检索结果-南通市图书馆

Short-term Residential Load Forecasting Based on K-shape Clustering and Domain Adversarial Transfer Network

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

Journal of Modern Power Systems and Clean Energy 2024年第4期12卷 1239-1249页

作者： Jizhong Zhu Yuwang miao Hanjiang Dong Shenglin Li Ziyu Chen Di Zhang School of Electric Power Engineering South China University of TechnologyGuangzhou 510641China Department of Electrical Engineering The Hong Kong Polytechnic UniversityHong KongChina

In recent years,the expansion of the power grid has led to a continuous increase in the number of consumers within the distribution ***,due to the scarcity of historical data for these new consumers,it has become a com-plex challenge to accurately forecast their electricity demands through traditional forecasting *** paper proposes an innovative short-term residential load forecasting method that harnesses advanced clustering,deep learning,and transfer learning technologies to address this *** begin,this paper leverages the domain adversarial transfer *** employs limited data as target domain data and more abundant data as source domain data,thus enabling the utilization of source do-main insights for the forecasting task of the target ***,a K-shape clustering method is proposed,which effec-tively identifies source domain data that align optimally with the target domain,and enhances the forecasting ***-sequently,a composite architecture is devised,amalgamating at-tention mechanism,long short-term memory network,and seq2seq *** composite structure is integrated into the domain adversarial transfer network,bolstering the perfor-mance of feature extractor and refining the forecasting *** illustrative analysis is conducted using the residential load dataset of the Independent System Operator to validate the proposed method *** the case study,the relative mean square error of the proposed method is within 30 MW,and the mean absolute percentage error is within 2%.A signifi-cant improvement in accuracy,compared with other compara-tive experimental results,underscores the reliability of the pro-posed *** findings unequivocally demonstrate that the proposed method advocated in this paper yields superior fore-casting results compared with prevailing mainstream forecast-ing methods.

关键词： Load forecasting domain adversarial K-shape clustering long short-term memory network seq2seq network attention mechanism

Prediction of damage potential in mainshock–aftershock sequences using machine learning algorithms

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

Earthquake Engineering and Engineering Vibration 2024年第4期23卷 919-938页

作者： Zhou Zhou Wang Meng Han miao Yu Xiaohui Lu Dagang School of Civil and Transportation Engineering Beijing University of Civil Engineering and ArchitectureBeijing 100044China Multi-Functional Shaking Tables Laboratory Beijing University of Civil Engineering and ArchitectureBeijing 100044China College of Civil Engineering Tongji UniversityShanghai 200092China College of Civil Engineering and Architecture Guilin University of TechnologyGuilin 541004China School of Civil Engineering Harbin Institute of TechnologyHarbin 150090China

Assessing the potential damage caused by earthquakes is crucial for a community’s emergency *** this study,four machine learning(ML)methods—random forest,extremely randomized trees,AdaBoost(AB),and gradient boosting(GB)—were employed to develop prediction models for the damage potential of the mainshock(DIMS)and mainshock–aftershock sequences(DIMA).Building structures were modeled using eight single-degree-of-freedom(SDOF)systems with different hysteretic rules.A set of 662 recorded mainshock–aftershock(MS-AS)ground motions was selected from the PEER *** intensity measures(IMs)were chosen to represent the characteristics of the mainshock and *** results revealed that the selected ML methods can well predict the structural damage potential of the SDOF systems,except for the AB *** GB model exhibited the best performance,making it the recommended choice for predicting DIMS and DIMA among the four ML ***,the impact of input variables in the prediction was investigated using the shapley additive explanations(SHAP)*** high-correlation variables were sensitive to the structural period(T).At T=1.0 s,the mainshock peak ground velocity(PGVM)and aftershock peak ground displacement(PGDA)significantly influenced the prediction of *** T increased to 5.0 s,the primary high-correlation factor of the mainshock IMs changed from PGVM to the mainshock peak ground displacement(PGDM);however,the highcorrelation variable of the aftershock IMs remained *** high-correlation factors for DIMS showed trends similar to those of ***,a table summarizing the first and second high-correlation variables for predicting DIMS and DIMA were provided,offering a valuable reference for parameter selection in seismic damage prediction for mainshock–aftershock sequences.

关键词： machine learning mainshock-aftershock damage potential prediction the high-correlation variables SDOF systems

Multi-granularity feature enhancement network for maritime ship detection

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第3期9卷 649-664页

作者： Li Ying Duoqian miao Zhifei Zhang Hongyun Zhang Witold Pedrycz Department of Computer Science and Technology Tongji UniversityShanghaiChina Project Management Office of China National Scientific Seafloor Observatory Tongji UniversityShanghaiChina Department of Electrical and Computer Engineering AlbertaEdmontonCanada System Research Institute Polish Academy of SciencesWarsawPoland

Due to the characteristics of high resolution and rich texture information,visible light images are widely used for maritime ship ***,these images are suscep-tible to sea fog and ships of different sizes,which can result in missed detections and false alarms,ultimately resulting in lower detection *** address these issues,a novel multi-granularity feature enhancement network,MFENet,which includes a three-way dehazing module(3WDM)and a multi-granularity feature enhancement module(MFEM)is *** 3WDM eliminates sea fog interference by using an image clarity automatic classification algorithm based on three-way decisions and FFA-Net to obtain clear image ***,the MFEM improves the accuracy of detecting ships of different sizes by utilising an improved super-resolution reconstruction con-volutional neural network to enhance the resolution and semantic representation capa-bility of the feature maps from *** results demonstrate that MFENet surpasses the other 15 competing models in terms of the mean Average Pre-cision metric on two benchmark datasets,achieving 96.28%on the McShips dataset and 97.71%on the SeaShips dataset.

关键词： object classification object recognition rough sets rough set theory

Rapid analysis of metal ions and organic compounds in strong acidic solutions by nano-ESI mass spectrometry

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

Chinese Chemical Letters 2024年第2期35卷 516-520页

作者： Jiaquan Xu Ting Li Zhendong Yu lili Song Xiu-Xiu Xu Hui Li Jiangxi Key Laboratory for Mass Spectrometry and Instrumentation East China University of TechnologyNanchang 330013China Department of Rehabilitation Medicine The First Affiliated Hospital of Nanchang UniversityNanchang 330006China

Rapid analysis of metal ions and organic compounds in strong acidic solutions is of sustainable interest in multiple ***,complicated and time-consuming pretreatments are always required for MS analysis of the compounds in strong acidic ***,it will result in a weak signal and cause serious damage to the mass ***,a simple method inherited from nano-ESI MS was developed for rapid analysis of strong acidic ***(nL)strong acidic solution was first loaded in the nano-ESI emitter,followed by evaporation to remove the H+and leave the analytes on the wall of the nano-ESI *** evaporation process can be completed within 1 min because of the extremely tiny volume(≤1 nL)of the loaded ***,the dried analytes on the wall of the nano-ESI emitter were redissolved by loading a new solvent,followed by nano-ESI MS *** using this method,metal ions and organic compounds in the strong acidic solution can be detected with low sample consumption(1 nL),high speed(90%).Proof-of-concept applications of the present method have been successfully achieved for the analysis of gastric juice(pH of the sample=1),monitoring reaction catalyzed by strong acid(pH of the system=0),and micro-area analysis of ores(pH of the extraction solvent=0),showing great application potential in multiple fields.

关键词： Strong acidic solutions Nano-ESI MS Rapid analysis Reaction monitoring Micro-area analysis Gastric juice analysis

Approximate Synchronization of Multi-Agent Systems over Finite Fields

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第4期37卷 1561-1580页

作者： YU miao FENG Jun-e XIA Jianwei FU Shihua SHEN Hao School of Mathematical Sciences Liaocheng UniversityLiaocheng 252059China School of Mathematics Shandong UniversityJinan 250100China School of Electrical and Information Engineering Anhui University of TechnologyMaanshan 243002China

In this paper,the approximate synchronization of leader-follower multiagent systems(MASs) over finite fields is studied in regard to local and global ***,the approximately synchronous state set(ASSS) is ***,combined with ASSS and transient periods,some criteria for the local and global approximate synchronization of systems are ***,the algorithms for calculating the maximum approximately synchronous basin(MASB) and the maximum control invariant set(MCIS) are ***,the global approximate synchronization of the system is achieved by designing the state feedback control,and a design algorithm of the controller using the truth matrix method is ***,the results of approximate synchronization are degenerated to complete ***,two examples are shown to demonstrate the results of this paper.

关键词： Approximate synchronization finite field multiagent system semi-tensor product state feedback control

Photoelectrochemical seawater oxidation with metal oxide materials:Challenges and opportunities

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2024年第10期97卷 767-782页

作者： miao Kan Hangyu Hu Weijie Zhuang Meng Tao Shiqun Wu Jinlong Zhang Key Laboratory for Advanced Materials and Joint International Research Laboratory of Precision Chemistry and Molecular Engineering Feringa Nobel Prize Scientist Joint Research Center School of Chemistry and Molecular Engineering East China University of Science and Technology Shanghai Engineering Research Center for Multimedia Environmental Catalysis and Resource Utilization East China University of Science and Technology

Photocatalytic water oxidation is a crucial counter-electrode reaction in the process of photoelectrochemical energy *** its importance,challenges remain in effectively and sustainably converting water to oxygen,particularly with readily available and inexpensive electrolyte solutions such as *** metal oxide materials have demonstrated their advantages in promoting efficiency by reducing overpotential and improving light utilization,stability remains limited by corrosion in multicomponent *** this paper,we reviewed the relationship between four basic concepts including photoelectrochemistry,metal oxide,water oxidation and seawater to better understand the challenges and opportunities in photoelectrochemical(PEC) seawater *** overcome these challenges,the advances in material design,interfacial modification,local environment control and reactor design have been further reviewed to benefit the industrial PEC seawater ***,we demonstrate engineered layered metal oxide electrodes and cell structures that enable powerful and stable seawater *** also outline and advise on the future direction in this area.

关键词： Anode Metal oxide Photoelectrochemistry Seawater Stability Water oxidation

Disruption of non-classically secreted protein(MoMtp)compromised conidiation,stress homeostasis,and pathogenesis of Magnaporthe oryzae

在线全文

学校读者我要写书评

暂无评论

Journal of Integrative Agriculture 2024年第8期23卷 2686-2702页

作者： Wajjiha Batool Justice Norvienyeku Wei Yi Zonghua Wang Shihong Zhang lili Lin Key Laboratory for Extreme-Environmental Microbiology College of Plant ProtectionShenyang Agricultural UniversityShenyang 110866China Ministerial and Provincial Joint Innovation Center for Safety Production of Cross-Strait Crops College of Life ScienceFujian Agriculture and Forestry UniversityFuzhou 350002China Key Laboratory of Green Prevention and Control of Tropical Plant Diseases and Pests College of Plant ProtectionHainan UniversityHaikou 570288China

Blast disease,caused by the hemibiotrophic ascomycete fungus,Magnaporthe oryzae,is a significant threat to sustainable rice production *** have shown that the blast fungus secretes vast arrays of functionally diverse proteins into the host cell for a successful disease ***,the final destinations of these effector proteins inside the host cell and their role in advancing fungal pathogenesis remain a ***,we reported that a putative mitochondrial targeting non-classically secreted protein(MoMtp)positively regulates conidiogenesis and appressorium maturation in ***,MoM TP gene deletion mutant strains triggered a hypersensitive response when inoculated on rice leaves displaying that MoMtp is essential for the virulence of *** addition,cell wall and oxidative stress results indicated that MoMtp is likely involved in the maintenance of the structural integrity of the fungus *** study also demonstrates an upregulation in the expression pattern of the MoMTP gene at all stages of infection,indicating its possible regulatory role in host invasion and the infectious development of ***,Agrobacterium infiltration and sheath inoculation confirmed that MoMtpGFP protein is predominantly localized in the host mitochondria of tobacco leaf and rice *** together,we conclude that MoMtp protein likely promotes the normal conidiation and pathogenesis of *** and might have a role in disturbing the proper functioning of the host mitochondria during pathogen invasion.

关键词： plant–pathogen interactions effectors hypersensitive response pathogenesis mitochondria

Thickening progression mechanism of silica fume-oil well cement composite system at high temperatures

在线全文

学校读者我要写书评

暂无评论

Petroleum Science 2024年第4期21卷 2793-2805页

作者： Hang Zhang miao-miao Hu Peng-Peng Li Guo-Qing Liu Qing-Lu Chang Jie Cao Ming Liu Wen-Hua Xu Xiu-Jian Xia Jin-Tang Guo School of Chemical Engineering and Technology Tianjin University Zhejiang Institute of Tianjin University Haihe Laboratory of Sustainable Chemical Transformations CNPC Engineering Technology R&D Company Limited

This work studied the thickening progression mechanism of the silica fume-oil well cement composite system at high temperatures(110-180.C) in order to provide a theoretical guidance for the rational application of silica fume in the cementing engineering. Results showed that silica fume seldom affected the thickening progression of oil well cement slurry at 110-120.C, but when temperature reached above130.C, it would aggravate the bulging degree of thickening curves and significantly extend the thickening time, meanwhile causing the abnormal “temperature-based thickening time reversal” and“dosage-based thickening time reversal” phenomena in the range of 130-160.C and 170-180.C respectively. At 130-160.C, the thickening time of oil well cement slurry was mainly associated with the generation rate of calcium hydroxide(CH) crystal. The introduced silica fume would be attracted to the cement minerals' surface that were hydrating to produce CH and agglomerate together to form an“adsorptive barrier” to hinder further hydration of the inner cement minerals. This “adsorptive barrier”effect strengthened with the rising temperature which extended the thickening time and caused the occurrence of the “temperature-based thickening time reversal” phenomenon. At 170-180.C, the pozzolanic activity of silica fume significantly enhanced and considerable amount of C-S-H was generated, thus the “temperature-based thickening time reversal” vanished and the “dosage-based thickening time reversal” was presented.

关键词： Silica fume Oil well cement Thickening time reversal Pozzolanic reaction Adsorptive barrier CH and C−S−H

双进双出粗粉分离器流场数值模拟与优化技术研究

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

黑龙江电力 2018年第4期40卷 353-357页

作者：苗莉莉忻州职业技术学院机械工程系山西忻州034100

针对双进双出分离器分离效率低的问题,开展了数值分析、理论计算、机构优化和工程性分析等研究过程,从而建立了仿真动力学模型,获取了双进双出分离器内的流场分布、压降特性和颗粒运动形态,对分离器的结构进行了优化。研究结果表明,双... 详细信息

针对双进双出分离器分离效率低的问题,开展了数值分析、理论计算、机构优化和工程性分析等研究过程,从而建立了仿真动力学模型,获取了双进双出分离器内的流场分布、压降特性和颗粒运动形态,对分离器的结构进行了优化。研究结果表明,双进双出粗粉分离器经过结构优化改进后,分离器压降阻力大幅度降低,明显提高了制粉系统的出力、分离效率、分级效果、细度分离效果和均匀性指数。

关键词：粗粉分离器数值模拟优化