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

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 Walker 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 was proposed and investigated in this work. To improve the diagnosis robustness: (1) the degradation mechanism of different faults in the high temperature PEM fuel cell was first analyzed via the distribution of relaxation time of EIS to determine the equivalent circuit model (ECM) with better interpretability, simplicity and accuracy;(2) the feature extraction was implemented on the identified parameters of the ECM and extra attention was paid to distinguishing between the long-term normal degradation and other faults;(3) a Siamese Network was adopted to get features with higher robustness in a new embedding. The diagnosis was 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 were added to the features for performance evaluation;(2) a robustness coefficient (Roubust_C) was 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, which 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 wide-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 Will 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

Wide-angle light scattering(WALS)was 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 *** was synthesized from titanium tetraisopropoxide(TTIP)and iron oxide from iron(II)nitrate nonahydrate(INN)using ethanol(EtOH)as *** images were taken at heights up to 120 mm above the burner surface and classified into droplet and particle *** size distributions were 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 was observed,while 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

Towards 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 Wei Yin Jianming Zhang Oliver Wang simon Niklaus simon Chen Jia-Wang 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 network trained on large-scale datasets,the output of which is used as an input to our *** propose an effective training scheme where we simulate various sparsity patterns in typical task *** addition,we design two new benchmarks to evaluate the generalizability and robustness of depth completion *** simple method shows 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 network.

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 two test rooms in Antofagasta(Chile) during summer,fall,and *** PCM is integrated into the rooftop of the first test room,while the roof panel of the second room is a sealed air *** work introduces a numerical model,which 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℃,while 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,with lower 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 winter,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 framework for robust and transparent data-driven wind turbine power 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 wind turbine power 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 wind *** this work,we address these issues and present a framework that leverages explainable artificial intelligence methods to gain systematic insights into data-driven power curve *** its core,we propose a metric to quantify how well a learned model strategy aligns with 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 when 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,we obtain physically more reasonable models,a prerequisite not only for robustness but also for meaningful insights into turbine operation by domain *** latter,we illustrate in the context of wind turbine performance *** summary,the framework aims to guide researchers and practitioners alike toward a more informed selection and utilization of data-driven wind turbine power curve models.

关键词： Explainable AI(XAI) Machine learning Wind energy Wind turbine power 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 Weschke German Aerospace Center(DLR)Institute of Transport Research Berlin 12489Germany

In recent years,e-scooters have been introduced in many European *** several places we have witnessed 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 known about exactly where conflicts and crashes *** of hazard hotspots is crucial when investigating risk levels and improving safety for all road ***,this paper develops an approach to investigating locations with potentially dangerous interactions within the active mobility system in the city of *** approach consists of explorative expert interviews,an online poll,and quantitative *** the latter we combine three ***,we research crash hotspots using official ***,we use data based on acceleration sensors from cyclists'smartphones to find locations of sudden ***,we use trip data from the operators of escooter sharing *** information gathered is used in a conclusive expert workshop to identify hazard *** show that many of the conflicts with 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 between *** 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:towards 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 flows within sessile droplets is highly effective for many lab-on-a-chip chemical and biomedical ***,generating such flows is difficult due to the typically small droplet ***,we present a simple,non-contact strategy to generate internal flows in sessile droplets for enhancing mixing and mass *** flows are driven by actuating a rigid substrate into oscillation with certain amplitude distributions without 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 within the droplets in 1.35 s and increases in mass transfer rates of more than seven times static *** of concept was conducted with experiments of silver nanoparticle synthesis and with 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 flows 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 Elehwany 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 whereby occupant feedback is used in the sequence of operation of building energy *** OcC has been used in a wide 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,while 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 with 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 with minimal exploration *** substantial energy savings were observed with 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

Glucagon-like peptide (GLP)-1 regulation of lipid and lipoprotein metabolism

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Medical Review 2024年第4期4卷 301-311页

作者： simon Hoffman Khosrow Adeli Molecular Medicine Research InstituteThe Hospital for Sick ChildrenUniversity of TorontoTorontoONCanada Cardiovascular&Metabolic Disease Merck Research LaboratoriesSouth San FranciscoCAUSA Molecular Medicine Research InstituteThe Hospital for Sick ChildrenUniversity of Toronto555 University Avenue M5G 1X8TorontoONCanada

Metabolic health is highly dependent on intestinal and hepatic handling of dietary and endogenous lipids and *** of lipid and lipoprotein metabolism are commonly observed in patients with insulin resistant states such as obesity,metabolic syndrome,and type 2 ***-idence from both animal models and human studies indicates that a major underlying factor in metabolic or diabetic dysli-pidemia is the overproduction of hepatic and intestinal apoli-poprotein(apo)B-containing lipoprotein *** particles are catabolized down into highly proatherogenic remnants,which can be taken up into the arterial intima and promote plaque *** gut-derived peptides have been identiﬁed as key regulators of energy metabolism;one such peptide is the incretin hormone glucagon-like peptide(GLP)-*** laboratory has previously demonstrated that GLP-1 can signal both centrally and peripherally to reduce postprandial and fasting lipoprotein ***,we have demonstrated that GLP-1 receptor(GLP-1R)agonists can ameliorate diet-induced ***,we published evidence for a novel vagal neuroendocrine signalling pathway by which native GLP-1 may exert its anti-lipemic eﬀ***,we demonstrated a novel role for other gut-derived peptides in regulating intestinal lipoprotein ***,ample evidence supports a key role for GLP-1R on the portal vein aﬀerent neurons and nodose ganglion in modulating intestinal fat absorption and lipoprotein produc-tion and identiﬁes other gut-derived peptides as novel regula-tors of postprandial *** from these data may support identiﬁcation of potential drug targets and the development of new therapeutics targeting treatment of dia-betic dyslipidemia.

关键词： glucagon-like peptide-1 lipid lipoprotein intes-tine neuroendocrine