检索结果-南通市图书馆

Chinese Journal of Aeronautics 2024年第12期37卷 212-230页

作者： Ying HUANG Jianguo ZHANG Xiaoduo FAN Qi GONG Lukai SONG School of Reliability and Systems Engineering Beihang UniversityBeijing 100191China AVIC Aero Polytechnology Establishment Beijing 100028China Department of Mechanical Engineering The Hong Kong Polytechnic UniversityHong Kong 100872China Research Institute of Aero-Engine Beihang UniversityBeijing 102206China

Estimating the failure probability of highly reliable structures in practice engineering,such as aeronautical components,is challenging because of the strong-coupling and the small failure probability *** this paper,an Expanded Learning Intelligent back propagation(EL-IBP)neural network approach is developed:firstly,to accurately characterize the engineering response coupling relationships,a high-fidelity Intelligent-optimized back propagation(IBP)neural network metamodel is developed;furthermore,to elevate the analysis efficacy for small failure assessment,a novel expanded learning strategy for adaptive IBP metamodeling is *** numerical examples and one typical practice engineering case are analyzed,to validate the effectiveness and engineering application value of the proposed *** comparison shows that the ELIBP method holds significant efficiency and accuracy superiorities in engineering *** current study may shed a light on pushing the adaptive metamodeling technique deeply toward complex engineering reliability analysis.

关键词： Reliability analysis back propagation neural network Adaptive metamodel Variance expansion Small failure probability Strong-coupling

Porosity Prediction from Well Logs Using back propagation neural network Optimized by Genetic Algorithm in One Heterogeneous Oil Reservoirs of Ordos Basin, 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

Journal of Earth Science 2021年第4期32卷 828-838页

作者： Lin Chen Weibing Lin Ping Chen Shu Jiang Lu Liu Haiyan Hu Wuhan Center China Geological SurveyWuhan 430205China Energy and Geoscience Institute University of UtahSalt Lake City 84108USA Hubei Key Laboratory of Marine Geological Resources China University of GeosciencesWuhan 430074China College of Marine Science and Technology China University of GeosciencesWuhan 430074China Key Laboratory of Tectonics and Petroleum Resources of Ministry of Education China University of GeosciencesWuhan 430074China Exploration and Development Institute Huabei Branch Company of SINOPECZhengzhou 450006China School of Geosciences Yangtze UniversityWuhan 430100China

A reliable and effective model for reservoir physical property prediction is a key to reservoir characterization and *** present,using well logging data to estimate reservoir physical parameters is an important means for reservoir *** on the characteristics of large quantity and complexity of estimating process,we have attempted to design a nonlinear back propagation neural network model optimized by genetic algorithm(BPNNGA)for reservoir porosity *** model is with the advantages of self-learning and self-adaption of back propagation neural network(BPNN),structural parameters optimizing and global searching optimal solution of genetic algorithm(GA).The model is applied to the Chang 8 oil group tight sandstone of Yanchang Formation in southwestern Ordos *** to the correlations between well logging data and measured core porosity data,5 well logging curves(gamma ray,deep induction,density,acoustic,and compensated neutron)are selected as the input neurons while the measured core porosity is selected as the output *** number of hidden layer neurons is defined as 20 by the method of multiple calibrating *** results demonstrate that the average relative error of the model output is 10.77%,indicating the excellent predicting effect of the *** predicting results of the model are compared with the predicting results of conventional multivariate stepwise regression algorithm,and BPNN *** average relative errors of the above models are 12.83%,12.9%,and 13.47%,*** show that the predicting results of the BPNNGA model are more accurate than that of the other two,and BPNNGA is a more applicable method to estimate the reservoir porosity parameters in the study area.

关键词： porosity prediction well logs back propagation neural network genetic algorithm Ordos Basin Yanchang Formation

同方期刊数据库

Gear Fault Detection Analysis Method Based on Fractional Wavelet Transform and back propagation neural network

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2019年第12期121卷 1011-1028页

作者： Yanqiang Sun Hongfang Chen Liang Tang Shuang Zhang Beijing Engineering Research Center of Precision Measurement Technology and Instruments Beijing University of TechnologyBeijing100124China

A gear fault detection analysis method based on Fractional Wavelet Transform(FRWT)and back propagation neural network(BPNN)is *** the changing order as the variable,the optimal order of gear vibration signals is determined by discrete fractional Fourier *** the optimal order,the fractional wavelet transform is applied to eliminate noise from gear vibration *** this way,useful components of vibration signals can be successfully separated from background ***,a set of feature vectors obtained by calculating the characteristic parameters for the de-noised signals are used to characterize the gear vibration ***,the feature vectors are divided into two groups,including training samples and testing samples,which are input into the BPNN for learning and *** results showed that this gear fault detection analysis method could well maintain the useful signal components related to gear faults and effectively extract the weak fault *** accuracy rate reached 96.67%in the identification of the type of gear fault.

关键词： Gear fault detection preparation factional wavelet transform back propagation neural network

Shallow water bathymetry based on a back propagation neural network and ensemble learning using multispectral satellite imagery

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 Oceanologica Sinica 2023年第5期42卷 154-165页

作者： Sensen Chu Liang Cheng Jian Cheng Xuedong Zhang Jie Zhang Jiabing Chen Jinming Liu Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology Nanjing UniversityNanjing 210023China Collaborative Innovation Center of South China Sea Studies Nanjing UniversityNanjing 210093China School of Geography and Ocean Science Nanjing UniversityNanjing 210023China Jiangsu Center for Collaborative Innovation in Novel Software Technology and Industrialization Nanjing 210023China Zhejiang Institute of Hydraulics and Estuary Hangzhou 310020China Institute of Defense Engineering Academy of Military SciencesBeijing 100036China

The back propagation(BP)neural network method is widely used in bathymetry based on multispectral satellite ***,the classical BP neural network method faces a potential problem because it easily falls into a local minimum,leading to model training *** study confirmed that the local minimum problem of the BP neural network method exists in the bathymetry field and cannot be ***,to solve the local minimum problem of the BP neural network method,a bathymetry method based on a BP neural network and ensemble learning(BPEL)is ***,the remote sensing imagery and training sample were used as input datasets,and the BP method was used as the base learner to produce multiple water depth inversion ***,a new ensemble strategy,namely the minimum outlying degree method,was proposed and used to integrate the water depth inversion ***,an ensemble bathymetric map was *** Reef,northeastern Jiuzhang Atoll,and Pingtan coastal zone were selected as test cases to validate the proposed *** with the BP neural network method,the root-mean-square error and the average relative error of the BPEL method can reduce by 0.65–2.84 m and 16%–46%in the three test cases at *** results showed that the proposed BPEL method could solve the local minimum problem of the BP neural network method and obtain highly robust and accurate bathymetric maps.

关键词： bathymetry back propagation neural network ensemble learning local minimum problem multispectral satellite imagery

Prediction of SMILE surgical cutting formula based on back propagation neural network

在线全文

学校读者我要写书评

暂无评论

International Journal of Ophthalmology(English edition) 2023年第9期16卷 1424-1430页

作者： Dong-Qing Yuan Fu-Nan Tang Chun-Hua Yang Hui Zhang Ying Wang Wei-Wei Zhang Liu-Wei Gu Qing-Huai Liu Department of Ophthalmology Jiangsu Province Hospital(the First Affiliated Hospital with Nanjing Medical University)Nanjing 210029Jiangsu ProvinceChina Clinical Medical Engineering Department Jiangsu Province Hospital(the First Affiliated Hospital with Nanjing Medical University)Nanjing 210029Jiangsu ProvinceChina

AIM:To predict cutting formula of small incision lenticule extraction(SMILE)surgery and assist clinicians in identifying candidates by deep learning of back propagation(BP)neural ***:A prediction program was developed by a BP neural *** were 13188 pieces of data selected as training *** 840 eye samples from 425 patients were recruited for reverse verification of training *** of prediction by BP neural network and lenticule thickness error between machine learning and the actual lenticule thickness in the patient data were ***:After training 2313 epochs,the predictive SMILE cutting formula BP neural network models performed *** values of mean squared error and gradient are 0.248 and 4.23,*** scatterplot with linear regression analysis showed that the regression coefficient in all samples is *** final error accuracy of the BP neural network is-0.003791±0.4221102μ***:With the help of the BP neural network,the program can calculate the lenticule thickness and residual stromal thickness of SMILE surgery *** with corneal parameters and refraction of patients,the program can intelligently and conveniently integrate medical information to identify candidates for SMILE surgery.

关键词： small incision lenticule extraction back propagation neural network deep learning cutting formula prediction

Research on Face Recognition Based on back propagation 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

Research on Face Recognition Based on Back Propagation Neura...

A Hybrid Model Based on back-propagation neural network and Optimized Support Vector Machine with Particle Swarm Algorithm for Assessing Blade Icing on Wind Turbines

2010 3rd International Conference on Computer and Electrical Engineering(ICCEE 2010)

作者： Lingyun Shen Lingyun Shen Baihe Lang Tailin Han Yang Li Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences College of Electronic Science and Engineering Changchun University of Science and Technology

A new method, face recognition based on back propagation neural network, is presented in this paper. The proposed method extracts feature from face image with differential projection and geometrical features into eigenvector which is classified by back propagation neural network. Besides our method, the principal component analysis (PCA)-based method, the linear discriminated analysis (LDA)-based method and the Markov Random Fields (MRF)-based method were also tested for comparisons. The experimental results on ORL face database show that the proposed method achieves an average recognition accuracy of over 98% by using only 13 features. Moreover, the recognition accuracy is enhanced effectively, and the computational complexity and feature dimensions are reduced greatly.

关键词： face recognition back propagation neural network image eigenvector

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Energy Engineering 2021年第6期118卷 1869-1886页

作者： Xiyang Li Bin Cheng Hui Zhang Xianghan Zhang Zhi Yun College of Mechanical and Electrical Engineering Shihezi UniversityShihezi832003China Key Laboratory of Northwest Agricultural Equipment Ministry of Agriculture and Rural AffairsShihezi832003China

With the continuous increase in the proportional use of wind energy across the globe,the reduction of power generation efficiency and safety hazards caused by the icing on wind turbine blades have attracted more consideration for ***,it is crucial to accurately analyze the thickness of icing on wind turbine blades,which can serve as a basis for formulating corresponding control measures and ensure a safe and stable operation of wind turbines in winter times and/or in high altitude *** paper fully utilized the advantages of the support vector machine(SVM)and back-propagation neural network(BPNN),with the incorporation of particle swarm optimization(PSO)algorithms to optimize the parameters of the *** paper proposes a hybrid assessment model of PSO-SVM and BPNN based on dynamic weighting *** sets of icing data under a rotating working state of the wind turbine were used as examples for model *** on a comparative analysis with other models,the results showed that the proposed model has better accuracy and stability in analyzing the icing on wind turbine blades.

关键词： Support vector machine back propagation neural network particle swarm optimization blade icing assessment

Collaborative optimization design of process parameter and structural topology for laser additive manufacturing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2023年第1期36卷 456-467页

作者： Shaoying LI Hongkai WEI Shangqin YUAN Jihong ZHU Jiang LI Weihong ZHANG State IJR Center of Aerospace Design and Additive Manufacturing Northwestern Polytechnical UniversityXi’an 710072China MIIT Lab of Metal Additive Manufacturing and Innovative Design Northwestern Polytechnical UniversityXi’an 710072China Unmanned System Research Institute Northwestern Polytechnical UniversityXi’an 710072China

High-resolution laser additive manufacturing(LAM)significantly releases design free-dom,promoting the development of topology optimization(TO)and advancing structural design *** order to fully take advantage of voxelated forming methods and establish the quantitative relationship between the mechanical properties of printing components and multiple process factors(laser-and process-parameters),the concurrent optimization design method based on LAM should cover the process-performance *** study proposes a novel artificial intelligence-facilitated TO method for LAM to concurrently design microscale material property and macroscale structural topology of 3D components by adopting heuristic and gradient-based *** process–structure–property relationship of selective laser sintering is established by the back propagation neural network,and it is integrated into the TO algorithm for providing a systematic design scheme of structural topology and process *** with the classical optimization method,numerical examples show that this method is able to improve the mechanical performance of the macrostructure *** addition,the collaborative design method is able to be widely applied for complex functional part design and optimization,as well as case studies on artificial intelligence-facilitated product evaluation.

关键词： back propagation neural network Gradient algorithm Laser additive manufactur-ing Process–structure–property Topology optimization

Pollutants removal and simulation model of combined membrane process for wastewater treatment and reuse in submarine cabin for long voyage

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2009年第11期21卷 1503-1512页

作者： CHEN Zhaobo ZHOU Aijuan REN Nanqi TIAN Yu HU Dongxue State Key Laboratory of Urban Water Resource and Environment Harbin Institute of Technology Harbin 150090 China School of Materials Science & Chemical Engineering Harbin Engineering University Harbin 150001 China

A laboratory scale test was conducted in a combined membrane process （CMP） with a capacity of 2.91 m3/d for 240 d to treat the mixed wastewater of humidity condensate, hygiene wastewater and urine in submarine cabin during prolonged voyage. Removal performance of chemical oxygen demand （COD）, ammonia nitrogen （NH4^＋-N）, turbidity and anionic surfactants （LAS） was investigated under different conditions. It was observed that the effluent COD, NH4^＋-N, turbidity and LAS flocculated in ranges of 0.19-0.85 mg/L, 0.03-0.18 mg/L, 0.0-0.15 NTU and 0.0-0.05 mg/L, respectively in spite of considerable fluctuation in corresponding influent of 2120-5350 mg/L, 79.5-129.3 mg/L, 110-181.1NTU and 4.9-5.4 mg/L. The effluent quality of the CMP could meet the requirements of mechanical water and hygiene water according to the class I water quality standards in China （GB3838-2002）. The removal rates of COD, NH4^＋-N, turbidity and LAS removed in the MBR were more than 90%, which indicated that biodegradation is indispensable and plays a major role in the wastewater treatment and reuse. A model, built on the back propagation neural network （BPNN） theory, was developed for the simulation of CMP and produced high reliability. The average error of COD and NH4^＋-N was 5.14% and 6.20%, respectively, and the root mean squared error of turbidity and LAS was 2.76% and 1.41%, respectively. The results indicated that the model well fitted the laboratory data, and was able to simulate the removal of COD, NH4^＋-N, turbidity and LAS. It also suggested that the model proposed could reflect and manage the operation of CMP for the treatment of the mixed wastewaters in submarine.

关键词： combined membrane process wastewater treatment and reuse back propagation neural network

Design of neural network Based Wind Speed Prediction Model Using GWO

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2022年第2期40卷 593-606页

作者： R.Kingsy Grace R.Manimegalai Department of Computer Science and Engineering Sri Ramakrishna Engineering CollegeCoimbatore641022India Department of Computer Science and Engineering PSG Institute of Technology and Applied ResearchCoimbatore641062India

The prediction of wind speed is imperative nowadays due to the increased and effective generation of wind *** power is the clean,free and conservative renewable *** is necessary to predict the wind speed,to implement wind power *** paper proposes a new model,named WT-GWO-BPNN,by integrating Wavelet Transform(WT),back propagation neural network(BPNN)and GreyWolf Optimization(GWO).The wavelet transform is adopted to decompose the original time series data(wind speed)into approximation and detailed ***-BPNN is applied to predict the wind *** is used to optimize the parameters of back propagation neural network and to improve the convergence *** work uses wind power data of six months with 25,086 data points to test and verify the performance of the proposed *** proposed work,WT-GWO-BPNN,predicts the wind speed using a three-step procedure and provides better *** Absolute Error(MAE),Mean Squared Error(MSE),Mean absolute percentage error(MAPE)and Root mean squared error(RMSE)are calculated to validate the performance of the proposed *** results demonstrate that the proposed model has better performance when compared to other methods in the literature.

关键词： Wind speed wavelet transform back propagation neural network grey wolf optimization time series