检索结果-南通市图书馆

Data-driven diagnosis of high temperature PEM fuel cells based on the electrochemical impedance spectroscopy: Robustness improvement and evaluation

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 Energy Chemistry 2024年第9期96卷 544-558页

作者： Dan Yu Xingjun Li Samuel simon Araya simon Lennart Sahlin Vincenzo Liso Department of Energy Aalborg UniversityAalborg 9220Denmark w.lker Department of Mechanical Engineering The University of Texas at AustinAustinTX 78712USA Materials Research and Technology Development Luxembourg Institute of Science and Technology(LIST)4422 BelvauxLuxembourg

Utilizing machine learning techniques for data-driven diagnosis of high temperature PEM fuel cells is beneficial and meaningful to the system durability. Nevertheless, ensuring the robustness of diagnosis remains a critical and challenging task in real application. To enhance the robustness of diagnosis and achieve a more thorough evaluation of diagnostic performance, a robust diagnostic procedure based on electrochemical impedance spectroscopy (EIS) and a new.method for evaluation of the diagnosis robustness w.s proposed and investigated in this w.rk. To improve the diagnosis robustness: (1) the degradation mechanism of different faults in the high temperature PEM fuel cell w.s first analyzed via the distribution of relaxation time of EIS to determine the equivalent circuit model (ECM) w.th better interpretability, simplicity and accuracy;(2) the feature extraction w.s implemented on the identified parameters of the ECM and extra attention w.s paid to distinguishing betw.en the long-term normal degradation and other faults;(3) a Siamese Netw.rk w.s adopted to get features w.th higher robustness in a new.embedding. The diagnosis w.s conducted using 6 classic classification algorithms—support vector machine (SVM), K-nearest neighbor (KNN), logistic regression (LR), decision tree (DT), random forest (RF), and Naive Bayes employing a dataset comprising a total of 1935 collected EIS. To evaluate the robustness of trained models: (1) different levels of errors w.re added to the features for performance evaluation;(2) a robustness coefficient (Roubust_C) w.s defined for a quantified and explicit evaluation of the diagnosis robustness. The diagnostic models employing the proposed feature extraction method can not only achieve the higher performance of around 100% but also higher robustness for diagnosis models. Despite the initial performance being similar, the KNN demonstrated a superior robustness after feature selection and re-embedding by triplet-loss method, w.ich sug

关键词： PEM fuel cell Data-driven diagnosis Robustness improvement and evaluation Electrochemical impedance spectroscopy

In situ characterization of particle formation in spray flame synthesis using w.de-angle light scattering

在线全文

学校读者我要写书评

暂无评论

Particuology 2024年第3期86卷 304-312页

作者： simon Aβmann Franz J.T.Huber Stefan w.ll Lehrstuhl für Technische Thermodynamik(LTT) Friedrich-Alexander-Universitat Erlangen-Nürnberg(FAU)Erlangen91058Germany Erlangen Graduate Schoolin Advanced Optical Technologies(SAOT) Friedrich-Alexander-Universitat Erlangen-Nurnberg(FAU)Erlangen91052Germany Competence Unit Engineering of Advanced Materials(EAM) Friedrich-Alexander-Universitat Erlangen-Nürnberg(FAU)Erlangen91052Germany

w.de-angle light scattering(w.LS)w.s used for in situ measurements of droplet and nanoparticle size distributions during the synthesis of titania and iron oxide particles from liquid precursor solutions in the standardized SpraySyn burner for spray flame *** w.s synthesized from titanium tetraisopropoxide(TTIP)and iron oxide from iron(II)nitrate nonahydrate(INN)using ethanol(EtOH)as *** images w.re taken at heights up to 120 mm above the burner surface and classified into droplet and particle *** size distributions w.re derived from a sequential analysis of scattering data containing the oscillating Mie pattern,the lognormal size distribution parameters for spherical and fractal particle fractions from a multivariate approach on averaged particle scattering *** results show.that the precursor addition leads to altered evaporation behavior and even droplet disruption probably induced by puffing or micro-explosions compared to pure *** the case of TTIP(a hygroscopic alkoxide),the synthesis of a large fraction of spheres w.s observed,w.ile the nitrate INN leads to the formation of mostly fractal aggregates.

关键词： Spray flame synthesis Metal oxide particles Elastic light scattering Droplet size distribution Nanoparticle morphology Particle size distribution

Tow.rds Domain-agnostic Depth Completion

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第4期21卷 652-669页

作者： Guangkai Xu w.i Yin Jianming Zhang Oliver w.ng simon Niklaus simon Chen Jia-w.ng Bian Zhejiang University Hangzhou 310058China DaJiang Technology Shenzhen 518057China Adobe Research California 95110USA University of Oxford Oxford OX12JDUK

Existing depth completion methods are often targeted at a specific sparse depth type and generalize poorly across task *** present a method to complete sparse/semi-dense,noisy,and potentially low.resolution depth maps obtained by various range sensors,including those in modern mobile phones,or by multi-view.reconstruction *** method leverages a data-driven prior in the form of a single image depth prediction netw.rk trained on large-scale datasets,the output of w.ich is used as an input to our *** propose an effective training scheme w.ere w. simulate various sparsity patterns in typical task *** addition,w. design tw. new.benchmarks to evaluate the generalizability and robustness of depth completion *** simple method show. superior cross-domain generalization ability against state-of-the-art depth completion methods,introducing a practical solution to highqualitydepthcapture onamobile device.

关键词： Monocular depth estimation depth completion zero-shot generalization scene reconstruction neural netw.rk.

Experimental and Numerical Analysis of a PCM-Integrated Roof for Higher Thermal Performance of Buildings

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 Thermal Science 2024年第2期33卷 522-536页

作者： simon François RUIZ-VALERO Letzai GIRARD Aymeric GALLEGUILLOS Hector Centro de Desarrollo Urbano Sustentable(CEDEUS) Pontificia Universidad Católica de Chile7500000SantiagoChile Facultad de Ciencias e Ingeniería Pontificia Universidad Católica Madre y Maestra(PUCMM)10103Santo DomingoDominican Republic LMGC IMT Mines AlesUniv MontpellierCNRS30100AlèsFrance Facultad de Ingeniería y Ciencias Universidad Adolfo Ibañez2520000Viña del MarChile Centro de Desarrollo Energético Antofagasta(CDEA) Universidad de Antofagasta1240000AntofagastaChile

Phase change materials(PCMs) designate materials able to store latent *** change state from solid to liquid over a defined temperature *** process is reversible and can be used for thermo-technical *** present paper aims to study the thermal performance of an inorganic eutectic PCM integrated into the rooftop slab of a test room and analyze its potential for building thermal *** experiment is conducted in tw. test rooms in Antofagasta(Chile) during summer,fall,and *** PCM is integrated into the rooftop of the first test room,w.ile the roof panel of the second room is a sealed air *** w.rk introduces a numerical model,w.ich is built using the finite difference method and used to simulate the rooms' thermal *** thermal simulations of the PCM room are performed for other Chilean locations to evaluate and compare the capability of the PCM panel to store latent heat thermal energy in different *** show.that the indoor temperature of the PCM room in Antofagasta varies only 21.1℃±10.6℃,w.ile the one of the air-panel room varies 28.3℃±18.5℃.Under the experiment's conditions,the PCM room's indoor temperature observes smoother diurnal fluctuations,w.th low.r maximum and higher minimum indoor temperatures than that of the air-panel *** simulations in other cities show.that the PCM panel has a better thermal performance during w.nter,as it helps to maintain or increase the room temperature by some degrees to reach comfort *** demonstrates that the implementation of such PCM in the building envelope can effectively reduce space heating and cooling needs,and improve indoor thermal comfort in different climates of Chile.

关键词： phase change material thermal energy storage building space heating and cooling energy efficiency designbuilder

An explainable AI framew.rk for robust and transparent data-driven w.nd turbine pow.r curve models

在线全文

学校读者我要写书评

暂无评论

Energy and AI 2024年第1期15卷 312-327页

作者： simon Letzgus Klaus-Robert Müller Machine Learning Group Technische Universitβe BerlinStraβe des 17.Juni 135Berlin10623Germany Berlin Institute for the Foundations of Learning and Data Berlin10587Germany Department of Artificial Intelligence Korea UniversitySeoul136-713South Korea Max Planck Institute for Informatics Saarbrücken66123Germany

In recent years,increasingly complex machine learning methods have become state-of-the-art in modelling w.nd turbine pow.r curves based on operational *** these methods often exhibit superior performance on test sets,they face criticism due to a perceived lack of transparency and concerns about their robustness in dynamic,non-stationary environments encountered by w.nd *** this w.rk,w. address these issues and present a framew.rk that leverages explainable artificial intelligence methods to gain systematic insights into data-driven pow.r curve *** its core,w. propose a metric to quantify how.w.ll a learned model strategy aligns w.th the underlying physical principles of the *** novel tool enables model validation beyond the conventional error metrics in an automated *** demonstrate,for instance,its capacity as an indicator for model generalization even w.en limited data is ***,it facilitates understanding how.decisions made during the machine learning development process,such as data selection,pre-processing,or training parameters,affect learned *** a result,w. obtain physically more reasonable models,a prerequisite not only for robustness but also for meaningful insights into turbine operation by domain *** latter,w. illustrate in the context of w.nd turbine performance *** summary,the framew.rk aims to guide researchers and practitioners alike tow.rd a more informed selection and utilization of data-driven w.nd turbine pow.r curve models.

关键词： Explainable AI(XAI) Machine learning w.nd energy w.nd turbine pow.r curve SCADA Condition monitoring

Developing a multi-method approach to identifying e-scooter hazard hotspots

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 Traffic and Transportation Engineering(English Edition) 2024年第4期11卷 667-680页

作者： Michael Hardinghaus simon Nieland Rebekka Oostendorp Jan w.schke German Aerospace Center(DLR)Institute of Transport Research Berlin 12489Germany

In recent years,e-scooters have been introduced in many European *** several places w. have w.tnessed a rapid uptake of this new.mode of transport mainly as a result of public sharing schemes.A number of incidents,injuries and even fatalities have given rise to questions regarding the safety of these *** questions are being researched mainly using official crash data and data specifying injuries and hospital *** now.the research has focused on investigating typical injury patterns and estimating risk *** little is know. about exactly w.ere conflicts and crashes *** of hazard hotspots is crucial w.en investigating risk levels and improving safety for all road ***,this paper develops an approach to investigating locations w.th potentially dangerous interactions w.thin the active mobility system in the city of *** approach consists of explorative expert interview.,an online poll,and quantitative *** the latter w. combine three ***,w. research crash hotspots using official ***,w. use data based on acceleration sensors from cyclists'smartphones to find locations of sudden ***,w. use trip data from the operators of escooter sharing *** information gathered is used in a conclusive expert w.rkshop to identify hazard *** show.that many of the conflicts w.th pedestrians are caused by parked ***,e-scooter trips are concentrated in the inner city and along specific *** moving traffic,various data sources are used to identify hotspots at intersections and in areas betw.en *** present research lays the foundation for important further studies to investigate interactions at hotspots in detail by determining nine specific locations in the city of Berlin.

关键词： E-scooter Accidents Crashes Active mobility Micromobility Road safety

Internal flow.in sessile droplets induced by substrate oscillation:tow.rds enhanced mixing and mass transfer in microfluidic systems

在线全文

学校读者我要写书评

暂无评论

Microsystems & Nanoengineering 2024年第3期10卷 369-379页

作者： Tianyi Zhang Peng Zhou Terrence simon Tianhong Cui Department of Mechanical Engineering University of MinnesotaMinneapolisMN 55455USA

The introduction of flow. w.thin sessile droplets is highly effective for many lab-on-a-chip chemical and biomedical ***,generating such flow. is difficult due to the typically small droplet ***,w. present a simple,non-contact strategy to generate internal flow. in sessile droplets for enhancing mixing and mass *** flow. are driven by actuating a rigid substrate into oscillation w.th certain amplitude distributions w.thout relying on the resonance of the droplet *** oscillation characteristics and corresponding flow.patterns are documented *** indices and mass transfer coefficients of sessile droplets on the substrate surface are measured using optical and electrochemical *** demonstrate complete mixing w.thin the droplets in 1.35 s and increases in mass transfer rates of more than seven times static *** of concept w.s conducted w.th experiments of silver nanoparticle synthesis and w.th heavy metal ion sensing employing the sessile droplet as a microreactor for synthesis and an electrochemical cell for *** degrees of enhancement of synthesis efficiency and detection sensitivity attributed to the internal flow. are experimentally documented.

关键词： mixing oscillation synthesis

A reinforcement learning approach for thermostat setpoint preference learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Building Simulation 2024年第1期17卷 131-146页

作者： Hussein Elehw.ny Mohamed Ouf Burak Gunay Nunzio Cotrufo Jean-simon Venne Department of Environmental Engineering Carleton UniversityOttawaCanada Departmentof Building Civiland Environmental EngineeringConcordia UniversityMontrealCanada BrainBox Al Inc. MontrealCanada

Occupant-centric controls(OcC)is an indoor climate control approach w.ereby occupant feedback is used in the sequence of operation of building energy *** OcC has been used in a w.de range of building applications,an OcC category that has received considerable research interest is learning occupants'thermal preferences through their thermostat interactions and adapting temperature setpoints *** recent studies used reinforcement learning(RL)as an agent for OcC to optimize energy use and occupant *** studies depended on predicted mean vote(PMV)models or constant comfort ranges to represent comfort,w.ile only few.of them used thermostat *** paper addresses this gap by introducing a new.off-policy reinforcement learning(RL)algorithm that imitates the occupant behaviour by utilizing unsolicited occupant thermostat *** algorithm is tested w.th a number of synthetically generated occupant behaviour models implemented via the Python APl of *** simulation results indicate that the RL algorithm could rapidly learn preferences for all tested occupant behaviour scenarios w.th minimal exploration *** substantial energy savings w.re observed w.th most occupant scenarios,the impact on the energy savings varied depending on occupants'preferences and thermostat use behaviour stochasticity.

关键词： reinforcement learning preference learning occupant-centric controls smart thermostats off-policy learning

Source Enrichment Control on the Scale of Magmatic-Hydrothermal w.Sn Mineralization:Insights from Triassic and Jurassic Magma Reservoirs in the Continental Crust,Xitian,South China

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Geologica Sinica(English Edition) 2024年第1期98卷 132-149页

作者： GUO Chunli simon Aw.LDE Coralie SIEGEL CHEN Zhenyu w. Shichong MNR Key Laboratory of Metallogeny and Mineral Assessment Institute of Mineral ResourcesChinese Academy of Geological SciencesBeijing 100037China SinoProbe Laboratory Chinese Academy of Geological SciencesBeijing 100094China School of Earth and Planetary Sciences Curtin UniversityPerth 6845Australia Discovery Program Mineral ResourcesCommonwealth Scientific and Industrial Research OrganisationAustralian Resources Research CentrePerth 6151Australia No.416 Geological Group Hunan Bureau of Mineral Exploration and DevelopmentZhuzhouHunan 412007China

There are tw. factors,source composition and magmatic differentiation,potentially controlling w.Sn *** one is more important is w.dely debated and may need to be determined for each individual *** Xitian granite batholith located in South China is a natural laboratory for investigating the above *** consists essentially of tw. separate components,formed in the Triassic at ca.226 Ma and Jurassic at ca.152 Ma,*** Triassic and Jurassic rocks are both composed of porphyritic and fine-grained *** latter resulted from highlydifferentiated porphyritic ones but they have similar textural characteristics and mineral assemblages,indicating that they reached a similar degree of crystal *** both fine-grained phases are highly differentiated w.th elevated rare metal contents,economic w.Sn mineralization is rare in the Triassic granitoids and this can be attributed to less fertile source materials than their Jurassic counterparts,w.th a slightly more enriched isotopic signature and w.ole-rockεNd(226 Ma)of−10.4 to−9.2(2σ=0.2)compared w.thεNd(152 Ma)of−9.2 to−8.2(2σ=0.2)for the Jurassic *** initial w.Sn enrichment w.s derived from the metasedimentary rocks and strongly enhanced by rew.rking of the continental crust,culminating in the Jurassic.

关键词： w.Sn mineralization magma reservoir geometry crystal fractionation Xitian Triassic-Jurassic granitic batholith Nanling Range South China