检索结果-南通市图书馆

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1190-1201页

作者： Xiangqian Yao hao sun Zhijia Zhao Yu Liu School of Automation Science and Engineering South China University of TechnologyGuangzhou 510640China Yongjiang Laboratory Ningbo 315202 School of Astronautics Harbin Institute of TechnologyHarbin 150001China School of Mechanical and Electrical Engineering Guangzhou UniversityGuangzhou 510006China

For bipartite angle consensus tracking and vibration suppression of multiple Timoshenko manipulator systems with time-varying actuator faults,parameter and modeling uncertainties,and unknown disturbances,a novel distributed boundary event-triggered control strategy is proposed in this *** contrast to the earlier findings,time-varying consensus tracking and actuator defects are taken into account *** addition,the constructed event-triggered control mechanism can achieve a more flexible design because it is not required to satisfy the input-to-state *** achieve the control objectives,some new integral control variables are given by using back-stepping technique and boundary ***,adaptive neural networks are applied to estimate system *** the proposed event-triggered scheme,control inputs can reduce unnecessary ***,tracking errors and vibration states of the closed-looped network can be exponentially convergent into some small fields,and Zeno behaviors can be *** last,some simulation examples are given to state the effectiveness of the control algorithms.

关键词： Vibration satisfy bipartite

FL-EASGD:Federated Learning Privacy Security Method Based on Homomorphic Encryption

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 2361-2373页

作者： hao sun Xiubo Chen Kaiguo Yuan Information Security Center State Key Laboratory ofNetworking and Switching TechnologyBeijing University of Posts and TelecommunicationsBeijing100876China

Federated learning ensures data privacy and security by sharing models among multiple computing nodes instead of plaintext ***,there is still a potential risk of privacy leakage,for example,attackers can obtain the original data through model inference ***,safeguarding the privacy of model parameters becomes *** proposed solution involves incorporating homomorphic encryption algorithms into the federated learning ***,the existing federated learning privacy protection scheme based on homomorphic encryption will greatly reduce the efficiency and robustness when there are performance differences between parties or abnormal *** solve the above problems,this paper proposes a privacy protection scheme named Federated Learning-Elastic Averaging Stochastic Gradient Descent(FL-EASGD)based on a fully homomorphic encryption ***,this paper introduces the homomorphic encryption algorithm into the FL-EASGD scheme to preventmodel plaintext leakage and realize privacy security in the process ofmodel ***,this paper designs a robust model aggregation algorithm by adding time variables and constraint coefficients,which ensures the accuracy of model prediction while solving performance differences such as computation speed and node anomalies such as downtime of each *** addition,the scheme in this paper preserves the independent exploration of the local model by the nodes of each party,making the model more applicable to the local data ***,experimental analysis shows that when there are abnormalities in the participants,the efficiency and accuracy of the whole protocol are not significantly affected.

关键词： Federated learning homomorphic encryption privacy security stochastic gradient descent

Online control for pressure regulation of oxygen mask based on 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

Control Theory and Technology 2024年第3期22卷 487-501页

作者： Ligan Zhao Qinglin sun hao sun Jin Tao Zengqiang Chen College of Artificial Intelligence Nankai UniversityTianjin 300350China Silo Al Helsinki 00100Finland

The aviation oxygen mask,which has a small volume of less than 1L and strong air tightness,imposes extremely high requirements on control performance of the oxygen *** on analyses of the operation principle of oxygen supply system,the dynamic model is established through the combination of mechanism analysis and experimental *** that the traditional fixed-parameter controllers are difficult to meet the control requirements with changes in pulmonary ventilation,this paper presents an online feedback controller based on neural network compensation(NNC),with connection weights that can be updated without *** mathematical simulations at different respiratory parameters,such as respiratory rate,are performed to verify the superior lower inspiratory resistance of controller with *** terms of hardware,an embedded AI control platform is to complete the experimental ***,the work may have downward compatibility to achieve stable oxygen supply in civil fields,such as medical ventilators,high-altitude expeditions.

关键词： Neural network Online control Pressure regulation AI platform

Probabilistic seismic inversion based on physics-guided deep mixture density 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

Petroleum Science 2024年第3期21卷 1611-1631页

作者： Qian-hao sun Zhao-Yun Zong Xin Li National Key Laboratory of Deep Oil and Gas China University of Petroleum(East China)Qingdao266580ShandongChina Laoshan Laboratory Qingdao266580ShandongChina CNOOC Research Institute Ltd. Beijing100028China

Deterministic inversion based on deep learning has been widely utilized in model parameters *** by logging data,seismic data,wavelet and modeling operator,deterministic inversion based on deep learning can establish nonlinear relationships between seismic data and model ***,seismic data lacks low-frequency and contains noise,which increases the non-uniqueness of the *** conventional inversion method based on deep learning can only establish the deterministic relationship between seismic data and parameters,and cannot quantify the uncertainty of *** order to quickly quantify the uncertainty,a physics-guided deep mixture density network(PG-DMDN)is established by combining the mixture density network(MDN)with the deep neural network(DNN).Compared with Bayesian neural network(BNN)and network dropout,PG-DMDN has lower computing cost and shorter training time.A low-frequency model is introduced in the training process of the network to help the network learn the nonlinear relationship between narrowband seismic data and low-frequency *** addition,the block constraints are added to the PG-DMDN framework to improve the horizontal continuity of the inversion *** illustrate the benefits of proposed method,the PG-DMDN is compared with existing semi-supervised inversion *** synthetic data examples of Marmousi II model are utilized to quantify the influence of forward modeling part,low-frequency model,noise and the pseudo-wells number on inversion results,and prove the feasibility and stability of the proposed *** addition,the robustness and generality of the proposed method are verified by the field seismic data.

关键词： Deep learning Probabilistic inversion Physics-guided Deep mixture density network

Surface roughness classification using light scattering matrix and deep learning

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2024年第2期67卷 520-535页

作者： sun hao TAN Wei RUAN YiXiao BAI Long XU JianFeng State Key Laboratory of Intelligent Manufacturing Equipment and Technology School of Mechanical Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China Wuhan Digital Design and Manufacturing Innovation Center Co. LtdWuhan 430074China

High-quality optical components have been widely used in various applications;thus,extremely high beam quality is ***,surface roughness is a key indicator of the surface *** this study,the angular distribution of light scattering field intensity was obtained for surfaces having different roughness profiles based on the finite difference time domain(FDTD)method,and the results were compared with those obtained using the generalized Harvey-Shack(GHS)*** was shown that the FDTD approach can be used for an accurate simulation of the scattered field of a rough surface,and the superposition of results obtained from many surfaces that have the same roughness level was in good agreement with the result given by the analytic GHS model.A light scattering matrix(LSM)method was proposed based on the FDTD simulation results that could obtain rich surface roughness *** classification effect of LSM was compared with that of the single-incidence scattering distribution(SISD)based on a ResNet-50 deep learning *** classification accuracy of the model trained with the LSM dataset was obtained as 95.74%,which was 23.40%higher than that trained using the SISD ***,the effects of different noise types and filtering methods on the classification performance were analyzed,and the LSM was also shown to improve the robustness and generalizability of the trained surface roughness ***,the proposed LSM method has important implications for improving the data acquisition scheme of current light scattering measurement systems,and it also has the potential to be used for detection and characterization of surface defects of optical components.

关键词： surface roughness FDTD simulation GHS theory deep learning light scattering matrix

Large reversible magnetocaloric effect in antiferromagnetic Er_(3)Si_(2)C_(2) compound

在线全文

学校读者我要写书评

暂无评论

Journal of Rare Earths 2024年第8期42卷 1555-1559,I0005页

作者： hao sun Lu Tian Xinqiang Gao Zhaojun Mo Jun Shen Baogen Shen School of Rare Earths University of Science and Technology of ChinaHefei230026China Ganjiang Innovation Academy Chinese Academy of SciencesGanzhou341000China Department of Energy and Power Engineering School of Mechanical EngineeringBeijing Institute of TechnologyBeijing100081China

The magnetic properties,magnetic phase transition and magnetocaloric effects(MCE) of Er_(3)Si_(2)C_(2) compound were investigated based on theoretical calculations and experimental *** on the first principles calculations,the antiferromagnetic(AFM) ground state type in Er_(3)Si_(2)C_(2) compound was predicted and its electronic structure was *** experimental results show that Ei_(3)Si_(2)C_(2) compound is an AFM compound with the Neel temperature(T_(N) of 7 K and undergoes a field-induced firstorder magnetic phase transition from AFM to ferromagnetic(FM) under magnetic fields exceeding 0.6 T at 2 *** magnetic transition process of Er_(3)Si_(2)C_(2) compound was investigated and *** values of the maximum magnetic entropy change(-ΔS_(M)^(max)) and the refrigeration capacity(RC) are 17 J/(kg·K)and 193 J/kg under changing magnetic fields of 0-5 T,*** a potential cryogenic magnetic refrigerant,the Er_(3)Si_(2)C_(2) compound also provides an interesting research medium to study the magnetic phase transition process.

关键词： Magnetic materials Magnetocaloric Metamagnetic transitions Magnetic phase transition Rare earths

UDT:U-shaped deformable transformer for subarachnoid haemorrhage image segmentation

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 756-768页

作者： Wei Xie Lianghao Jin Shiqi Hua hao sun Bo sun Zhigang Tu Jun Liu Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning Central China Normal UniversityWuhanChina School of Computer Science Central China Normal UniversityWuhanChina National Language Resources Monitoring and Research Center for Network Media Central China Normal UniversityWuhanChina The First Affiliated Hospital of Dalian Medical University DalianChina State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan UniversityWuhanChina Information Systems Technology and Design Pillar Singapore University of Technology and DesignSingaporeSingapore

Subarachnoid haemorrhage(SAH),mostly caused by the rupture of intracranial aneu-rysm,is a common disease with a high fatality *** lesions are generally diffusely distributed,showing a variety of scales with irregular *** complex characteristics of lesions make SAH segmentation a challenging *** cope with these difficulties,a u-shaped deformable transformer(UDT)is proposed for SAH ***,first,a multi-scale deformable attention(MSDA)module is exploited to model the diffuseness and scale-variant characteristics of SAH lesions,where the MSDA module can fuse features in different scales and adjust the attention field of each element dynamically to generate discriminative multi-scale ***,the cross deformable attention-based skip connection(CDASC)module is designed to model the irregular edge char-acteristic of SAH lesions,where the CDASC module can utilise the spatial details from encoder features to refine the spatial information of decoder ***,the MSDA and CDASC modules are embedded into the backbone Res-UNet to construct the proposed *** experiments are conducted on the self-built SAH-CT dataset and two public medical datasets(GlaS and MoNuSeg).Experimental results show that the presented UDT achieves the state-of-the-art performance.

关键词： image segmentation medical image processing

Martensite decomposition under thermal-mechanical coupling conditions to fabricate an ultrafine-grained Ti6Al4Mo4Zr1W0.2Si alloy

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 Materials Science & Technology 2024年第1期168卷 157-168页

作者： Taoyu Zhou Jiuxu Yang Nan Li hao sun Bohua Zhang Zibo Zhao Qingjiang Wang Shi-changxu Innovation Center for Advanced Materials Institute of Metal ResearchChinese Academy of SciencesShenyang 110016China School of Materials Science and Engineering University of Science and Technology of ChinaShenyang 110016China

The fabrication of ultrafine-grained microstructures(grain size below 1μm)in titanium alloys is beneficial for improving their mechanical properties at room temperature and medium tempera-tures(400-550°C).However,a long-standing challenge involves the low-cost manufacturing of bulk ultrafine-grained titanium *** this work,we developed a facile strategy through martensite de-composition at thermal-mechanical coupling conditions,to fabricate an equiaxed microstructure in a Ti6Al4Mo4Zr1W0.2Si model alloy with an averageαgrain size of 315±62 *** formation of the ultrafine-grained microstructure was because the lattice strain stored in the martensitic initial mi-crostructure enhanced the nucleation rate of dynamic recrystallization,meanwhile,the pinning role of martensite decomposition productsβand(Ti,Zr)_(5)Si_(3)phases suppressed grain coarsening at high *** to conventional(α+β)alloys,the tensile strength of this alloy improved by 20%-30%at both room temperature and 550°C,without decreasing its *** situ SEM observations revealed that the ultrafine-grained microstructure would not only suppress dislocation motions but also contribute to the homogenous deformation in the matrix of the material,therefore,it resulted in higher mechanical *** research results may be of great significance to the development of next-generation aviation titanium alloys.

关键词： Ultrafine-grained Titanium alloy In situ observation Deformation mechanism Thermostability

Discharge evolution law of debris flow based on a sharp bend physical modeling test

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 Mountain Science 2024年第6期21卷 1904-1915页

作者： LU Ming sun hao LIU Jinfeng Abrar HUSSAIN SHANG Yuqi FU Hang Key Laboratory of Mountain Hazards and Earth Surface Process Chinese Academy of SciencesChengdu 610041China Institute of Mountain Hazards and Environment Chinese Academy of SciencesChengdu 610041China University of Chinese Academy of Sciences Beijing 100049China

For the basins with debris flow development,its channel terrain exhibits a tortuous shape,which significantly restricts the movement of debris flows and leads to severe erosion effects on the concave ***,this study aims to analyze the shear force of debris flows within the bend *** established the relationship between the shear force and bend curvature through laboratory *** the long-term erosion by debris flows,the curvature radius of bends gradually increases,however,when this increasing trend reaches an equilibrium state with the intensity of debris flow discharge,there will be no significant change in curvature *** general,the activity pattern and discharges of debris flows would remain relatively ***,we can infer the magnitude of debris flow discharges from the terrain parameters of the bend channel.

关键词： Debris flow discharge Erosion effect Bend channel Curvature radius

Seasonal changes in gut microbiota of sea cucumber over natural aestivation cycle

在线全文

学校读者我要写书评

暂无评论

Journal of Oceanology and Limnology 2024年第3期42卷 849-864页

作者： Ye Zhao Han WANG haona WANG Lijie ZHANG hao sun Yanying ZHANG Ocean School Yantai UniversityYantai 264005China

Sea cucumber Apostichopus japonicus is an ideal model organism for marine invertebrate aestivation;it annually enters a“sleeping state”for nearly 3 months when ambient water temperature range is 25–30℃.The natural fasting is accompanied by remodeling the intestinal biota and function,which is a part of host biology and could affect the gut *** investigatesd the impact of annual aestivation on gut microbiota using high-throughput sequencing of 16S rRNA *** reveal a notable alteration in the composition of gut bacteria during aestivation during which various indigenous families and genera that exhibit a preference for dietary glycans(e.g.,family Rhodobacteraceae and Flavobacteriaceae)decreased,while the taxa capable of utilizing substrates derived from the host(e.g.,genus Akkermansia and Prevotella)increased,and so did certain opportunistic pathogenic ***,the investigation delved into the gut morphology and immunity response of *** and reveal that the intestine of *** undergoes substantial atrophy and degeneration during ***,there was an observed augmentation in the levels of acid and neutral mucin within mucous cells,as well as an enhanced immune defense response(as evidenced by increased gene expression of AjTLR3,LITAF,Ajp105,and LYZ).These results imply that the composition of sea cucumber gut microbiota differed between aestivation and active periods,which potentially affects the intestinal functions of the host and the symbiotic relationship between host and its microbiota over the activeaestivation cycle.

关键词： Apostichopus japonicus aestivation gut microbiota diet Illumina sequencing