检索结果-南通市图书馆

维普期刊数据库博看期刊

Improving Multi-Model Ensemble Forecasts of Tropical Cyclone Intensity Using Bayesian Model Averaging

在线全文

学校读者我要写书评

暂无评论

Journal of Meteorological Research 2018年第5期32卷 794-803页

作者： xiaojiang SONG Yuejian ZHU Jiayi PENG Hong GUAN Key Laboratory of Research on Marine Hazards Forecasting National Marine Environmental Forecasting Center Environmental Modeling Center NOAA/NWS/NCEP I.M.Systems Group Inc. and NOAA/NWS/NCEP/EMC System Research Group Inc. Colorado Springs CO 80901 and NOAA/NWS/NCEP/EMC

This paper proposes a method for multi-model ensemble forecasting based on Bayesian model averaging （BMA）, aiming to improve the accuracy of tropical cyclone （TC） intensity forecasts, especially forecasts of minimum surface pressure at the cyclone center （Pmin）＇ The multi-model ensemble comprises three operational forecast models： the Global Forecast System （GFS） of NCEP, the Hurricane Weather Research and Forecasting （HWRF） models of NCEP, and the Integrated Forecasting System （IFS） of ECMWF. The mean of a predictive distribution is taken as the BMA forecast. In this investigation, bias correction of the minimum surface pressure was applied at each forecast lead time, and the distribution （or probability density function, PDF） of emin was used and transformed. Based on summer season forecasts for three years, we found that the intensity errors in TC forecast from the three models var-ied significantly. The HWRF had a much smaller intensity error for short lead-time forecasts. To demonstrate the proposed methodology, cross validation was implemented to ensure more efficient use of the sample data and more reliable testing. Comparative analysis shows that BMA for this three-model ensemble, after bias correction and distri-bution transformation, provided more accurate forecasts than did the best of the ensemble members （HWRF）, with a 5%-7% decrease in root-mean-square error on average. BMA also outperformed the multi-model ensemble, and it produced ＂predictive variance＂ that represented the forecast uncertainty of the member models. In a word, the BMA method used in the multi-model ensemble forecasting was successful in TC intensity forecasts, and it has the poten-tial to be applied to routine operational forecasting.

关键词： tropical cyclone Bayesian model average intensity bias correction forecast uncertainty ensemble forecast

基于句法CYK图神经网络的知识增强文本分类

在线全文

学校读者我要写书评

暂无评论

计算机应用 2024年第S1期44卷 11-17页

作者：章巍陈学奇韩剑锋虞小江吴海燕浙江浙能临海海上风力发电有限公司浙江临海317000 杭州蓝城新能源科技有限公司杭州310000 浙江财经大学信息技术与人工智能学院杭州310018

句子分类方法主要分为基于特征工程的机器学习方法、序列化模型和结构化模型,但基于特征工程的机器学习方法对词序不敏感易产生稀疏向量,序列化模型忽略了句子的短语、依存关系等句法结构信息,结构化模型如句法树、二叉树等的准确率受... 详细信息

句子分类方法主要分为基于特征工程的机器学习方法、序列化模型和结构化模型,但基于特征工程的机器学习方法对词序不敏感易产生稀疏向量,序列化模型忽略了句子的短语、依存关系等句法结构信息,结构化模型如句法树、二叉树等的准确率受句法解析工具影响。针对上述问题,构建基于句法CYK(Cocke Younger Kasami)图神经网络(GNN)的知识增强文本分类模型S-CYK,对输入句子分别构建对应的短语树和CYK图以形成句法CYK图,并利用关系图注意力网络(RGAT)进行句子分类。在公共数据集AG’s News、DBpedia、ARP(Amazon Review Polarity)和ARF(Amazon Review Full)上的实验结果表明,与现有先进模型半监督变分自编码器(SSVAE)、对抗性微调BERT(AFTB)、基于GloVe的ABLSTM(GloVe+ABLSTM)和融合FastText的CNN(CNN with FastText)相比,S-CYK模型在4个数据集的准确率提升了0.04%~1.21%。S-CYK使用句法CYK图结构进行知识增强,能有效增强聚合句子信息的能力。

关键词：句法知识 CYK算法知识增强图神经网络文本分类

Evaluating soil nutrients of Dacrydium pectinatum in China using machine learning techniques

在线全文

学校读者我要写书评

暂无评论

Forest Ecosystems 2020年第3期7卷 378-391页

作者： Chunyan Wu Yongfu Chen xiaojiang Hong Zelin Liu Changhui Peng State Key Laboratory of Tree Genetics and Breeding Key Laboratory of Tree Breeding and Cultivation of the State Forestry AdministrationResearch Institute of ForestryChinese Academy of ForestryBeijing100091China Research Institute of Forest Resource Information Techniques Chinese Academy of ForestryBeijing100091China Hainan Bawangling National Natural Reserve Changjiang572722HainanChina Department of Biological Science Institute of Environment SciencesUniversity of Quebec at MontrealMontrealQCCanada

Background: The accurate estimation of soil nutrient content is particularly important in view of its impact on plant growth and forest regeneration. In order to investigate soil nutrient content and quality for the natural regeneration of Dacrydium pectinatum communities in China, designing advanced and accurate estimation methods is ***: This study uses machine learning techniques created a series of comprehensive and novel models from which to evaluate soil nutrient content. Soil nutrient evaluation methods were built by using six support vector machines and four artificial neural ***: The generalized regression neural network model was the best artificial neural network evaluation model with the smallest root mean square error(5.1), mean error(-0.85), and mean square prediction error(29). The accuracy rate of the combined k-nearest neighbors(k-NN) local support vector machines model(i.e. k-nearest neighbors-support vector machine(KNNSVM)) for soil nutrient evaluation was high, comparing to the other five partial support vector machines models investigated. The area under curve value of generalized regression neural network(0.6572) was the highest, and the cross-validation result showed that the generalized regression neural network reached 92.5%.Conclusions: Both the KNNSVM and generalized regression neural network models can be effectively used to evaluate soil nutrient content and quality grades in conjunction with appropriate model variables. Developing a new feasible evaluation method to assess soil nutrient quality for Dacrydium pectinatum, results from this study can be used as a reference for the adaptive management of rare and endangered tree species. This study, however, found some uncertainties in data acquisition and model simulations, which will be investigated in upcoming studies.

关键词： Support vector machine KNNSVM Generalized regression neural network Nutrient grade Rare and endangered tree species

660MW高水分褐煤锅炉超低负荷运行特性研究

在线全文

学校读者我要写书评

暂无评论

热力发电 2024年第5期53卷 82-92页

作者：李子祥张启超乌晓江叶妮娜许芸张忠孝上海交通大学机械与动力工程学院上海200240 上海能源建设工程设计研究有限公司上海200135 国家能源集团科学技术研究院有限公司南京210046

为揭示大容量高水分褐煤机组的超低负荷运行特性及性能优化方式,基于建立并验证的燃煤锅炉燃烧模型,研究了33%最大连续额定负荷下燃烧器运行方式对660 MW高水分褐煤锅炉炉内燃烧、传热及NO_(x)转化特性的影响。结果表明:超低负荷下炉内... 详细信息

为揭示大容量高水分褐煤机组的超低负荷运行特性及性能优化方式,基于建立并验证的燃煤锅炉燃烧模型,研究了33%最大连续额定负荷下燃烧器运行方式对660 MW高水分褐煤锅炉炉内燃烧、传热及NO_(x)转化特性的影响。结果表明:超低负荷下炉内仍可形成良好组织的流动及燃烧场,但锅炉综合性能显著下降,如燃烧温度及受热面吸热量显著降低、炉膛出口NO_(x)排放增加等;运行4层燃烧器时投运连续的下、中间组或中间、上组燃烧器,可有效防止燃烧、传热过程的显著恶化及NO_(x)排放的明显增加;燃烧器投运层数影响锅炉综合性能,运行2层燃烧器时炉内剧烈燃烧区域过于集中,不利于维持较高的燃烧温度及传热强度,炉膛出口NO_(x)排放升高。研究结果揭示了超低负荷下燃烧器投运位置及层数对660 MW高水分褐煤锅炉综合性能的影响,可为大规模可再生能源电力并网背景下高水分褐煤机组参与深度调峰的运行调整及优化提供指导。

关键词：褐煤超低负荷燃烧器位置燃烧器层数锅炉性能

冷轧双相钢DP590的连铸坯角部横裂纹研究

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

炼钢 2024年第5期40卷 81-88页

作者：李哲李岩杰田伟杨杰张大勇杨晓江河钢集团唐钢公司河北唐山063000

冷轧双相钢DP590连铸坯角部横裂纹给冷轧产品的质量带来很大困扰,导致其后续连退产品边部出现夹渣、翘皮或裂纹等缺陷。通过对连铸坯角部横裂纹部位进行观察,发现角部横裂纹发生在连铸坯的振谷部位,横裂纹向铸坯宽面和窄面有一定的延伸... 详细信息

冷轧双相钢DP590连铸坯角部横裂纹给冷轧产品的质量带来很大困扰,导致其后续连退产品边部出现夹渣、翘皮或裂纹等缺陷。通过对连铸坯角部横裂纹部位进行观察,发现角部横裂纹发生在连铸坯的振谷部位,横裂纹向铸坯宽面和窄面有一定的延伸,发生横裂纹的振谷通常是不规则振痕,其形貌带有横向的凹陷特征。通过连铸坯的枝晶侵蚀试验发现,连铸坯发生角部横裂纹的部位,二次枝晶间距大,裂纹处的连铸坯表面冷却速率显著低于正常的连铸坯表面,这说明连铸坯坯壳冷却均匀性需要改善。并且裂纹附近有明显异常粗大的枝晶间距,通过电子探针检测发现这些异常粗大枝晶间存在硫、锰的富集现象,说明这是凝固过程中枝晶间发生断裂,富集锰硫溶质的钢液补充形成的。结合浇铸的结晶器热电偶测量温度趋势,判断该型保护渣控制传热能力以及渣膜的稳定性不足。通过优化保护渣和提高铸坯拉速,消除了连铸坯凹陷和角部横裂纹。

关键词：角部横裂纹二次枝晶连铸坯横向凹陷 DP590钢

同方期刊数据库

Co-management of small-scale fishery in the Tonle Sap Lake,Cambodia

在线全文

学校读者我要写书评

暂无评论

Regional Sustainability 2021年第1期2卷 1-11页

作者： Serey Sok xiaojiang Yu Research Office Royal University of Phnom PenhRussian Federation BoulevardPhnom Penh12150Cambodia School of Geosciences University of SydneySydney2006Australia

In Cambodia,fishery co-management is an important process to transfer authority and ownership to the communities along the Tonle Sap Lake to manage *** paper aims to determine why the co-management of small-scale fishery has not been implemented satisfactorily in the Tonle Sap Lake of *** research was primarily based on a household survey among 404 house-holds for quantitative data,equally divided between the Cham(202 households)and Khmer(202 households).Participatory process was also applied to collect qualitative data from key *** found that limited interaction among the involved stakeholders,i.e.,unequal distribution of authority and resources co-management,has impeded *** engagement of fisherfolk was influenced by dependence on fishery,law enforcement,and events organized by the *** the Khmer had better opportunities to participate in planning at the provincial and district levels,the Cham were only engaged in local development activities initiated by their ***,the latter evinced a higher rate of satisfaction due to their access tofishery resources and to a large quantity of fishing *** the future,efforts should be made to:(1)improve resource and authority sharing among all key stakeholders;(2)urgently resolve issues pertinent to capacity building,insufficient budgets for commune councils(CoCs)and community fishery(CFi);and(3)urge law enforcement regarding illegal fishing.

关键词： Small-scale fishery Co-management Local planning process Community fishery Tonle Sap Lake

Effects of different introduction methods of Ce^4+and Zr^4+on denitration performance and anti-K poisoning performance of V2O5-WO3/TiO2 catalyst

在线全文

学校读者我要写书评

暂无评论

Journal of Rare Earths 2020年第11期38卷 1207-1214,I0003页

作者： Jun Cao xiaojiang Yao Li Chen Keke Kang Min Fu Yang Chen Research Center for Atmospheric Environment Key Laboratory of Reservoir Aquatic Environment of CASChongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China Chongqing Key Laboratory of Catalysis and New Environmental Materials College of Environment and ResourcesChongqing Technology and Business UniversityChongqing 400067China

The purpose of this work is to explore the effects of the introduction methods of Ce^4+and Zr^4+on the physicochemical properties,activity,and K tolerance of V2 O5-WO3/TiO2 catalyst for the selective catalytic reduction of NOx by *** different methods,namely pre-impregnation,post-impregnation,coimpregnation,and co-precipitation,were used to synthesize a series of V2 O5-WO3-TiO2-CeO2-ZrO2 *** catalysts were characterized by XRD,BET,NH3-TPD,XPS,and H2-TPR ***,the activity and anti-K poisoning performance were tested by an NH3-SCR model *** results show that the introduction of Ce^4+and Zr^4+can improve the catalytic performance of V2O5-WO3/TiO2 catalyst,but the impregnation method cannot enhance the anti-K poisoning ***^4+and Zr^4+introduced by co-precipitation method can effectively improve the tolerance of K,which is mainly due to the incorporation of Ce^4+and Zr^4+into TiO2 lattice to form a uniform TiO2-CeO2-ZrO2 solid solution,resulting in the optimal surface acidity and redox performance,and reducing the decreases caused by ***,based on the best introduction method,we further optimized the molar ratio of Ce^4+/Zr^4+,It is found that the catalyst exhibits the best anti-K poisoning performance when the molar ratio of Ce^4+/Zr^4+is 2:1.

关键词： V2O5-WO3/TiO2 denitration catalyst Ce^4+,Zr^4+modification Introduction methods Molar ratio Anti-K poisoning performance Rare Earths

Coupled Heat Transfer Simulation of the Spiral Water Wall in a Double Reheat Ultra-supercritical Boiler

在线全文

学校读者我要写书评

暂无评论

Journal of Thermal Science 2018年第6期27卷 592-601页

作者： DONG Jiancong ZHOU Tuo WU xiaojiang ZHANG Jian FAN Haojie ZHANG Zhongxiao School of Mechanical Engineering Shanghai Jiao Tong University Institute of Engineering Thermophysics Chinese Academy of Sciences Department of Research and Development Shanghai Boiler Works Co. Ltd.

This paper presented a coupled heat transfer model combining the combustion in the furnace and the ultra-supercritical(USC) heat transfer in the water wall tubes. The thermal analysis of the spiral water wall in a 1000 MW double reheat USC boiler was conducted by the coupled heat transfer simulations. The simulation results show that there are two peak heat flux regions on each wall of spiral water wall, where the primary combustion zone and burnt-out zone locate respectively. In the full load condition, the maximal heat flux of the primary combustion zone is close to 500 kW/m^2, which is higher than that in the conventional single reheat USC boilers. The heat flux along the furnace width presents a parabolic shape that the values in the furnace center are much higher than that in the corner regions. The distribution of water wall temperature has a perfect accordance with the heat flux distribution of the parabolic shape curves, which can illustrate the distribution of water wall temperature is mainly determined by heat flux on the water wall. The maximal water wall temperature occurs at the middle width of furnace wall and approaches 530°C, which can be allowed by the metal material of water wall tube 12Cr1MoVG. In the primary combustion zone, the wall temperatures in half load are almost close to the values in 75% load condition, caused by the heat transfer deterioration of the subcritical pressure fluid under the high heat flux condition. The simulation results in this study are beneficial to the better design and operational optimization for the double reheat USC boilers.

关键词： coupled model heat transfer spiral water wall double reheat ultra-supercritical

Application of Response Surface Methodology for Analysis of Reheat Steam Temperatures in a Double Reheat Coal-Fired Boiler

在线全文

学校读者我要写书评

暂无评论

Journal of Thermal Science 2022年第6期31卷 2203-2215页

作者： ZHANG Jian XU Wei ZHANG Zhongxiao FAN Haojie WU xiaojiang DONG Jiancong Institute of Thermal Energy Engineering School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Energy Research Institute Nanjing Institute of TechnologyNanjing211167China

For the improvement of reheat steam quality and performance of double reheat coal-fired utility boiler under wide load operation, a variety of temperature regulation ways were utilized to adjust the energy distribution between different heating surfaces. In this paper, thermodynamic calculation based on the fundamental heat transfer theory was conducted for the analysis of temperature regulation strategy effects to steam temperature. In consideration of the specific overlapping heating surface arrangement, the compartment model was adopted to solve this problem. Response surface methodology(RSM) was used to analysis the effect of each temperature regulating variables on the steam temperature and boiler efficiency;then the polynomial model was fitted to predict the primary and secondary steam temperature simultaneously. Results showed that the flue gas recirculation rate has a relatively significant influence on the steam temperature, the maximum temperature deviation between fitting value and calculation value is 3.85℃ in 75% THA;the quadratic model can well predict the steam temperature under different operation conditions in wide load change. The variation of flue gas baffle has a significant influence on the boiler efficiency, compared to the flue gas recirculation and angle of burner oscillation. The influence of various factors on the reheat steam temperature is flue gas baffle > flue gas recirculation > angle of burner oscillation.

关键词： reheat steam temperature flue gas baffle flue gas recirculation response surface methodology coal-fired boiler