检索结果-南通市图书馆

Generative pre-trained transformers(GPT)-based automated data mining for building energy management:Advantages,limitations and the future

引用

Energy and Built Environment 2024年第1期5卷 143-169页

作者： chaobo zhang Jie Lu Yang Zhao Institute of Refrigeration and Cryogenics Zhejiang UniversityHangzhouChina Department of the Built Environment Eindhoven University of TechnologyEindhovenThe Netherlands Key Laboratory of Clean Energy and Carbon Neutrality of Zhejiang Province Jiaxing Research InstituteZhejiang UniversityJiaxingChina

Advanced data mining methods have shown a promising capacity in building energy ***,in the past decade,such methods are rarely applied in practice,since they highly rely on users to customize solutions according to the characteristics of target building energy ***,the major barrier is that the practical applications of such methods remain *** is necessary to enable computers to have the human-like ability to solve data mining *** pre-trained transformers(GPT)might be capable of addressing this issue,as some GPT models such as GPT-3.5 and GPT-4 have shown powerful abilities on interaction with humans,code generation,and inference with common sense and domain *** study explores the potential of the most advanced GPT model(GPT-4)in three data mining scenarios of building energy management,i.e.,energy load prediction,fault diagnosis,and anomaly detection.A performance evaluation framework is proposed to verify the capabilities of GPT-4 on generating energy load prediction codes,diagnosing device faults,and detecting abnormal system operation *** is demonstrated that GPT-4 can automatically solve most of the data mining tasks in this domain,which overcomes the barrier of practical applications of data mining methods in this *** the exploration of GPT-4,its advantages and limitations are also discussed comprehensively for revealing future research directions in this domain.

关键词： ChatGPT GPT-4 Artificial general intelligence Data mining Building energy management

来源：

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

干湿交替下黄土区苜蓿根系抗拔力学性能

引用

水土保持研究 2024年第1期31卷 214-223页

作者：黄梦琦张超波丁阳张强冯潇慧蒋静太原理工大学水利科学与工程学院太原030024

[目的]研究黄土区干湿交替过程对草本植物根系抗拔力学性能的影响,以期为草本植物根系固土护坡工程提供一定的理论支持和依据。[方法]选取紫花苜蓿为研究对象,采用重塑土根系拉拔试验,研究苜蓿根系抗拔力学性能及其与根径、根长、土壤... 详细信息

[目的]研究黄土区干湿交替过程对草本植物根系抗拔力学性能的影响,以期为草本植物根系固土护坡工程提供一定的理论支持和依据。[方法]选取紫花苜蓿为研究对象,采用重塑土根系拉拔试验,研究苜蓿根系抗拔力学性能及其与根径、根长、土壤容重、干湿交替作用等影响因素的关系。[结果](1)苜蓿根系抗拔力学性能指标与根径、根长和土壤容重存在幂函数或指数函数关系。(2)相比未干湿交替试样,干湿交替试样根系抗拔力学性能指标均显著减小。(3)砂壤土中苜蓿根系抗拔力学性能指标均优于壤土,且干湿交替在砂壤土中对苜蓿根系抗拔力学性能指标的影响小于在壤土中的影响。(4)根径、根长及容重和干湿交替的耦合作用对根系抗拔力学性能指标有显著影响。[结论]在干湿交替作用下,根径、根长和土壤容重对苜蓿根系抗拔力学性能有一定影响。

关键词：干湿交替苜蓿根系抗拔力学性能耦合影响

来源：

维普期刊数据库

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

微波强化中和铅锌冶炼渣干燥机制研究

引用

中国有色冶金 2024年第1期53卷 81-87页

作者：张朝波杨坤尹为波付光张特云南驰宏锌锗股份有限公司云南曲靖655011 昆明理工大学冶金与能源工程学院云南昆明650093

针对现行铅锌冶炼渣干燥周期长、过程污染大等问题,本文提出微波强化干燥新工艺,在分析原料物性状态的基础上,对中和铅锌冶炼渣高温介电及微波干燥影响因素进行分析,明确了微波强化中和铅锌冶炼渣干燥过程机制。结果表明,中和铅锌冶炼... 详细信息

针对现行铅锌冶炼渣干燥周期长、过程污染大等问题,本文提出微波强化干燥新工艺,在分析原料物性状态的基础上,对中和铅锌冶炼渣高温介电及微波干燥影响因素进行分析,明确了微波强化中和铅锌冶炼渣干燥过程机制。结果表明,中和铅锌冶炼渣中含有结晶水的物相为CaSO_(4)·0.5H_(2)O,自由水含量为30.2%,结晶水含量为7.2%,自由水与结晶水的吸波性能相似,且明显优于渣中其他物相;在粒径8 cm、厚度2.2 cm、微波功率700 W、干燥时间15 min条件下,微波干燥中和铅锌冶炼渣效果最优,自由水完全去除,结晶水去除率达到53.06%,总失水率为34.02%;微波干燥中和铅锌冶炼渣时,会引起中和铅锌冶炼渣的破裂分层,有助于实现快速高效干燥;相较常规干燥,微波干燥1 kg中和铅锌冶炼渣节约能耗16.98%(630 kJ),比常规多脱除5.40%的水分,干燥时间缩短87.5%。本论文所建立中和铅锌冶炼渣干燥技术具有明显优势。

关键词：中和铅锌冶炼渣微波介电特性干燥机制吸波性能脱水

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A multi agent-based optimal control method for combined cooling and power systems with thermal energy storage

引用

Building Simulation 2021年第6期14卷 1709-1723页

作者： Zihao Wang chaobo zhang Hongbo Li Yang Zhao State Key Laboratory of Air-Conditioning Equipment and System Energy Conservation ZhuhaiChina Guangdong Key Laboratory of Refrigeration Equipment and Energy Conservation Technology ZhuhaiChina Institute of Refrigeration and Cryogenics Zhejiang UniversityHangzhouChina

Combined cooling,heating and power(CCHP)systems have been considered as a potential energy saving technology for buildings due to their high energy efficiency and low carbon *** energy storage(TES)can improve the energy efficiency of CCHP systems,since they reduce the mismatch between the energy supply and ***,it also increases the complexity of operation optimization of CCHP *** this study,a multi-agent system(MAS)-based optimal control method is proposed to minimize the operation cost of CCHP systems combined with *** types of agents,i.e.,coordinator agents,building agents,energy management agents and optimization agents,are implemented in the MAS to cooperate with each *** operation optimization problem is solved by the genetic algorithm.A simulated system is utilized to validate the performance of the proposed *** show that the operation cost reductions of 10.0%on a typical summer day and 7.7%on a typical spring day are achieved compared with a rule-based control method.A sensitivity analysis is further performed and results show that the optimal operation cost does not change obviously when the rated capacity of TES exceeds a threshold.

关键词： multi-agent systems distributed control-operation optimization demand response combined cooling,heating and power system thermal energy storage

来源：

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

A real-time abnormal operation pattern detection method for building energy systems based on association rule bases

引用

Building Simulation 2022年第1期15卷 69-81页

作者： chaobo zhang Yang Zhao Yangze Zhou Xuejun zhang Tingting Li Institute of Refrigeration and Cryogenics Zhejiang UniversityHangzhouChina Chu Kochen Honors College Zhejiang UniversityHangzhouChina

Expert systems are effective for anomaly detection in building energy ***,it is usually inefficient to establish comprehensive rule bases manually for complex building energy *** rule mining is available to accelerate the establishment of the rule bases due to its powerful capability of discovering rules from numerous *** paper proposes a real-time abnormal operation pattern detection method towards building energy *** can benefit from both expert systems and association rule *** rules are utilized to establish association rule bases of abnormal and normal operation *** established rule bases are then utilized to develop an expert system for real-time detection of abnormal operation *** proposed method is applied to an actual chiller plant for evaluating its *** show that 15 types of known abnormal operation patterns and 11 types of unknown abnormal operation patterns are detected successfully by the proposed method.

关键词： building energy systems building energy conservation expert systems association rule mining anomaly detection

来源：

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

Vertical root distribution and root cohesion of typical tree species on the Loess Plateau, China

引用

Journal of Arid Land 2014年第5期6卷 601-611页

作者： chaobo zhang LiHua CHEN Jing JIANG College of Water Resources Science and Engineering Taiyuan University of Technology Key Laboratory of Soil and Water Conservation and Combating Desertification of Ministry of Education of China School ofWater and Soil Conservation Beijing Forestry University

Black locust（Robinia pseudoacacia L.） and Chinese pine（Pinus tabulaeformis Carr.） are two woody plants that are widely planted on the Loess Plateau for controlling soil erosion and land desertification. In this study, we conducted an excavation experiment in 2008 to investigate the overall vertical root distribution characteristics of black locust and Chinese pine. We also performed triaxial compression tests to evaluate the root cohesion（additional soil cohesion increased by roots） of black locust. Two types of root distribution, namely, vertical root（VR） and horizontal root（HR）, were used as samples and tested under four soil water content（SWC） conditions（12.7%, 15.0%, 18.0% and 20.0%, respectively）. Results showed that the root lengths of the two species were mainly concentrated in the root diameter of 5–20 mm. A comparison of root distribution between the two species indicated that the root length of black locust was significantly greater than that of Chinese pine in nearly all root diameters, although the black locust used in the comparison was 10 years younger than the Chinese pine. Root biomass was also significantly greater in black locust than in Chinese pine, particularly in the root diameters of 3–5 and 5–10 mm. These two species were both found to be deep-rooted. The triaxial compression tests showed that root cohesion was greater in the VR samples than in the HR samples. SWC was negatively related to both soil shear strength and root cohesion. These results could provide useful information on the architectural characteristics of woody root system and expand the knowledge on shallow slope stabilization and soil erosion control by plant roots on the Loess Plateau.

关键词： root distribution root cohesion root extinction coefficient soil erosion soil reinforcement Loess Plateau

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Federated learning-based short-term building energy consumption prediction method for solving the data silos problem

引用

Building Simulation 2022年第6期15卷 1145-1159页

作者： Junyang Li chaobo zhang Yang Zhao Weikang Qiu Qi Chen Xuejun zhang Institute of Refrigeration and Cryogenics Zhejiang UniversityHangzhouChina Department of Energy Engineering Zhejiang UniversityHangzhouChina Zhejiang Energy Group Co. Ltd.HangzhouChina

Transfer learning is an effective method to predict the energy consumption of information-poor buildings by learning transferable knowledge from operational data of information-rich ***,it is not recommended to directly use the operational data without protection due to the risk of leaking occupants’*** address this problem,this study proposes a federated learning-based method to learn transferable knowledge from building operational data without privacy *** trains a transferable federated model based on the operational data from the buildings similar to the target building with limited *** advanced secure aggregation algorithm is adopted in the training process to ensure that no one can infer private information from the training *** federated model obtained is evaluated by comparing it with the standalone model without federated learning based on 13 similar office buildings from the Building Data Genome *** results show that the federated model outperforms the standalone model concerning the prediction accuracy and training *** average,the federated model achieves a 25.4%decrease in CV-RMSE when the target building has limited operational *** if the target building has no operational data,the federated model still achieves acceptable accuracy(CV-RMSE is 22.2%).Meanwhile,the training time of the federated model is 90%less than that of the standalone *** research insights can help develop federated learning-based methods for solving the data silos problem in building energy *** methodology and analysis procedures are reproducible and all codes and data sets are available on Github.

关键词： building energy consumption prediction federated learning transfer learning data privacy protection data silos

来源：

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

Effects of loading rate on root pullout performance of two plants in the eastern Loess Plateau,China

引用

Journal of Arid Land 2023年第9期15卷 1129-1142页

作者： zhang chaobo LI Rong JIANG Jing YANG Qihong College of Water Resources Science and Engineering Taiyuan University of TechnologyTaiyuan 030024China Key Laboratory of the Regulation and Flood Control of Middle and Lower Reaches of the Changjiang River under Ministry of Water Resources Changjiang River Scientific Research InstituteWuhan 430010China

Root pullout performance of plants is an important mechanical basis for soil reinforcement by plant roots in the semi-arid *** have shown that it is affected by plant factors(species,ages,root geometry,etc.)and soil factors(soil types,soil moisture,soil bulk densities,etc.).However,the effects of loading rates on root pullout performance are not well *** explore the mechanical interactions under different loading rates,we conducted pullout tests on Medicago sativa *** Hippophae rhamnoides *** under five loading rates,i.e.,5,50,100,150,and 200 mm/*** addition,tensile tests were conducted on the roots in diameters of 0.5-2.0 mm to compare the relationship between root tensile properties and root pullout *** showed that two root failure modes,slippage and breakage,were observed during root pullout *** *** roots were pulled out,while 72.2%of *** roots were *** maximum fracture diameter and fracture root length of *** were 1.22 mm and 7.44 cm under 100 mm/min loading rate,*** displacement values were 4.63%(±0.43%)and 8.91%(±0.52%)of the total root length for *** and ***,*** values of maximum pullout force were 14.6(±0.7)and 17.7(±1.8)N under 100 mm/min for *** and ***,*** of the maximum pullout strength for *** and *** were 38.38(±5.48)MPa under 150 mm/min and 12.47(±1.43)MPa under 100 mm/min,***-soil friction coefficient under 100 mm/min was significantly larger than those under other loading rates for both the two *** of the maximum root pullout energy for *** and *** were 87.83(±21.55)mm•N under 100 mm/min and 173.53(±38.53)mm•N under 200 mm/min,*** pullout force was significantly related to root diameter(P<0.01).Peak root pullout force was significantly affected by loading rates when the effect of root diameter was included(P<0.01),and vice *** fo

关键词： plant roots soil reinforcement loading rate root pullout properties root-soil interaction loess area

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Probabilistic graphical models in energy systems:A review

引用

Building Simulation 2022年第5期15卷 699-728页

作者： Tingting Li Yang Zhao Ke Yan Kai Zhou chaobo zhang Xuejun zhang Institute of Refrigeration and Cryogenics Zhejiang UniversityHangzhouChina Department of Building School of Design and EnvironmentNational University of Singapore4 Architecture DriveSingapore Zhejiang Energy Gas Group Co. LtdHangzhouChina

Probabilistic graphical models(PGMs)can effectively deal with the problems of energy consumption and occupancy prediction,fault detection and diagnosis,reliability analysis,and optimization in energy *** with the black-box models,PGMs show advantages in model interpretability,scalability and *** have great potential to realize the true artificial intelligence in energy systems of the next *** paper intends to provide a comprehensive review of the PGM-based approaches published in the last *** reveals the advantages,limitations and potential future research directions of the PGM-based approaches for energy *** types of PGMs are summarized in this review,including static models(SPGMs)and dynamic models(DPGMs).SPGMs can conduct probabilistic inference based on incomplete,uncertain or even conflicting ***-based approaches are proposed to deal with various management tasks in energy *** show outstanding performance in fault detection and diagnosis of energy *** can represent a dynamic and stochastic process by describing how its state changes with ***-based approaches have high accuracy in predicting the energy consumption,occupancy and failures of energy *** the future,a unified framework is suggested to fuse the knowledge-driven and data-driven PGMs for achieving better *** PGM-based approaches are needed that can be adapted to various energy *** algorithms would outperform the basic PGMs by integrating advanced techniques such as deep learning and first-order logic.

关键词： probabilistic graphical model energy system Bayesian network-dynamic Bayesian network Markov chain hidden Markov model

来源：

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

湿法炼锌酸浸液中铜锗的分离工艺及行为研究

引用

有色金属（冶炼部分） 2024年第10期 98-105页

作者：张朝波邓志敢保雪凡张程戴兴征付光张特魏昶云南驰宏锌锗股份有限公司云南曲靖655011 昆明理工大学冶金与能源工程学院昆明650093

在常规湿法炼锌工艺的中性浸出—酸浸逆流浸出过程中,酸浸液返回中性浸出时会导致酸浸液中的少部分铜和大部分锗沉淀进入中浸渣,造成铜的回收率低、锗未能直接分离富集。针对锌焙砂酸浸液中铜、锗的分离富集,研究酸浸液直接置换沉铜—... 详细信息

在常规湿法炼锌工艺的中性浸出—酸浸逆流浸出过程中,酸浸液返回中性浸出时会导致酸浸液中的少部分铜和大部分锗沉淀进入中浸渣,造成铜的回收率低、锗未能直接分离富集。针对锌焙砂酸浸液中铜、锗的分离富集,研究酸浸液直接置换沉铜—中和沉淀富集锗工艺及过程中铜和锗的分离行为。结果表明:较低pH和较高铁粉加入量时会使得酸浸液中的铜和锗共沉淀;在溶液pH为1.5~2.0、铁粉加入系数为1.2、温度70℃的条件下反应20 min可实现溶液中铜和锗的有效分离,铜、锗的沉淀率分别为96.53%和2.51%;溶液中的砷与铜共同沉淀,置换渣中主要物相为Cu_(3)As和Cu_(2)O,置换渣中铜的质量分数为58.02%。沉铜后液在H_(2)O_(2)用量5 mL/L、温度70℃、时间2.5 h、终点pH为5.0~5.2的条件下,中和后液中铜、铁、锗的含量分别为16.52、1.39和0.43 mg/L,满足后续净化的要求;中和渣含锗2 501.40 g/t,可作为回收锗的原料。

关键词：锌焙砂酸浸液置换沉铜中和沉锗分离

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：