknown node values and lead to high efficiency in the calculation of the residual and Jacobian matrices needed in Newton’s method,which does not require numerical integration in the resulting nonlinear discrete system.The validity of the proposed method is examined through several nonlinear problems with interior or boundary layers.The results demonstrate that the proposed wavelet method shows excellent accuracy and stability against nonuniform grids,and high resolution of localized steep gradients can be achieved by using local refined multiresolution grids.In addition,Newton’s method converges rapidly in solving the nonlinear discrete system created by the proposed wavelet method,including the initial guess far from real solutions. 展开更多
关键词 wavelet multiresolution interpolation transcendental nonlinearity localized steep gradient singularly perturbed boundary value problem Troesch’s problem
下载PDF
On fine-grained visual explanation in convolutional neural networks
7
作者 Xia Lei Yongkai Fan Xiong-Lin Luo 《Digital Communications and Networks》 SCIE CSCD 2023年第5期1141-1147,共7页
Existing explanation methods for Convolutional Neural Networks(CNNs)lack the pixel-level visualization explanations to generate the reliable fine-grained decision features.Since there are inconsistencies between the e... Existing explanation methods for Convolutional Neural Networks(CNNs)lack the pixel-level visualization explanations to generate the reliable fine-grained decision features.Since there are inconsistencies between the explanation and the actual behavior of the model to be interpreted,we propose a Fine-Grained Visual Explanation for CNN,namely F-GVE,which produces a fine-grained explanation with higher consistency to the decision of the original model.The exact backward class-specific gradients with respect to the input image is obtained to highlight the object-related pixels the model used to make prediction.In addition,for better visualization and less noise,F-GVE selects an appropriate threshold to filter the gradient during the calculation and the explanation map is obtained by element-wise multiplying the gradient and the input image to show fine-grained classification decision features.Experimental results demonstrate that F-GVE has good visual performances and highlights the importance of fine-grained decision features.Moreover,the faithfulness of the explanation in this paper is high and it is effective and practical on troubleshooting and debugging detection. 展开更多
关键词 Convolutional neural network EXPLANATION Class-specific gradient fine-grainED
下载PDF
基于二阶价值梯度模型强化学习的工业过程控制方法
8
作者 张博 潘福成 +1 位作者 周晓锋 李帅 《计算机应用研究》 CSCD 北大核心 2024年第8期2434-2440,共7页
为了实现对高延时、非线性和强耦合的复杂工业过程稳定准确的连续控制,提出了一种基于二阶价值梯度模型强化学习的控制方法。首先,该方法在模型训练过程中加入了状态价值函数的二阶梯度信息,具备更精确的函数逼近能力和更高的鲁棒性,学... 为了实现对高延时、非线性和强耦合的复杂工业过程稳定准确的连续控制,提出了一种基于二阶价值梯度模型强化学习的控制方法。首先,该方法在模型训练过程中加入了状态价值函数的二阶梯度信息,具备更精确的函数逼近能力和更高的鲁棒性,学习迭代效率更高;其次,通过采用新的状态采样策略,可以更高效地利用模型进行策略学习。最后,通过在OpenAI的Gym公共实验环境和两个工业场景的仿真环境的实验表明:基于二阶价值梯度模型对比传统的基于最大似然估计模型,环境模型预测误差显著降低;基于二阶价值梯度模型的强化学习方法学习效率优于现有的基于模型的策略优化方法,具备更好的控制性能,并减小了控制过程中的振荡现象。可见该方法能有效地提升训练效率,同时提高工业过程控制的稳定性和准确性。 展开更多
关键词 工业过程控制 模型强化学习 二阶价值梯度 状态价值函数 状态采样策略
下载PDF
基于SC-XGBoost的电站燃煤低位发热量软测量方法
9
作者 乔世超 王轶男 +4 位作者 吕佳阳 陈衡 刘涛 徐钢 翟融融 《煤炭科学技术》 EI CAS CSCD 北大核心 2024年第S01期332-340,共9页
随着国家大力推进能源供给侧结构性改革,新能源装机容量不断提升,电力市场竞争愈加激烈。另一方面,全球煤炭市场的复杂多变,导致以煤炭为能量来源的发电企业成本上涨。燃煤发热量是衡量煤质的重要评价标准之一,也是采购煤炭最重要的依据... 随着国家大力推进能源供给侧结构性改革,新能源装机容量不断提升,电力市场竞争愈加激烈。另一方面,全球煤炭市场的复杂多变,导致以煤炭为能量来源的发电企业成本上涨。燃煤发热量是衡量煤质的重要评价标准之一,也是采购煤炭最重要的依据,对燃煤发热量进行准确预测能够有效地控制电厂运行采购成本。为了实现燃煤发热量的高效预测,采用Pearson系数对相关变量进行特征选取,采用基于密度的噪点空间聚类(Density-Based Spatial Clustering of Applications with Noise,DBSCAN)算法对某电厂自备煤厂近2年1733条化验数据进行去噪,对去噪后数据进行谱聚类(Spectral Clustering,SC)分析。将分类后的子样本集采用极致梯度提升(Extreme Gradient Boosting,XGBoost)算法分别建立预测模型,并与最小二乘法回归(Ordinary Least Squares,OLS)、支持向量机(Support Vector Machines,SVM)模型进行性能比较。结果表明,基于XGBoost的电站燃煤发热量预测模型相较于其他算法准确性有明显提升,泛化能力更强。对经过SC算法分类后的燃煤分别建立预测模型能够进一步提高模型的精细化水平,为燃煤电站发热量预测提供一种可靠高效的方法。 展开更多
关键词 低位发热量 机器学习 谱聚类 极致梯度提升(XGBoost) 软测量
下载PDF
变分法研究一类分数阶微分方程边值问题解的存在性
10
作者 黎文博 周文学 +1 位作者 吴亚斌 张敏 《云南大学学报(自然科学版)》 CAS CSCD 北大核心 2024年第2期201-212,共12页
利用一类分数阶微分方程边值问题的变分法,建立了该边值问题解存在的充分条件.然后将问题归结为一个等价的积分形式,使得边值问题的解被定义为对应泛函的临界点.最后利用山路引理,建立了该边值问题解的存在性.
关键词 临界点理论 变分法 边值问题 梯度
下载PDF
基于值学习与策略梯度的深度强化学习在核工程领域的适配性分析
11
作者 谭思超 刘震 +5 位作者 刘永超 李桐 梁彪 王博 李江宽 田瑞峰 《原子能科学技术》 EI CAS CSCD 北大核心 2024年第S02期382-392,共11页
深度强化学习能够实现端到端处理,将高维度的原始输入数据直接转化为输出动作。深度强化学习按照间接和直接的策略优化方式,主要可分为基于值学习和基于策略梯度的两类方法。二者因原理不同,在解决问题的能力和适用场景上存在差异。核... 深度强化学习能够实现端到端处理,将高维度的原始输入数据直接转化为输出动作。深度强化学习按照间接和直接的策略优化方式,主要可分为基于值学习和基于策略梯度的两类方法。二者因原理不同,在解决问题的能力和适用场景上存在差异。核领域中的决策问题状态参数维度高,同时决策参数与状态参数之间存在强非线性关系,是深度强化学习的潜在应用场景。本文从强化学习的基本原理出发,归纳了基于值学习和基于策略梯度的强化学习方法的机理差异,并结合目前研究现状对两类方法在核工程领域可能的应用场景进行了深入分析。最后,总结了深度强化学习在后续应用中所面临的挑战及应用趋势。 展开更多
关键词 人工智能 深度强化学习 值函数 策略梯度
下载PDF
基于PIVKA-Ⅱ、AFP检测和机器学习算法的肝癌诊断预测模型性能分析
12
作者 宋佳悦 袁权 +1 位作者 车雨东 张毅敏 《中西医结合肝病杂志》 CAS 2024年第9期775-780,共6页
目的:探讨基于PIVKA-Ⅱ和AFP检测及机器学习算法的肝癌辅助诊断预测模型建立及诊断应用价值。方法:选取2022年3月至2022年12月浙江省肿瘤医院健康体检者112例,肝良性疾病患者149例,以及初诊为肝癌的患者265例,评价受试者基线血清异常凝... 目的:探讨基于PIVKA-Ⅱ和AFP检测及机器学习算法的肝癌辅助诊断预测模型建立及诊断应用价值。方法:选取2022年3月至2022年12月浙江省肿瘤医院健康体检者112例,肝良性疾病患者149例,以及初诊为肝癌的患者265例,评价受试者基线血清异常凝血酶原(PIVKA-Ⅱ)和血清甲胎蛋白(AFP)水平,结合机器学习算法构建辅助诊断预测模型,比较不同模型在肝癌中的诊断价值。结果:血清PIVKA-Ⅱ和AFP在肝癌组患者中的水平最高,与肝癌患者肿瘤的大小、数量、分化程度等临床特征相关。以年龄、性别、PIVKA-Ⅱ和AFP水平为特征,借助梯度提升机(GBM)算法构建的肝癌辅助诊断预测模型在诊断肝癌、早期肝癌、晚期肝癌和AFP阴性肝癌的性能均优于PIVKA-Ⅱ、AFP单项及ASAP模型。结论:以年龄、性别、PIVKA-Ⅱ和AFP水平为特征,借助GBM算法构建的肝癌辅助诊断预测模型提高了肝癌的诊断准确率。 展开更多
关键词 肝癌 PIVKA-Ⅱ AFP 梯度提升机算法 诊断价值
下载PDF
退化Hessian商方程斜边值问题的梯度估计
13
作者 孙文静 韩菲 《宁夏师范学院学报》 2024年第7期5-11,共7页
研究一类退化Hessian商方程斜边值问题,通过选取适当的辅助函数,利用极大值原理和基本对称函数的性质,在f1/k-l∈C^(1)(Ω×R(n))和一般结构条件下得到该方程当f依赖于x和Du时解的全局梯度估计.
关键词 退化Hessian商方程 斜边值 梯度估计
下载PDF
基于近红外光谱技术的气体浓度检测研究
14
作者 梁良 杜雨馨 杨子建 《激光杂志》 CAS 北大核心 2024年第3期253-257,共5页
气体浓度在各领域分析中具有重要意义,由于在气体浓度检测过程中,受光谱维度的影响导致检测结果出现较大的误差,为了降低在测量过程中产生的不利影响,提出基于近红外光谱技术的气体浓度检测研究。通过去势-标准正态变换,校正近红外光谱... 气体浓度在各领域分析中具有重要意义,由于在气体浓度检测过程中,受光谱维度的影响导致检测结果出现较大的误差,为了降低在测量过程中产生的不利影响,提出基于近红外光谱技术的气体浓度检测研究。通过去势-标准正态变换,校正近红外光谱基线。联合广义S变换和奇异值分解共同去噪近红外光谱,提升光谱质量。基于主成分分析提出偏最小二乘降维法用于降维近红外光谱。以朗伯比尔定律为基础,引入Lorenz线性拟合近红外光谱吸收谱线,采用梯度下降法直接拟合预处理近红外光谱吸收信号,计算得到最终气体浓度检测结果。实验结果表明,所提方法在检测甲苯、丙烷和丙烯气体浓度时,检测结果与实际气体浓度基本一致,有效降低了残差平方和与均方根误差,且检测时间低于2.3 s。 展开更多
关键词 近红外光谱技术 气体浓度检测 奇异值分解 偏最小二乘降维 梯度下降法
原文传递
基于梯度提升回归树算法的煤炭发热量计算
15
作者 万国祥 《能源科技》 2024年第3期85-89,共5页
煤炭发热量是衡量煤质的关键指标,反映了煤炭充分燃烧时释放的能量。煤炭发热量可通过实验测定和计算途径获取,其中实验方法虽精确却复杂昂贵耗时。在实际应用中,通过多元线性回归估算得出发热量数据,但是这种方法计算的结果准确率较低... 煤炭发热量是衡量煤质的关键指标,反映了煤炭充分燃烧时释放的能量。煤炭发热量可通过实验测定和计算途径获取,其中实验方法虽精确却复杂昂贵耗时。在实际应用中,通过多元线性回归估算得出发热量数据,但是这种方法计算的结果准确率较低。鉴于此,提出了一种基于梯度提升回归树(GBRT)的煤炭发热量计算方法,该方法是一种机器学习回归分析方法,能够有效克服多元线性回归模型在处理非线性数据时的局限性。在国际公认的COALQUAL煤质数据库上对提出的模型进行了验证和对比,结果显示:GBRT模型的预测误差(MAE、MSE、RMSE)均小于多元线性回归模型;拟合优度(R2=0.989)大于多元线性回归模型(R2=0.970)。说明GBRT是一种高效、准确的煤炭发热量预测模型,对于煤质评价具有一定的实际意义。 展开更多
关键词 煤炭发热量 梯度提升回归树 回归分析 预测
下载PDF
基于特征组合优化的工业互联网恶意行为实时检测方法
16
作者 胡向东 张琴 《电子学报》 EI CAS CSCD 北大核心 2024年第9期3075-3085,共11页
工业互联网中节点数据具有高维、冗余和海量等特性,传统的恶意行为检测模型无法对工业互联网恶意攻击行为做出快速且准确的判断,提出基于特征组合优化的工业互联网恶意行为实时检测方法.采用改进的相关性快速过滤算法和基于奇异值分解... 工业互联网中节点数据具有高维、冗余和海量等特性,传统的恶意行为检测模型无法对工业互联网恶意攻击行为做出快速且准确的判断,提出基于特征组合优化的工业互联网恶意行为实时检测方法.采用改进的相关性快速过滤算法和基于奇异值分解的主成分分析算法对工业互联网恶意行为样本数据进行特征组合优化,基于对称不确定性信息度量指标和近似马尔科夫毯准则进行特征相关性计算、冗余特征识别与排除,通过参数特征维度的不同配置得到若干候选特征组合;利用决策树评估器筛选出准确率最高的候选特征组合;通过奇异值分解的主成分分析进一步进行特征降维,得到低维高信息量的最优特征组合;结合极端梯度提升算法和优化的特征组合对工业互联网恶意行为样本进行分类,基于密西西比州立大学多分类电力系统攻击样本数据对本文方法进行了验证;实验结果表明,特征组合优化检测模型训练时间可缩减57.53%,单个样本的平均检测时间为0.002 ms,可减少23.99%,基于特征组合优化的检测模型的准确率、召回率和F1值较特征优化前分别提升了1.11%、1.25%和1.01%.本文方法的突出优势表现为在提升模型检测效果的同时可明显降低模型检测时间,能更好适应工业互联网的实时性要求. 展开更多
关键词 工业互联网 改进的相关性快速过滤算法 奇异值分解的主成分分析 特征组合优化 极端梯度提升 恶意行为实时检测
下载PDF
基于梯度提升树模型的新能源二手车价值评估
17
作者 李晨 关勇军 《商业观察》 2024年第29期21-25,共5页
随着新能源汽车规模的快速扩大,大量的新能源汽车涌入二手车市场。文章选取来自瓜子二手车网站的近1000项数据集作为样本,结合特征价格理论,选取19个评估维度作为特征,通过随机森林算法对特征重要性进行排序,剔除不重要的特征变量后选... 随着新能源汽车规模的快速扩大,大量的新能源汽车涌入二手车市场。文章选取来自瓜子二手车网站的近1000项数据集作为样本,结合特征价格理论,选取19个评估维度作为特征,通过随机森林算法对特征重要性进行排序,剔除不重要的特征变量后选用梯度提升树作为预测模型。经过参数优化,梯度提升树模型的拟合优度为0.98,平均绝对误差为0.37,结果证明梯度提升树模型对于纯电动二手车价值评估具有一定作用。 展开更多
关键词 新能源二手车 价值评估 梯度提升树 随机森林
下载PDF
Strategies for Applying LED Lights in Night Space Lighting for Bridges
18
作者 Yingling Dai Qinghua Zhao 《Journal of World Architecture》 2024年第3期57-62,共6页
LED lights have been widely used in urban night space lighting in recent years as they are small,energy-saving,and efficient.This article explores the use of LEDs in bridge night space lighting and their application s... LED lights have been widely used in urban night space lighting in recent years as they are small,energy-saving,and efficient.This article explores the use of LEDs in bridge night space lighting and their application strategies.The aim is to offer valuable insights and references for urban planners and bridge lighting designers in China.By advancing the application of LED technology in bridge night lighting,the goal is to enhance the city’s nighttime ambiance,making the bridge an iconic landmark and a defining feature of the city. 展开更多
关键词 Bridge night space lighting LED application Color band and gradient Artistic value Online publication:July 11 2024
下载PDF
黄陵矿区地热特征与煤热共采前景分析
19
作者 王少锋 申小龙 +2 位作者 刘军 赵真 王伟 《中国煤炭》 北大核心 2024年第10期134-141,共8页
为研究黄陵矿区地热地质特征及地热资源开发利用,整理和研究了黄陵矿区85个煤孔测井井温资料,梳理测温孔在48~72 h的近似稳态测温数据,编制了有代表性测温孔孔底温度曲线,同时计算了矿区地温梯度,绘制了黄陵矿区地温梯度特征分布图,并... 为研究黄陵矿区地热地质特征及地热资源开发利用,整理和研究了黄陵矿区85个煤孔测井井温资料,梳理测温孔在48~72 h的近似稳态测温数据,编制了有代表性测温孔孔底温度曲线,同时计算了矿区地温梯度,绘制了黄陵矿区地温梯度特征分布图,并在此基础上绘制了500、1000、1500 m垂深地温分布特征图。同时,结合采集的岩石热导率测试数据,计算出黄陵矿区的大地热流值,并对地热资源进行了评估。研究结果表明,黄陵矿区测温钻孔井底温度恢复与井内稳定时间之间呈指数函数关系,以此建立了温测钻孔井底温度变化的校正公式;黄陵矿区主要地热参数为地温梯度在1.1~5.2℃/hm之间,平均值为2.7℃/hm;500 m垂深平均地温为24.99℃,1000 m垂深为38.53℃,1500 m垂深为52.07℃;岩石热导率为2.0~4.0 W/(m·K),在3.0~3.5 W/(m·K)时最多,平均值为2.54 W/(m·K);大地热流值为32.71~97.62 mW/m^(2),平均值为63.17 mW/m^(2);在平面上,地温梯度、地温场、大地热流总体呈现为南高北低、东高西低的分布趋势。基于黄陵矿区地热资源评估,矿区的热储层地热资源量为3.11×10^(19)J,可采热能储量为4.65×10^(18)J。目前黄陵矿区煤热共采地热利用多集中在矿井余热,考虑到黄陵矿区优异的地热赋存及矿井开采条件,进一步开展煤-热共采地热利用技术的研究及工程示范具有重要的示范意义。 展开更多
关键词 黄陵矿区 地温梯度 热导率 大地热流值 地热资源量
下载PDF
基于卷积神经网络的红外与可见光图像融合方法
20
作者 李景景 杜梅 孙滨 《激光杂志》 CAS 北大核心 2024年第2期135-139,共5页
针对当前红外与可见光图像融合方法存在融合效果差、效率低等问题,为了获得更优的红外与可见光图像融合结果,提出了基于卷积神经网络的红外与可见光图像融合方法。首先收集待融合红外与可见光图像,采用Retinex算法对图像进行增强操作,... 针对当前红外与可见光图像融合方法存在融合效果差、效率低等问题,为了获得更优的红外与可见光图像融合结果,提出了基于卷积神经网络的红外与可见光图像融合方法。首先收集待融合红外与可见光图像,采用Retinex算法对图像进行增强操作,提升图像亮度和细节信息,然后采用卷积神经网络提取图像融合特征,并设计红外与可见光图像融合规则,根据规则得到图像融合结果,最后应用多个数据集进行红外与可见光图像融合性能测试实验,结果表明,卷积神经网络的图像融合后整体视觉效果好,重要细节信息丰富,熵和平均梯度的值超过了6,融合时间低于1 s,整体性能优于其它红外与可见光图像对比融合方法。 展开更多
关键词 红外成像系统 可见光成像系统 卷积神经网络 融合规则 均梯度值
原文传递
上一页 1 2 21 下一页 到第
使用帮助 返回顶部