检索结果-南通市图书馆

维普期刊数据库

Machine-learned wearable sensors for real-time hand-motion recognition: toward practical applications

在线全文

学校读者我要写书评

暂无评论

National Science Review 2024年第2期11卷 231-263页

作者： Kyung Rok Pyun Kangkyu Kwon Myung Jin Yoo Kyun Kyu Kim Dohyeon Gong Woon-Hong Yeo Seungyong Han Seung Hwan Ko department of mechanical engineering Seoul National University IEN Center for Human-Centric Interfaces and engineering Institute for Electronics and NanotechnologyGeorgia Institute of Technology School of Electrical and Computer engineering Georgia Institute of Technology department of Chemical engineering Stanford University department of mechanical engineering Ajou University George W.Woodruff School of mechanical engineering Georgia Institute of Technology Institute of Advanced Machinery and Design(SNU-IAMD) Seoul National University

Soft electromechanical sensors have led to a new paradigm of electronic devices for novel motion-based wearable applications in our daily lives. However, the vast amount of random and unidentified signals generated by complex body motions has hindered the precise recognition and practical application of this technology. Recent advancements in artificial-intelligence technology have enabled significant strides in extracting features from massive and intricate data sets, thereby presenting a breakthrough in utilizing wearable sensors for practical applications. Beyond traditional machine-learning techniques for classifying simple gestures, advanced machine-learning algorithms have been developed to handle more complex and nuanced motion-based tasks with restricted training data sets. Machine-learning techniques have improved the ability to perceive, and thus machine-learned wearable soft sensors have enabled accurate and rapid human-gesture recognition, providing real-time feedback to users. This forms a crucial component of future wearable electronics, contributing to a robust human–machine interface. In this review, we provide a comprehensive summary covering materials, structures and machine-learning algorithms for hand-gesture recognition and possible practical applications through machine-learned wearable electromechanical sensors.

关键词： wearable sensor soft electronics artificial intelligence machine learning human–machine interfaces gesture recognition

Effect of cooling media on bead geometry,microstructure,and mechanical properties of wire arc additive manufactured IN718 alloy

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Advances in Manufacturing 2024年第1期12卷 124-149页

作者： Parveen Kumar Satish Kumar Sharma Ratnesh Kumar Raj Singh department of mechanical engineering Thapar Institute of Engineering and TechnologyPatialaPunjab147004India

This work aims to present and explore thermal management techniques for the wire arc additive manufacturing(WAAM)of IN718 components.Excessive heat can be mitigated via air or water cooling.In this study,the material was deposited under four different heat-input conditions with air or water cooling.In air cooling,the layer is deposited in a normal atmospheric air environment,whereas with water cooling,the material is deposited inside a water tank by varying the water level.To validate the air and water cooling thermal management techniques,IN718 single-pass and multilayer linear walls were deposited using the bidirectional gas metal arc welding based WAAM setup under four different heat input conditions.During the deposition of single layers,the temperature profiles were recorded,and the geometric and microstructural features were explored.For multilayer wall structures,the mechanical properties(hardness,tensile strength,and elongation)were determined and assessed using the corresponding microstructural features explored through scanning electron microscopy(SEM),energy dispersive spectroscopy(EDS),and electron backscatter diffraction(EBSD)analyses.The microstructure observed through SEM analysis in the building direction was found to be nonhomogenous compared with that in the deposition direction.Moreover,water cooling was found to govern bead characteristics,such as wall width and height.The grain size and anisotropy of the mechanical properties also decreased in the water-cooled case.Hence,water cooling is an economical and efficient method to mitigate excessive heat accumulation in WAAM-deposited IN718.

关键词： Air cooling Water cooling IN718 Bead characteristics Microstructure Electron backscatter diffraction(EBSD)

Fault diagnosis of HVAC system with imbalanced data using multi-scale convolution composite neural network

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3期17卷 371-386页

作者： Rouhui Wu Yizhu Ren Mengying Tan Lei Nie School of mechanical engineering Hubei University of TechnologyWuhan430068China industrial Research Institute of Xiangyang Hubei University of technology Xiangyang441100China

Accurate fault diagnosis of heating,ventilation,and air conditioning(HVAC)systems is of significant importance for maintaining normal operation,reducing energy consumption,and minimizing maintenance costs.However,in practical applications,it is challenging to obtain sufficient fault data for HVAC systems,leading to imbalanced data,where the number of fault samples is much smaller than that of normal samples.Moreover,most existing HVAC system fault diagnosis methods heavily rely on balanced training sets to achieve high fault diagnosis accuracy.Therefore,to address this issue,a composite neural network fault diagnosis model is proposed,which combines SMOTETomek,multi-scale one-dimensional convolutional neural networks(M1DCNN),and support vector machine(SVM).This method first utilizes SMOTETomek to augment the minority class samples in the imbalanced dataset,achieving a balanced number of faulty and normal data.Then,it employs the M1DCNN model to extract feature information from the augmented dataset.Finally,it replaces the original Softmax classifier with an SVM classifier for classification,thus enhancing the fault diagnosis accuracy.Using the SMOTETomek-M1DCNN-SVM method,we conducted fault diagnosis validation on both the ASHRAE RP-1043 dataset and experimental dataset with an imbalance ratio of 1:10.The results demonstrate the superiority of this approach,providing a novel and promising solution for intelligent building management,with accuracy and F1 scores of 98.45%and 100%for the RP-1043 dataset and experimental dataset,respectively.

关键词： fault diagnosis chiller imbalanced data SMOTETomek multi-scale neural networks

Quasi-periodic orbits of small solar sails with time-varying attitude around Earth–Moon libration points

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Astrodynamics 2024年第1期8卷 161-174页

作者： Toshihiro Chujo department of mechanical engineering School of EngineeringTokyo Institute of TechnologyTokyo152-8550Japan

This paper proposes new quasi-periodic orbits around Earth–Moon collinear libration points using solar sails.By including the time-varying sail orientation in the linearized equations of motion for the circular restricted three-body problem(CR3BP),four types of quasi-periodic orbits(two types around L1 and two types around L2)were formulated.Among them,one type of orbit around L2 realizes a considerably small geometry variation while ensuring visibility from the Earth if(and only if)the sail acceleration due to solar radiation pressure is approximately of a certain magnitude,which is much smaller than that assumed in several previous studies.This means that only small solar sails can remain in the vicinity of L2 for a long time without propellant consumption.The orbits designed in the linearized CR3BP can be translated into nonlinear CR3BP and high-fidelity ephemeris models without losing geometrical characteristics.In this study,new quasi-periodic orbits are formulated,and their characteristics are discussed.Furthermore,their extendibility to higher-fidelity dynamic models was verified using numerical examples.

关键词： solar sail libration point orbit Earth-Moon system circular restricted three-body problem(CR3BP)

Broadband angular spectrum analog processors based on all-dielectric metasurfaces

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2024年第7期67卷 188-190页

作者： Lin Deng Yongmin Liu department of Electrical and Computer engineering Northeastern UniversityBoston 02115USA department of mechanical and industrial engineering Northeastern UniversityBoston 02115USA

Digital signal processors are extensively used to execute mathematical operations and advanced computational tasks on digital data.However,they suffer from several inherent limitations,including low speed,high energy consumption,and large memory requirements,because of the hardware bottleneck and the imperative conversion between digital and analogue signals.

关键词： dielectric spectrum hardware

维普期刊数据库

Predicting grain size-dependent superplastic properties in friction stir processed ZK30 magnesium alloy with machine learning methods

在线全文

学校读者我要写书评

暂无评论

Journal of Magnesium and Alloys 2024年第5期12卷 1931-1943页

作者： Farid Bahari-Sambran Fernando Carre?o C.M.Cepeda-Jiménez Alberto Orozco-Caballero Physical Metallurgy department CENIM-CSIC department of mechanical engineering Chemistry and Industrial Design Polytechnic University of Madrid

The aim of this work is to predict, for the first time, the high temperature flow stress dependency with the grain size and the underlaid deformation mechanism using two machine learning models, random forest（RF） and artificial neural network（ANN）. With that purpose, a ZK30 magnesium alloy was friction stir processed（FSP） using three different severe conditions to obtain fine grain microstructures（with average grain sizes between 2 and 3 μm） prone to extensive superplastic response. The three friction stir processed samples clearly deformed by grain boundary sliding（GBS） deformation mechanism at high temperatures. The maximum elongations to failure, well over 400% at high strain rate of 10-2s-1, were reached at 400 ℃ in the material with coarsest grain size of 2.8 μm, and at 300 ℃ for the finest grain size of 2 μm. Nevertheless, the superplastic response decreased at 350 ℃ and 400 ℃ due to thermal instabilities and grain coarsening, which makes it difficult to assess the operative deformation mechanism at such temperatures. This work highlights that the machine learning models considered, especially the ANN model with higher accuracy in predicting flow stress values, allow determining adequately the superplastic creep behavior including other possible grain size scenarios.

关键词： Machine learning Artificial intelligence Magnesium alloys Superplasticity Friction stir processing Grain coarsening

Comparative analysis of single-crater parameters in ultrasonic-assisted and unassisted micro-EDM of Ti6Al4V using discharge plasma imaging

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Nanotechnology and Precision engineering 2024年第2期7卷 11-24页

作者： Sohaib Raza Chandrakant Nirala department of mechanical engineering Indian Institute of Technology RoparPunjab 140001India

Ultrasonic-assisted micro-electro-discharge machining(EDM)has the potential to enhance processing responses such as material removal rate(MRR)and surface finish.To understand the reasons for this enhancement,the physical mechanisms responsible for the individual discharges and the craters that they form need to be explored.This work examines features of craters formed by single discharges at various parameter values in both conventional and ultrasonic-assistedEDM of Ti6Al4V.High-speed imaging of the plasma channel is performed,and data on the individual discharges are captured in real-time.A 2D axisymmetric model using finite element software is established to model crater formation.On the basis of simulation and experimental results,a comparative study is then carried out to examine the effects of ultrasonic vibrational assistance on crater geometry.For every set ofEDM parameters,the crater diameter and depth from a single discharge are found to be higher in ultrasonic-assistedEDM than in conventionalEDM.The improved crater geometry and the reduced bulge formation at the crater edges are attributed to the increased melt pool velocity and temperature predicted by the model.

关键词： Ultrasonic vibration Discharge crater Plasma diameter Single discharge

Gravity-driven powder flow and the influence of external vibration on flow characteristics

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Particuology 2024年第5期88卷 201-209页

作者： Muhammad Shahid Ansari Ratna Kumar Annabattula Sathyan Subbiah department of mechanical engineering Indian Institute of Technology MadrasChennai 600036India

The controlled and homogeneous flow of dry granular powders through hoppers is essential for applications,namely,packaging of food grains,fertilizers and additive manufacturing processes such as directed energy deposition for better product quality.One of the major issues encountered in the granular flows through hoppers is flow stagnation due to the well-known arching phenomenon.Vibration-assisted granular flow through hoppers is one of the mechanisms used for better mass flow control.In this work,the influence of external mechanical vibration on the powder flow is investigated experimentally and using discrete element simulations.First,the mass flow rate through the hopper increases with an increase in vibration amplitude and then decreases,signifying the existence of an optimal amplitude of vibration.The DEM simulations explained the underlying mechanisms for the existence of an optimal amplitude of vibration corresponding to the maximum mass flow rate.A range of vibration amplitudes from 0 mm to 3.5 mm is used to study the flow behaviour;the maximum flow of around 33 g/s to 35 g/s is observed for 0.75 mm to 1.25 mm vibration amplitude for the hopper-particle combination studied in this work.The work also reports the influence of vibration frequency,hopper,and particle dimension on the flow characteristics.The research facilitates the effective use of mechanical vibration to enhance powder flow that can further be extended to non-spherical and multi-material particles.

关键词： Discrete element method Flow rate Granular flow Path tracking Vibration intensity

Impact of Fin Arrangement on Heat Transfer and Melting Characteristics of Phase Change Material

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 435-456页

作者： Arun UNIYAL Yogesh K.PRAJAPATI department of mechanical engineering National Institute of Technology UttarakhandSrinagar(Garhwal)246174India department of mechanical engineering BIT SindriDhanbadJharkhand828123India

Present work investigates the heat transfer and melting behaviour of phase change material(PCM) in six enclosures(enclosure-1 to 6) filled with paraffin wax.Proposed enclosures are equipped with distinct arrangements of the fins while keeping the fin's surface area equal in each case.Comparative analysis has been presented to recognize the suitable fin arrangements that facilitate improved heat transfer and melting rate of the PCM.Left wall of the enclosure is maintained isothermal for the temperature values 335 K,350 K and 365 K.Dimensionless length of the enclosure including fins is ranging between 0 and 1.Results have been illustrated through the estimation of important performance parameters such as energy absorbing capacity,melting rate,enhancement ratio,and Nusselt number.It has been found that melting time(to melt 100% of the PCM) is 60.5%less in enclosure-2(with two fins of equal length) as compared to the enclosure-1,having no fins.Keeping the fin surface area equal,if the longer fin is placed below the shorter fin(enclosure-3),melting time is further decreased by 14.1% as compared to enclosure-2.However,among all the configurations,enclosure-6 with wire-mesh fin structure exhibits minimum melting time which is 68.4% less as compared to the enclosure-1.Based on the findings,it may be concluded that fins are the main driving agent in the enclosure to transfer the heat from heated wall to the PCM.Proper design and positioning of the fins improve the heat transfer rate followed by melting of the PCM in the entire area of the enclosure.Evolution of the favourable vortices and natural convection current in the enclosure accelerate the melting phenomenon and help to reduce charging time.

关键词： phase change material enclosure fin melting fraction energy storage heat transfer

维普期刊数据库