检索结果-南通市图书馆

Automated Machine Learning Algorithm Using Recurrent Neural Network to Perform Long-Term Time Series Forecasting

在线全文

学校读者我要写书评

暂无评论

computers, Materials & continua 2024年第3期78卷 3529-3549页

作者： Ying Su Morgan c.wang Shuai Liu Department of Statistics and Data Science University of Central FloridaOrlandoFL32816-2370USA School of Mathematics and Statistics Beijing Technology and Business UniversityBeijing100048China

Long-term time series forecasting stands as a crucial research domain within the realm of automated machine learning(AutoML).At present,forecasting,whether rooted in machine learning or statistical learning,typically relies on expert input and necessitates substantial manual *** manual effort spans model development,feature engineering,hyper-parameter tuning,and the intricate construction of time series *** complexity of these tasks renders complete automation unfeasible,as they inherently demand human intervention at multiple *** surmount these challenges,this article proposes leveraging Long Short-Term Memory,which is the variant of Recurrent Neural Networks,harnessing memory cells and gating mechanisms to facilitate long-term time series ***,forecasting accuracy by particular neural network and traditional models can degrade significantly,when addressing long-term time-series ***,our research demonstrates that this innovative approach outperforms the traditional Autoregressive Integrated Moving Average(ARIMA)method in forecasting long-term univariate time *** is a high-quality and competitive model in time series prediction,and yet it requires significant preprocessing *** multiple accuracy metrics,we have evaluated both ARIMA and proposed method on the simulated time-series data and real data in both short and long ***,our findings indicate its superiority over alternative network architectures,including Fully connected Neural Networks,convolutional Neural Networks,and Nonpooling convolutional Neural *** AutoML approach enables non-professional to attain highly accurate and effective time series forecasting,and can be widely applied to various domains,particularly in business and finance.

关键词： Automated machine learning autoregressive integrated moving average neural networks time series analysis

Flow resistance of gravel bed channels

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

International Journal of Sediment Research 2014年第1期29卷 126-132页

作者： Wen c.wang David R.DAWDY Multech Engineering consultants

Existing resistance formulas produce a wide range of friction-factor estimates for gravel bed *** purpose of this paper is to develop a reliable resistance formula in terms of the Darcy-Weisbach friction factor/ Published data were screened and used to establish the *** existing formulas have considered that/is a function of relative roughness D84/R only,where R is the hydraulic radius and D84is the particle size referred to the intermediate diameter that equals or exceeds that of 84 percent of bed *** this paper,/is considered as a function of Froude number in addition to the relative roughness./for D84/R>1 displays a different trend than that for D84/Rc velocity distribution for D84/R>***/formula for D84/R<1 has been established.

关键词： Flow resistance Darcy-Weisbach friction factor Relative roughness Relative submergence Gravel bed channels Open channels

Mechanisms of ultraviolet disinfection and chlorination of Escherichia coli： culturability, membrane permeability,metabolism, and genetic damage

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2018年第3期30卷 356-366页

作者： Limei Xu chongmiao Zhang Pengcheng Xu Xiaochang c.wang International Science and Technology cooperation center for Urban Alternative Water Resources Development China Key Laboratory of Northwest Water Resource Environment and Ecology MOE China Engineering Technology Research center for Wastewater Treatment and Reuse Shaanxi Province China School of Environmental and Municipal Engineering Xi'an University of Architecture and Technology Xi'an 710055 China

Traditional culture methods may underestimate the tolerance of microorganisms to disinfectants because of the existence of viable but nonculturable or sublethally injured cells after *** selection of a strict method is crucial for the evaluation of disinfection *** actions of 2 typical disinfectants–ultraviolet（UV）and chlorine–on the fecal indicator Escherichia coli were investigated by the detection of culturability,membrane permeability,metabolic activity,deoxyribonucleic acid（DNA）,and messenger ribonucleic acid（m RNA）.During UV disinfection,the irreversible damages in the cell membrane and cellular adenosine triphosphate（ATP）were negligible at low UV doses（80 m J/cm^2）.However,membrane permeability was damaged at low doses of chlorine（5 mg/L）,leading to leakage of cellular *** study showed that a slight lesion in DNA was detected even at high doses of UV（400 m J/cm^2）and chlorine（5 mg/L）*** decay of m RNA was more rapid than that of *** degradation level of m RNA depended on the choice of target *** exposure to 50 m J/cm^2UV dose or 5 mg/L chlorine for30 min,the DNA damage repair function（Rec A m RNA）was *** m RNA involved in the DNA damage repair function can be a potential indicator of bacterial viability.

关键词： UV chlorination Membrane damage Adenosine triphosphate DNA mRNA

Two-dimensional correlation spectroscopic analysis on the interaction between humic acids and aluminum coagulant

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2018年第2期30卷 181-189页

作者： Pengkang Jin Jina Song Xiaochang c.wang Xin Jin School of Environmental and Municipal Engineering Xi'an University of Architecture and Technology college of Energy and Environmental Engineering Hebei University of Engineering

In this study, two-dimensional correlation spectroscopy integrated with synchronous fluorescence and infrared absorption spectroscopy was employed to investigate the interaction between humic acids and aluminum coagulant at slightly acidic and neutral p H. Higher fluorescence quenching was produced for fulvic-like and humic-like fractions at p H 5. At p H 5, the humic-like fractions originating from the carboxylic acid, carboxyl and polysaccharide compounds were bound to aluminum first, followed by the fulvic-like fractions originating from the carboxyl and polysaccharide compounds. This finding also demonstrated that the activated functional groups of HA were involved in forming the Al-HA complex, which was accompanied by the removal of other groups by ***, at p H 7, almost no fluorescence quenching occurred, and surface complexation was observed to occur, in which the activated functional groups were absorbed on the amorphous Al（OH）3. Two-dimensional FT-IR correlation spectroscopy indicated the sequence of HA structural change during coagulation with aluminum, with IR bands affected in the order of cOOH〉 cOO-〉NH deformation of amide Ⅱ〉 aliphatic hydroxyl c／OH at p H 5, and cOO-〉aliphatic hydroxyl c／OH at p H 7. This study provides a promising pathway for analysis and insight into the priority of functional groups in the interaction between organic matters and metal coagulants.

关键词： Two-dimensional correlation spectroscopy Al-HA complex Surface complexation Interaction sequence

Thermodynamic prediction and experimental investigation of short-term dynamic membrane formation in dynamic membrane bioreactors:Effects of sludge properties

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2019年第3期31卷 85-96页

作者： Zhenzhen Yu Yisong Hu Mawuli Dzakpasu Xiaochang c.wang Key Lab of Northwest Water Resource Environment and Ecology MOE Xi'an University of Architecture and Technology International Science & Technology cooperation center for Urban Alternative Water Resources Development Key Lab of Environmental Engineering Shaanxi Province

In dynamic membrane bioreactors(DMBRs), a dynamic membrane(DM) forms on a support material to act as the separation membrane for solids and liquids. In this study, batch filtration tests were carried out in a DMBR using nylon mesh(25 μm) as support material to filtrate sludge suspensions of variable properties from three different sources to evaluate the effects on the short-term DM formation process(within 240 min). Furthermore, the extended Derjaguin–Landau–Verwey–Overbeek(XDLVO) theory was applied to analyze the sludge adhesion and cohesion behaviors on the mesh surface to predict quantitative parameters of the short-term DM formation process(including initial formation and maturation stage). The filtration results showed that the order of the initial DM formation time(permeate turbidity cator) was as follows: sludge with poor settleability and dewaterability cculability. Moreover, normal sludge(regarding settleability, dewaterability,flocculability, and extracellular polymeric substance) showed a more acceptable DM formation performance(short DM formation time, low permeate turbidity, and high permeate flux) than sludge with poor settleability, dewaterability and flocculability. The influence of sludge properties on the initial DM formation time corroborates the prediction of sludge adhesion behaviors by XDLVO theory. Additionally, the XDLVO calculation results showed that acid–based interaction, energy barrier, and secondary energy minimum were important determinants of the sludge adhesion and cohesion behaviors. Therefore, short-term DM formation process may be enhanced to achieve stable long-term DMBR operation through positive modification of the sludge properties.

关键词： Dynamic membrane bioreactor Dynamic membrane formation XDLVO theory Sludge properties Wastewater treatment

Application of a hybrid gravity-driven membrane filtration and dissolved ozone flotation(MDOF)process for wastewater reclamation and membrane fouling mitigation

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2019年第7期31卷 17-27页

作者： Xin Jin Wei wang Shuai wang Pengkang Jin Xiaochang c.wang Wushou Zhang Weijun An Yong wang Key Lab of Northwest Water Resource Environment and Ecology MOE Xi'an University of Architecture and Technology Langzheng Environmental Protection Technology co. Ltd.

This study proposed a novel membrane filtration and dissolved ozone flotation integrated(MDOF) process and tested it at pilot scale. Membrane filtration in the MDOF process was operated in gravity-driven mode, and required no backwashing, flushing, or chemical cleaning. Because ozone was added in the MDOF process, ozonation, coagulation, and membrane filtration could occur in a single reactor. Moreover, in situ ozonation occurred in the MDOF process, which differs from the conventional pre-ozonation membrane filtration process. Significant enhancement of turbidity removal was further achieved through the addition of membrane filtration. Membrane fouling was mitigated in the MDOF process compared to the MDAF process. In situ ozonation in the MDOF process decreased the fluorescence intensity and transformed the high MW dissolved organics into small MW compounds. For the fouling layer, the extracellular polymeric substance(EPS) contents and cake layer morphology were analyzed. The results indicated that the contents of EPS decreased. Furthermore, a thinner and more loosely structured cake layer formed in the MDOF process. Because coagulation and ozonation occurred simultaneously in a single reactor, the generation of hydroxyl radicals was enhanced through the catalytic effect of Al-based coagulants on ozone decomposition, which further alleviated membrane fouling in the MDOF process.

关键词： Dissolved ozone flotation Gravity-driven membrane filtration Membrane fouling In situ ozonation

Smart cutting Tools and Smart Machining: Development Approaches, and Their Implementation and Application Perspectives

在线全文

学校读者我要写书评

暂无评论

chinese Journal of Mechanical Engineering 2017年第5期30卷 1162-1176页

作者： Kai cheng Zhi-chao Niu Robin c.wang Richard Rakowski Richard Bateman college of Engineering Design and Physical SciencesBrunel University London

Smart machining has tremendous potential and is becoming one of new generation high value precision manufacturing technologies in line with the advance of Industry 4.0 concepts. This paper presents some innovative design concepts and, in particular, the development of four types of smart cutting tools, including a force-based smart cutting tool, a temperature-based internally-cooled cutting tool, a fast tool servo （FTS） and smart collets for ultra- precision and micro manufacturing purposes. Implemen- tation and application perspectives of these smart cutting tools are explored and discussed particularly for smart machining against a number of industrial application requirements. They are contamination-free machining, machining of tool-wear-prone Si-based infra-red devices and medical applications, high speed micro milling and micro drilling, etc. Furthermore, implementation tech- niques are presented focusing on：（a） plug-and-produce design principle and the associated smart control algo- rithms, （b） piezoelectric film and surface acoustic wave transducers to measure cutting forces in process, （c） critical cutting temperature control in real-time machining, （d） in- process calibration through machining trials, （e） FE-based design and analysis of smart cutting tools, and （f） applica- tion exemplars on adaptive smart machining.

关键词： Smart cutting tool Smart machining Fast toolservo (FFS) Precision machining Micro manufacturing Smart tooling

Dynamic membrane bioreactor performance enhancement by powdered activated carbon addition:Evaluation of sludge morphological,aggregative and microbial properties

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2019年第1期31卷 73-83页

作者： Zhenzhen Yu Yisong Hu Mawuli Dzakpasu Xiaochang c.wang Huu Hao Ngo Key Lab of Northwest Water Resource Environment and Ecology MOE Xi'an University of Architecture and Technology International Science & Technology cooperation center for Urban Alternative Water Resources Development Key Lab of Environmental Engineering centre for Technology in Water and Wastewater School of Civil and Environmental Engineering University of Technology Sydney

The effects of powdered activated carbon(PAc) addition on sludge morphological, aggregative and microbial properties in a dynamic membrane bioreactor(DMBR) were investigated to explore the enhancement mechanism of pollutants removal and filtration performance. Sludge properties were analyzed through various analytical measurements. The results showed that the improved sludge aggregation ability and the evolution of microbial communities affected sludge morphology in PAc-DMBR, as evidenced by the formation of large, regularly shaped and strengthened sludge flocs. The modifications of sludge characteristics promoted the formation process and filtration flux of the dynamic membrane(DM) layer. Additionally, PAc addition did not exert very significant influence on the propagation of eukaryotes(protists and metazoans)and microbial metabolic activity. High-throughput pyrosequencing results indicated that adding PAc improved the bacterial diversity in activated sludge, as PAc addition brought about additional microenvironment in the form of biological PAc(BPAc), which promoted the enrichment of Acinetobacter(13.9%), comamonas(2.9%), Flavobacterium(0.31%) and Pseudomonas(0.62%), all contributing to sludge flocs formation and several(such as Acinetobacter) capable of biodegrading relatively complex organics. Therefore, PAc addition could favorably modify sludge properties from various aspects and thus enhance the DMBR performance.

关键词： Dynamic membrane bioreactor Powdered activated carbon Sludge property Filtration performance Wastewater treatment Microbial community

In Vitro Evaluation of the Feasibility of commercial Zn Alloys as Biodegradable Metals

在线全文

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2016年第9期32卷 909-918页

作者： c.wang H.T.Yang X.Li Y.F.Zheng Department of Interventional Radiology and Vascular Surgery Peking University Third Hospital Department of Materials Science and Engineering College of Engineering Peking University

In this work, three widely used commercial Zn alloys （ZA4-1, ZA4-3, ZA6-1 ） were purchased and pre- pared by hot extrusion at 200℃. The microstructure, mechanical properties, corrosion behaviors, biocompatibility and hemocompatibility of Zn alloys were studied with pure Zn as control, commercial Zn alloys demonstrated increased strength and superb elongation compared with pure Zn. Accelerated corrosion rates and uniform corrosion morphologies were observed in terms of commercial Zn alloys due to galvanic effects between Zn matrix and α-Al phases. 100% extracts of ZA4-1 and ZA6-1 alloys showed mild cytotoxicity while 50% extracts of all samples displayed good biocompatibility. Retardant cell cycle and inhibited stress fibers expression were observed induced by high concentration of Zn^2＋ releasing during corrosion. The hemolysis ratios of Zn alloys were lower than 1% while the adhered platelets showed slightly activated morphologies. In general, commercial Zn alloys possess promising mechanical properties, appropriate corrosion rates, significantly improved biocompatibility and good hemocompatibility in comparison to pure Zn. It is feasible to develop biodegradable metals based on commercial Zn alloys.

关键词： commercial Zn alloys Biodegradable metals Mechanical properties corrosion behaviors cytotoxicity Hemocompatibility