检索结果-南通市图书馆

维普期刊数据库博看期刊

Bioinspired synthesis of cochlearol B and ganocin A

在线全文

学校读者我要写书评

暂无评论

Chinese Chemical Letters 2024年第7期35卷 242-246页

作者： zhenhao Wang Yuliang tang Ruyu Li Shuai Tian Yu tang Dehai Li Key Laboratory of Marine Drugs Chinese Ministry of Education/Sanya Oceanographic Institute Ocean University of ChinaQingdao 266003/Sanya 572025China Laboratory for Marine Drugs and Bioproducts Pilot National Laboratory for Marine Science and TechnologyQingdao 266237China Marine Biomedical Research Institute of Qingdao Ocean University of ChinaQingdao 266071China

Described here is a divergent,biosynthetically inspired synthesis of cochlearol B and ganocin *** steps of the synthesis include the chromene unit construction through a biomimetic acid-catalyzed[4+2]ring cyclization.A photochemical[2+2]cycloaddition was featured to construct the cyclobutane core of cochlearol *** skeletal rearrangements of cochlearol B afforded ganocin A,that one of them was Lewis acid mediated epoxide rearrangement and another was DDQ induced cyclobutane formed tetrahydrofuran *** described syntheses not only achieved these natural products in an efficient manner,but also provided insight into the biosynthetic relationship between the two different skeletons.

关键词： Biomimetic rearrangement Avarane skeleton Cascade reactions Lewis acid Total synthesis

Modeling NOx Emission of Coal-fired Boiler with Differential Evolution Optimized Least Square Support Vector Machine

在线全文

学校读者我要写书评

暂无评论

Modeling NOx Emission of Coal-fired Boiler with Differential...

第30届中国控制与决策会议

作者： zhenhao tang Haiyang Zhang College of Automation Engineering Northeast Electric Power University

The NO emission is one of the major air pollutants of thermal power plants. Due to the complexity of the boiler production process, the NO emission was related with many parameters(such as, primary air flow, fuel flow). Building a NO emission prediction is the basis of combustion optimization and emission reduction. A least square support vector machine(LSSVM) model was developed and verified. Good prediction performance was achieved with the proper learning parameters which were chosen by a differential evolution(DE) algorithm. To illustrate the effectiveness of the DELSSVM, BP neural networks, Multi-layer perceptron(MLP) and partial least squares(PLS) regression algorithm were employed to make a comparison. Experimental results show that the DE optimized LSSVM(DELSSVM) has a promising performance in the prediction of the NO emission.

关键词： Coal-fired Boiler NOx Emission Least Square Support Vector Machine Differential Evolution

Modeling the superheated steam temperature with a data-driven based approach

在线全文

cnki会议

学校读者我要写书评

暂无评论

Modeling the superheated steam temperature with a data-drive...

第30届中国控制与决策会议

作者： zhenhao tang Mingxuan YANG Bo Zhao College of Automation Engineering Northeast Electric Power University

Superheated steam temperature is a vital factor that affects the power generation efficiency. A data-driven based approach is proposed to modeling the superheated steam temperature. The ReliefF algorithm is employed to select the input features. In addition, a back propagation neural network（BP） model with parameters optimized by genetic algorithm（GA） is proposed to constructed the prediction model. Experiment results demonstrate that the proposed method can get better forecasting results in comparison with the PSO-BP（particle swarm optimized back propagation neural network）, linear regression approach and the MLP（multi-layer perceptron） approach.

关键词： Superheated steam temperature Genetic algorithm Back propagation Modeling

一种基于卷积特征的NO_(x)排放浓度深度预测模型

在线全文

cnki会议

学校读者我要写书评

暂无评论

中国电机工程学报 2023年第21期43卷 8356-8365页

作者：唐振浩张佳宁沈涛东北电力大学自动化工程学院吉林省吉林市132012 哈尔滨锅炉厂有限责任公司黑龙江省哈尔滨市150040

为提高燃煤锅炉出口NO_(x)排放浓度的预测精度,该文提出一种基于卷积特征提取的NO_(x)排放浓度深度学习预测模型。首先,分析锅炉燃烧产生NO_(x)的机理,确定模型初选变量;然后,计算不同初选变量与NO_(x)排放浓度之间的最大相关系数,确定... 详细信息

为提高燃煤锅炉出口NO_(x)排放浓度的预测精度,该文提出一种基于卷积特征提取的NO_(x)排放浓度深度学习预测模型。首先,分析锅炉燃烧产生NO_(x)的机理,确定模型初选变量;然后,计算不同初选变量与NO_(x)排放浓度之间的最大相关系数,确定变量延迟时间;其次,为挖掘输入变量深层交互信息,设计二维卷积网络进行特征提取,获得高维预测模型输入候选集合;同时,通过偏最小二乘法计算候选集变量与NO_(x)排放浓度之间相关性,降低输入变量维数,确定最终模型的输入变量;最后,设计深度神经网络建立NO_(x)排放预测模型,预测NO_(x)排放浓度。基于1000MW锅炉实际运行数据的实验结果表明,所提出卷积深度神经网络预测算法的平均相对百分比误差小于4%,预测精度能够满足实际生产的需求。

关键词：锅炉燃烧卷积特征提取 NO_(x)排放浓度深度学习时间延迟

Short-Term Wind Power Prediction Based on RF-VMD-ELM

在线全文

学校读者我要写书评

暂无评论

Short-Term Wind Power Prediction Based on RF-VMD-ELM

第31届中国过程控制会议（CPCC2020）

作者： DONG Jiayuan tang zhenhao CAO Shengxian BU Bing HAN Hongzhi School of Automation Engineering Northest Electric Power University Guodian Hefeng Wind Power Development Co. Ltd.

Due to the time variability of wind speed and the influence of meteorological factors, the output power of wind turbines fluctuates, which poses challenges to the safe operation of power systems. Therefore, how to accurately predict short-term wind power has become the primary issue. For short-term wind power modeling, an extreme learning machine prediction model is proposed based on random forest feature selection and variational mode decomposition feature *** the first part, the wind power is used as the reference variable, then the random forest algorithm is utilized to filter and to select the input variables to be exploited in the feature extraction part. Next, the input variables are subjected to variational mode decomposition and the main frequency information is extracted as the final input variable of the prediction model. In the second part, an extreme learning machine is utilized to establish a prediction model with the use of input variables processed above, then the prediction performance of the model is evaluated. It can be realized form the experimental results that the proposed short-term wind power forecasting model has good forecasting accuracy compared with other models.

关键词： short-term wind power prediction variational mode decomposition random forest extreme learning machine

基于动态时延分析和典型样本筛选的NO_(x)排放浓度预测

在线全文

cnki会议

学校读者我要写书评

暂无评论

中国电机工程学报 2023年第9期43卷 3488-3497页

作者：李悦唐振浩曹生现沈涛东北电力大学自动化工程学院吉林省吉林市132012 哈尔滨锅炉厂有限责任公司黑龙江省哈尔滨市150040

选择性催化还原(selectivecatalyticreduction,SCR)是一个变时间延迟的动态过程。为建立准确SCR出口NO_(x)排放浓度预测模型,提出一种基于动态时延分析和典型样本筛选的建模算法。首先,通过机理分析和实际生产数据Pearson相关性分析,确... 详细信息

选择性催化还原(selectivecatalyticreduction,SCR)是一个变时间延迟的动态过程。为建立准确SCR出口NO_(x)排放浓度预测模型,提出一种基于动态时延分析和典型样本筛选的建模算法。首先,通过机理分析和实际生产数据Pearson相关性分析,确定模型输入变量。然后,采用时间滑动窗口策略,计算滑动时间窗口内变量互信息熵,根据互信息熵排序确定各变量对于NO_(x)排放浓度的动态延迟时间。其次,为了降低建模样本数量,采用K-Means聚类算法对时延分析后的样本集合进行筛选,筛选出具有代表性和多样性的典型运行数据样本。最后,设计极限学习机算法,构建SCR系统出口NO_(x)动态预测模型。基于1000MW超超临界锅炉运行数据的验证结果显示,所提算法的预测误差小于5%,能够对SCR系统出口NO_(x)浓度进行准确预测。

关键词：滑动窗口选择性催化还原互信息 K-Means聚类动态预测

基于数据驱动和智能优化的高炉十字测温温度预报

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

信息与控制 2014年第3期43卷 355-360页

作者：唐振浩唐立新杨阳东北大学物流优化与控制研究所辽宁沈阳110819 东北大学流程工业综合自动化国家重点实验室辽宁沈阳110819 东北大学制造系统与物流优化辽宁省重点实验室辽宁沈阳110819

采用基于最小二乘支持向量机(LS-SVM)的数据驱动方法建立高炉十字测温温度模型.首先通过对数据的相关性分析,选择与十字测温相关的输入变量;再用改进的智能优化算法(粒子群算法)来优化LS-SVM的参数,从而提高预测模型的精度;最后得到十... 详细信息

采用基于最小二乘支持向量机(LS-SVM)的数据驱动方法建立高炉十字测温温度模型.首先通过对数据的相关性分析,选择与十字测温相关的输入变量;再用改进的智能优化算法(粒子群算法)来优化LS-SVM的参数,从而提高预测模型的精度;最后得到十字测温温度的LS-SVM预测模型.根据生产现场实际数据进行的实验表明,基于相关性分析的输入量选取能够在不影响预测精度的情况下降低计算复杂度;与常用的网格法相比,本文方法所建立的十字测温数据驱动模型精度提高3%,能够满足生产需要.

关键词：高炉十字测温最小二乘支持向量机粒子群优化算法数据驱动

基于数据驱动的燃煤锅炉NO_(x)排放浓度动态修正预测模型

在线全文

学校读者我要写书评

暂无评论

中国电机工程学报 2022年第14期42卷 5182-5193页

作者：唐振浩朱得宇李扬东北电力大学自动化工程学院吉林省吉林市132012 东北电力大学电气工程学院吉林省吉林市132012

NO_(x)浓度实时预测对于燃煤电厂污染物排放控制和机组运行具有重要意义。为了克服燃烧过程大时延及强非线性特性,提出一种考虑时间延迟的动态修正预测模型。利用最大信息系数(maximum information coefficient MIC)计算相关参数与NO_(x... 详细信息

NO_(x)浓度实时预测对于燃煤电厂污染物排放控制和机组运行具有重要意义。为了克服燃烧过程大时延及强非线性特性,提出一种考虑时间延迟的动态修正预测模型。利用最大信息系数(maximum information coefficient MIC)计算相关参数与NO_(x)浓度的延迟时间,重构建模数据集;然后,构建基于Lasso和ReliefF的自适应特征选择算法,筛选与NO_(x)浓度相关程度高的参数;最后,建立结合误差校正的极限学习机(extreme learning machine,ELM)模型,达到动态预测氮氧化物浓度的目的。基于实际数据的实验结果表明:相同变量在升、降、平稳等负荷工况下的延迟时间不同;且不同负荷工况下模型特征变量存在差异;动态误差校正策略有效提升建模精度;所提出算法在不同工况下的预测误差均小于2%,能够准确预测燃烧出口的NO_(x)浓度,为NO_(x)排放监测和燃烧过程优化提供指导。

关键词： NO_(x)排放特征选择极限学习机误差修正数据驱动

NOx Emission Prediction Model of Coal-fired Boiler Based on Extreme Learning Machine and Error Correction

在线全文

学校读者我要写书评

暂无评论

NOx Emission Prediction Model of Coal-fired Boiler Based on ...

第31届中国过程控制会议（CPCC2020）

作者： ZHU Deyu tang zhenhao CHAI Xiangying MU Zhonghua PANG Xiaoya HAN Hongzhi School of Automation Engineering Northeast Electric Power University Electric Power Research Institute State Grid Gansu Electric Power Corporation

The real-time prediction of NOx emission is very important for the emissions reduction of coal-fired power plants. Therefore, a NOx prediction method based on extreme learning machine is proposed. First of all, according to the characteristics of boiler combustion, time delay is computed in data processing. Then, a Lasso combined with ReliefF feature selection method is proposed to select the basic set and candidate set. Finally, an extreme learning machine(ELM)combined with error correction model is established to predict the NOx emission. The experimental results based on practical data show that the proposed method is effective to predict NOx emissions.

关键词： NOx emission feature selection extreme learning machine error correction data-driven