检索结果-南通市图书馆

Theoretical & Applied Mechanics Letters 2024年第1期14卷 27-34页

作者： Zilan Zhang Yu Ao Shaofan Li Grace X.Gu Department of Mechanical Engineering University of CaliforniaBerkeley 94720USA Department of Engineering Peking UniversityBeijing 100871China Department of Civil and Environmental Engineering University of CaliforniaBerkeley 94720USA

Conventional wing aerodynamic optimization processes can be time-consuming and imprecise due to the complexity of versatile flight missions.Plenty of existing literature has considered two-dimensional infinite airfoil optimization,while three-dimensional finite wing optimizations are subject to limited study because of high computational costs.Here we create an adaptive optimization methodology built upon digitized wing shape deformation and deep learning algorithms,which enable the rapid formulation of finite wing designs for specific aerodynamic performance demands under different cruise conditions.This methodology unfolds in three stages:radial basis function interpolated wing generation,collection of inputs from computational fluid dynamics simulations,and deep neural network that constructs the surrogate model for the optimal wing configuration.It has been demonstrated that the proposed methodology can significantly reduce the computational cost of numerical simulations.It also has the potential to optimize various aerial vehicles undergoing different mission environments,loading conditions,and safety requirements.

关键词： Aerodynamic optimization Computational fluid dynamics Radial basis function Finite wing deep learning neural network

基于水动力载荷混合数据集的高精度神经网络代理模型构建

在线全文

学校读者我要写书评

暂无评论

哈尔滨工程大学学报（英文版） 2024年第1期23卷 49-63页

作者：敖愈李云波李少凡龚家烨 College of Shipbuilding Engineering Harbin Engineering UniversityHarbin 150001China Department of Civil and Environmental Engineering University of CaliforniaBerkeleyCalifornia 94720USA College of Ocean Science and Engineering Shanghai Maritime UniversityShanghai 201303China

In this work,we constructed a neural network proxy model(NNPM)to estimate the hydrodynamic resistance in the ship hull structure design process,which is based on the hydrodynamic load data obtained from both the potential flow method(PFM)and the viscous flow method(VFM).Here the PFM dataset is applied for the tuning,pre-training,and the VFM dataset is applied for the fine-training.By adopting the PFM and VFM datasets simultaneously,we aim to construct an NNPM to achieve the high-accuracy prediction on hydrodynamic load on ship hull structures exerted from the viscous flow,while ensuring a moderate data-acquiring workload.The high accuracy prediction on hydrodynamic loads and the relatively low dataset establishment cost of the NNPM developed demonstrated the effectiveness and feasibility of hybrid dataset based NNPM achieving a high precision prediction of hydrodynamic loads on ship hull structures.The successful construction of the high precision hydrodynamic prediction NNPM advances the artificial intelligence-assisted design(AIAD)technology for various marine structures.

关键词： deep learning neural network Hybrid dataset Proxy model Ship hull design Machine learning

Chiller faults detection and diagnosis with sensor network and adaptive 1D CNN

在线全文

学校读者我要写书评

暂无评论

Digital Communications and networks 2022年第4期8卷 531-539页

作者： Ke Yan Xiaokang Zhou Department of the Built Environment National University of Singapore4 Architecture Drive117566Singapore Faculty of Data Science Shiga UniversityHikone5228522Japan RIKEN Center for Advanced Intelligence Project RIKENTokyo1030027Japan

Computer-empowered detection of possible faults for Heating,Ventilation and Air-Conditioning(HVAC)subsystems,e.g.,chillers,is one of the most important applications in Artificial Intelligence(AI)integrated Internet of Things(IoT).The cyber-physical system greatly enhances the safety and security of the working facilities,reducing time,saving energy and protecting humans’health.Under the current trends of smart building design and energy management optimization,Automated Fault Detection and Diagnosis(AFDD)of chillers integrated with IoT is highly demanded.Recent studies show that standard machine learning techniques,such as Principal Component Analysis(PCA),Support Vector Machine(SVM)and tree-structure-based algorithms,are useful in capturing various chiller faults with high accuracy rates.With the fast development of deep learning technology,Convolutional neural networks(CNNs)have been widely and successfully applied to various fields.However,for chiller AFDD,few existing works are adopting CNN and its extensions in the feature extraction and classification processes.In this study,we propose to perform chiller FDD using a CNN-based approach.The proposed approach has two distinct advantages over existing machine learning-based chiller AFDD methods.First,the CNN-based approach does not require the feature selection/extraction process.Since CNN is reputable with its feature extraction capability,the feature extraction and classification processes are merged,leading to a more neat AFDD framework compared to traditional approaches.Second,the classification accuracy is significantly improved compared to traditional methods using the CNN-based approach.

关键词： Chiller Fault detection and diagnosis deep learning neural network Long short term memory Recurrent neural network Gated recurrent unit

Integrated framework for seismic fragility assessment of cable-stayed bridges using deep learning neural networks

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(Technological Sciences) 2023年第2期66卷 406-416页

作者： PANG YuTao YIN PengCheng WANG JianGuo WU Li Faculty of Engineering China University of Geosciences(Wuhan)Wuhan 430074China China Railway Siyuan Survey and Design Group Co. Ltd.Wuhan 430074China Department of Civil Geological and Mining EngineeringPolytechnique MontréalMontréal H3C 3A7Canada

The increasing intensity of strong earthquakes has a large impact on the seismic safety of bridges worldwide.As the key component in the transportation network,the cable-stayed bridge should cope with the increasing future hazards to improve seismic safety.Seismic fragility analysis can assist the resilience assessment under different levels of seismic intensity.However,such an analysis is computationally intensive,especially when considering various random factors.The present paper implemented the deep learning neural networks that are integrated into the performance-based earthquake engineering framework to predict fragility functions and associated resilience index of cable-stayed bridges under seismic hazards to improve the computational efficiency while having sufficient accuracy.In the proposed framework,the Latin hypercube sampling was improved with additional uniformity to enhance the training process of the neural network.The well-trained neural network was then applied in a probabilistic simulation process to derive different component fragilities of the cable-stayed bridge.The estimated fragility functions were combined with the Monte Carlo simulations to predict system resilience.The proposed integrated framework in this study was demonstrated on an existing single-pylon cable-stayed bridge in China.Results reveal that this integrated framework yields accurate predictions of fragility functions for the cable-stayed bridge and has reasonable accuracy compared with the conventional methods.

关键词： deep learning neural network cable-stayed bridge fragility analysis uniform design method seismic resilience

An artificial intelligence-aided design (AIAD) of ship hull structures

在线全文

学校读者我要写书评

暂无评论

Journal of Ocean Engineering and Science 2023年第1期8卷 15-32页

作者： Yu Ao Yunbo Li Jiaye Gong Shaofan Li College Of Shipbuilding Engineering Harbin Engineering UniversityChina Department of Civil and Environmental Engineering University of CaliforniaBerkeleyCA 94720USA College of Ocean Science and Engineering Shanghai Maritime UniversityChina

Ship-hull design is a complex process because the any slight local alteration in ship hull structure may significantly change the hydrostatic and hydrodynamic performances of a ship.To find the optimum hull shape under the design requirements,the state-of-art of ship hull design combines computational fluid dynamics computation with geometric modeling.However,this process is very computationally intensive,which is only suitable at the final stage of the design process.To narrow down the design parameter space,in this work,we have developed an AI-based deep learning neural network to realize a real-time prediction of the total resistance of the ship-hull structure in its initial design process.In this work,we have demonstrated how to use the developed DNN model to carry out the initial ship hull design.The validation results showed that the deep learning model could accurately predict the ship hull’s total resistance accurately after being trained,where the average error of all samples in the testing dataset is lower than 4%.Simultaneously,the trained deep learning model can predict the hip’s performances in real-time by inputting geometric modification parameters without tedious preprocessing and calculation processes.The machine learning approach in ship hull design proposed in this work is the first step towards the artificial intelligence-aided design in naval architectures.

关键词： Artificial intelligence deep learning neural network Hull deformation Machine learning Ship hull design Total resistance

Courtyard design impact on indoor thermal comfort and utility costs for residential households: Comparative analysis and deep-learning predictive model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Architectural Research 2022年第5期11卷 963-980页

作者： Amir Tabadkani Sara Aghasizadeh Saeed Banihashemi Aso Hajirasouli School of Architecture and Built Environment Deakin UniversityGeelongAustralia Department of Architectural Technology Faculty of Architecture and UrbanismUniversity of ArtTehranIran Design&Built Environment School University of CanberraCanberraAustralia School of Architecture and Built Environment Queensland University of TechnologyQueenslandAustralia

A courtyard is an architectural design element which is often known as microclimate modifiers and is responsible to increase the indoor occupant comfort in traditional architecture. The aim of this study is to conduct a parametric evaluation of courtyard design variants in a residential building of different climates with a focus on indoor thermal comfort and utility costs. A brute-force approach is applied to generate a wide range of design alternatives and the simulation workflow is conducted by Grasshopper together with the environmental plugins Ladybug and Honeybee. The main study objective is the evaluation of the occupant thermal comfort in an air-conditioned residential building, energy load, and cost analysis, derived from different design variables including courtyard geometry, window-to-wall ratio, envelope materials, heating, and cooling set-point dead-bands, and building geographical location. Furthermore, a deep learning model is developed using the inputs and outputs of the simulation and analysis to transform the outcomes into the algorithmic and tangible environment feasible for predictive applications. The results suggest that regarding the thermal loads, costs, and indoor thermal comfort index (PMV), there are high correlations between the outdoor weather variation and dead-band ranges, while in extreme climates such as Singapore, courtyard spaces might not be efficient enough as expected. Finally, the highly accurate deep learning model is also developed, delivering superior predictive capabilities for the thermal comfort and utility costs of the courtyard designs.

关键词： Parametric design Courtyard microclimate Occupant comfort Building energy consumption deep learning neural network Residential

deepIoT.IDS:Hybrid deep learning for Enhancing IoT network Intrusion Detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第12期69卷 3945-3966页

作者： Ziadoon K.Maseer Robiah Yusof Salama A.Mostafa Nazrulazhar Bahaman Omar Musa Bander Ali Saleh Al-rimy Faculty of Information and Communication Technology Universiti Teknikal MalaysiaMelaka76100Malaysia Center of Intelligent and Autonomous Systems Faculty of Computer Science and Information TechnologyUniversiti Tun Hussein Onn MalaysiaJohor86400Malaysia Faculty of Business and Technology UNITAR International UniversitySelangor47301Malaysia School of Computing Faculty of EngineeringUniversiti Teknologi MalaysiaJohor81310Malaysia

With an increasing number of services connected to the internet,including cloud computing and Internet of Things(IoT)systems,the prevention of cyberattacks has become more challenging due to the high dimensionality of the network traffic data and access points.Recently,researchers have suggested deep learning(DL)algorithms to define intrusion features through training empirical data and learning anomaly patterns of attacks.However,due to the high dynamics and imbalanced nature of the data,the existing DL classifiers are not completely effective at distinguishing between abnormal and normal behavior line connections for modern networks.Therefore,it is important to design a self-adaptive model for an intrusion detection system(IDS)to improve the detection of attacks.Consequently,in this paper,a novel hybrid weighted deep belief network(HW-DBN)algorithm is proposed for building an efficient and reliable IDS(deepIoT.IDS)model to detect existing and novel cyberattacks.The HW-DBN algorithm integrates an improved Gaussian–Bernoulli restricted Boltzmann machine(deep GB-RBM)feature learning operator with a weighted deep neural networks(WDNN)classifier.The CICIDS2017 dataset is selected to evaluate the deepIoT.IDS model as it contains multiple types of attacks,complex data patterns,noise values,and imbalanced classes.We have compared the performance of the deepIoT.IDS model with three recent models.The results show the deepIoT.IDS model outperforms the three other models by achieving a higher detection accuracy of 99.38%and 99.99%for web attack and bot attack scenarios,respectively.Furthermore,it can detect the occurrence of low-frequency attacks that are undetectable by other models.

关键词： Cyberattacks internet of things intrusion detection system deep learning neural network supervised and unsupervised deep learning

General seismic wave and phase detection software driven by deep 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

Earthquake Research Advances 2021年第3期1卷 38-45页

作者： Ming Zhao Jiahui Ma Hao Chang Shi Chen Institute of Geophysics China Earthquake AdministrationBeijing100081China Beijing Baijiatuan Earth Science National Observation and Research Station Beijing100095China National Space Science Center The Chinese Academy of SciencesBeijing100190China Institute of Microelectronics The Chinese Academy of SciencesBeijing100029China

We developed an automatic seismic wave and phase detection software based on PhaseNet,an efficient and highly generalized deep learning neural network for P-and S-wave phase picking.The software organically combines multiple modules including application terminal interface,docker container,data visualization,SSH protocol data transmission and other auxiliary modules.Characterized by a series of technologically powerful functions,the software is highly convenient for all users.To obtain the P-and S-wave picks,one only needs to prepare threecomponent seismic data as input and customize some parameters in the interface.In particular,the software can automatically identify complex waveforms(i.***.continuous or truncated waves)and support multiple types of input data such as SAC,MSEED,NumPy array,etc.A test on the dataset of the Wenchuan aftershocks shows the generalization ability and detection accuracy of the software.The software is expected to increase the efficiency and subjectivity in the manual processing of large amounts of seismic data,thereby providing convenience to regional network monitoring staffs and researchers in the study of Earth's interior.

关键词： deep learning neural network Seismic phase detection Docker container