检索结果-南通市图书馆

Investigation of Optimal Megnetic Properties in NdFeB Magnets by Artificial Neural Network

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Investigation of Optimal Megnetic Properties in NdFeB Magnet...

2004国际稀土研究与应用研讨会（包头）

作者：连利仙刘颖胡旺侯廷红高升吉涂铭旌 College of Materials Science ＆ Engineering College of Materials Science ＆ Engineering School of Computer Science ＆ Engineering Sichuan University Chengdu 610065 China College of Materials Science ＆ Engineering College of Materials Science ＆ Engineering College of Materials Science ＆ Engineering

＜正＞ In order to study the effect of alloy component on magnetic properties of NdFeB magnets, the experiment schemes are carried out by the uniform design theory, and the relationship between the component and the magnetic properties is established by artificial neural network（ ANN） predicting model. The element contents of alloys are optimized by the ANN model. Meanwhile, the influences of mono-factor or multi-factor interaction on alloy magnetic properties are respectively discussed according to the curves ploted by ANN model. Simulation result shows that the predicted and measured results are in good agreement. The relative error is every low, the error is not more than 1.68% for remanence Br, 1.56% for maximal energy product （BH）m, and 7. 73% for coercivity Hcj. Hcj can be obviously improved and Br can be reduced by increasing Nd or Zr content. Co and B have advantageous effects on increasing Br and disadvantageous effects on increasing Hcj. Influence of alloying elements on Hcj and Br are inverse, and the interaction among the alloying elements play an important role in the magnetic properties of NdFeB magnets. The ANN prediction model presents a new approach to investigate the nonlinear relationship between the component and the magnetic properties of NdFeB alloys.

关键词： metal materials artificial neural network uniform design NdFeB magnetic properties rare earths

A New Differential Evolution Algorithm for Complex Constrained Optimization Problems

在线全文

cnki会议

学校读者我要写书评

暂无评论

A New Differential Evolution Algorithm for Complex Constrain...

第三十届中国控制会议

作者： XU Junqin~1,ZHANG Jihui~2 1.College of Mathematics,Qingdao University,Qingdao 266071,P.R.China 2.Institute of Complexity Science,Qingdao University,Qingdao 266071,P.R.China

＜正＞This paper presents a new differential evolution（DE） to address complex multi-modal function optimization problems. DE is a novel evolutionary approach capable of handling non-differentiable,nonlinear and multi-modal objective functions. Previous studies have shown that DE is an efficient,effective and robust evolutionary algorithm,but sometimes it is inefficient to solve complicated multi-modal *** order to improve its search efficiency,a local search procedure is designed and an improved DE（IDE） based on uniform design is *** performance is tested using some well known benchmark problems. Numerical results show the usefulness of our method.

关键词： Differential evolution uniform design Local search Multi-modal global optimization

Characterization of a duplex PCR assay for the detection of enterotoxigenic strains of Staphylococcus aureus

在线全文

cnki会议

学校读者我要写书评

暂无评论

Characterization of a duplex PCR assay for the detection of ...

中国食品科学技术学会第五届年会暨第四届东西方食品业高层论坛

作者： Junni Tang~(1,2) Xianming Shi Chunlei Shi~1 Huanchun Chen~2 (1Department of Food Science and Technology and Bor Luh Food Safety Center,Shanghai Jiao Tong University,Shanghai 201101 China)(2National Key Laboratory of Agricultural Microbiology,Huazhong Agricultural University,Wuhan 430070 China)

Sequence analysis demonstrated that all reported primers based on the thermonuclease gene (nuc)used in the detection of the food-borne pathogen,Staphylococcus aureus,were derived from the nuclease gene,instead of the thermonuclease *** this study,two pairs of primers targeting the sequences of the nuc gene and 16S rRNA gene were designed in a duplex PCR assay for the detection of ***,particularly those of the enterotoxigenic *** optimization of the amplification conditions by uniform design,two specific products were amplified in the PCR detection system:a 223-bp nuc fragment and a 565-bp 16S rDNA *** tests demonstrated that this duplex-PCR method has high specificity for only *** detection limit of the assay was 9.35 pg/μl using *** genomic *** sensitivity for direct detection of milk samples sparked with S. aureus was 104 to 105 CFU/ml,and the sensitivity was 1 CFU/ml as an initial concentration when an enrichment process was used.A PCR-based detection assay for enterotoxin gene was performed in parallel with the detection of the nuc-encoded TNase activity in several *** strains,and a good correlation between TNase production and enterotoxigenicity was demonstrated in all the strains tested.

关键词： duplex PCR uniform design Staphylococcus aureus rapid detection

Optimization of Longitudinal Beam Based on Two Types of Frontal Impact

在线全文

cnki会议

学校读者我要写书评

暂无评论

Optimization of Longitudinal Beam Based on Two Types of Fron...

The 9th International Forum of Automotive Traffic Safety

作者： Chen Xu 1 , Jikuang Yang 12 1 State Key Laboratory of Advanced and Manufacture for Vehicle Body, Hunan University, Changsha Hunan 410082 2 Department of Applied Mechanics, Chalmers University of Technology, Sweden.

The current paper aims to study a method to optimization of longitudinal beam based on 100%RB impact and 40% ODB impact. 100% RB impact and 40%ODB FE models were developed and validated with LS-DYNA, according to the requirement of crashworthiness of longitudinal beam, acceleration of left B-pillar, energy absorbed per unit mass were chosen as optimization objects ,the thicknesses of four parts of the longitudinal beam were considered as the design variables. uniform design was applied to build variable samples. Optimal results were obtained by surrogate model built by Kriging and optimization method NSGA-Ⅱ （Non-Dominated Sorting in Genetic Algorithms-Ⅱ）. The results show that 100%RB and 40%ODB impact should be considered together when longitudinal beam was designed;it has some limits if only one is concerned. The optimized longitudinal beam matches well and effectively improves vehicle crashworthiness.

关键词： longitudinal beam frontal impact uniform design NSGA-Ⅱ.

Optimization of Preservation on Fresh-cut Yam under Simulated Cold-chain Process

在线全文

cnki会议

学校读者我要写书评

暂无评论

Agricultural Biotechnology 2020年第5期9卷 103-106页

作者： Dongdi XIE Rongling HUANG Department of Food and Biological Engineer Hezhou UniversityHezhou 542899China

[Objectives]This study was conducted to investigate the effect of compound fresh-keeping liquid on the browning and quality of fresh-cut yam during the cold chain process.[Methods]Under the simulated cold chain condition of 4℃,a uniform design(U6*(64))experiment was carried out to optimize the compound preservative formula,and a better compound preservative formula was obtained using the regression equation.[Results]The compound preservative formula was:AA 0.25%,CA 0.5%,Nisin 0.09%,GSH 0.15%.The compound fresh-keeping liquid effectively delayed the browning of fresh-cut yam and the accumulation of MDA,maintained the content of TSS,inhibited the activity of PAL and delayed the appearance of the maximum activity of POD and POD.[Conclusions]This study provides technical support for the actual extension of the shelf life of fresh-cut yam.

关键词： Fresh-cut yam Cold chain process uniform design Preservation

Hybrid Multi-Object Optimization Method for Tapping Center Machines

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第4期 23-38页

作者： Ping-Yueh Chang Fu-I Chou Po-Yuan Yang Shao-Hsien Chen Department of Electrical Engineering National Kaohsiung University of Science and TechnologyKaohsiung807China Taiwan Department of Intelligent Robotics National Pingtung UniversityPingtung900China Taiwan Graduate Institute of Precision Manufacturing National Chin-Yi University of TechnologyTaichung411China Taiwan

This paper proposes a hybrid multi-object optimization method integrating a uniform design,an adaptive network-based fuzzy inference system(ANFIS),and a multi-objective particle swarm optimizer(MOPSO)to optimize the rigid tapping parameters and minimize the synchronization errors and cycle times of computer numerical control(CNC)***,rigid tapping parameters and uniform(including 41-level and 19-level)layouts were adopted to collect representative data for ***,ANFIS was used to build the model for the collected 41-level and 19-level uniform layout experiment *** tapping center machines,the synchronization errors and cycle times are important consid-erations,so these two objects were used to build the ANFIS ***,a MOPSO algorithm was used to search for the optimal parameter combinations for the two ANFIS models *** experimental results showed that the proposed method obtains suitable parameter values and optimal parameter combinations compared with the nonsystematic ***,the optimal parameter combination was used to optimize existing CNC tools during the commissioning *** the proportional and integral gains of the spindle could improve resistance to deformation during rigid *** posi-tion gain and prefeedback coefﬁcient can reduce the synchronization errors signiﬁcantly,and the acceleration and deceleration times of the spindle affect both the machining time and synchronization *** proposed method can quickly and accurately minimize synchronization errors from 107 to 19.5 pulses as well as the processing time from 3,600 to 3,248 ms;it can also shorten the machining time signiﬁcantly and reduce simultaneous errors to improve tapping yield,there-by helping factories achieve carbon reduction.

关键词： Tapping center machine uniform design adaptive network-based fuzzy inference system(ANFIS) multi-objective particle swarm optimizer

Feature Extraction of Time Series Data Based on CNN-CBAM

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

国际计算机前沿大会会议论文集 2023年第1期 233-245页

作者： Jiaji Qin Dapeng Lang Chao Gao Harbin Engineering University Harbin 150001China

Methods for extracting features from time series data using deep learning have been widely studied,but they still suffer from problems of severe loss of feature information across different network layers and parameter ***,a new time-series data feature extraction model(CNN-CBAM)that integrates convolutional neural networks(CNN)and convolutional attention mechanisms(CBAM)is ***,the parameters of the CNN and BiGRU prediction models are optimized through uniform design ***,the CNN is used to extract features from the time series data,outputting multiple feature *** feature maps are then subjected to feature re-extraction by the CBAM attention mechanism at both the spatial and channel ***,the feature maps are input into the BiGRU model for *** results show that after CNN-CBAM processing,the stability and accuracy of the BiGRU pre-diction model improved by 77.6%and 76.3%,respectively,outperforming other feature extraction ***,the training time of the model has only increased by 7.1%,demonstrating excellent time efﬁciency.

关键词： uniform design CNN CBAM Time-series Data Feature Extraction