检索结果-南通市图书馆

Soft coarse-grained particle model for particle-fluid systems

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1期84卷 178-193页

作者： Yanhao Ye ji xu Wei Ge State Key Laboratory of Multiphase Complex Systems Institute of Process EngineeringChinese Academy of SciencesBeijing100190China School of Chemical Engineering University of Chinese Academy of SciencesBeijing100049China Innovation Academy for Green Manufacture Chinese Academy of SciencesBeijing100190China

By modeling a group of neighboring real particles as a single coarse-grained particle(CGP),discrete particle method(DPM)is now capable of simulating industrial-scale particle-fluid ***,a systematic approach to determine the CGP properties and develop their interaction models is still lacking,which casts uncertainty on the predictivity of the *** this study,collisions between predefined particle groups are analyzed to construct kernel functions for modeling the CGPs and then the model parameters are determined by equating the statistical properties of the CGPs and the real particles in the physical process *** approach is implemented for homogeneous cooling of granular gas,then demonstrated effective in simulating experimental fluidized beds.

关键词： Coarse-grain(CG) Discrete particle method(DPM) Fluidized bed Multi-scale simulation

Identity Vector Extraction Using Shared Mixture of PLDA for Short-Time Speaker Recognition

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 Electronics 2019年第2期28卷 357-363页

作者： WANG Wenchao xu ji YAN Yonghong Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics Chinese Academy of Sciences University of Chinese Academy of Sciences Xinjiang Laboratory of Minority Speech and Language Information Processing Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Sciences

The state-of-the-art speaker recognition system degrades performance rapidly dealing with shorttime utterances. It is known to all that identity vectors(i-vectors) extracted from short utterances have large uncertainties and standard Probabilistic linear discriminant analysis(PLDA) method can not exploit this uncertainty to reduce the effect of duration variation. In this work, we use Shared mixture of PLDA(SM-PLDA)to remodel the i-vectors utilizing their ***-PLDA is an improved generative model with a shared intrinsic factor, and this factor can be regarded as an identity vector containing speaker indentification information. This identity vector can be modeled by PLDA. Experimental results are evaluated by both equal error rate and minimum detection cost function. The results conducted on the National institute of standards and technology(NIST) Speaker recognition evaluation(SRE) 2010 extended tasks show that the proposed method has achieved significant improvements compared with ivector/PLDA and some other advanced methods.

关键词： Short-time utterance Speaker recognition Shared mixture of PLDA Identity vector

Agglutinative Language Speech Recognition Using Automatic Allophone Deriving

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2016年第2期25卷 328-333页

作者： xu ji PAN jielin YAN Yonghong The Key Laboratory of Speech Acoustics and Content Understanding Chinese Academy of Sciences

Agglutinative language involves agglutination extensively, which results in the significant pronunciation variations in different contexts. Therefore, it is a problem to use phoneme sets translated from their written forms as basic units for acoustic modeling, due to the incapability to capture the pronunciation variations in Large-vocabulary continuous speech recognition(LVCSR).This paper presented a novel approach called Automatic allophone deriving(AAD) to create allophone candidates without any linguistic prior knowledge. Furthermore, an enhanced approach AAD-LT is proposed in which longtime features are used in AAD approach. Experiments are conducted on three languages which contains two agglutinative ones and an analytic one. The experiments suggest that AAD Long-time(AAD-LT) is very effective for the agglutinative languages in which more than 10% relative CER reduction is obtained.

关键词： Agglutinative language Large-vocabulary continuous speech recognition(LVCSR) Allophone Unsupervised

Parametric Resonance Analyses for Spar Platform in Irregular Waves

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

China Ocean Engineering 2018年第2期32卷 236-244页

作者： YANG He-zhen xu Pei-ji School of Engineering University of GlasgowGlasgow G128QQUnited Kingdom School of Naval Architecture Ocean and Civil EngineeringShanghai Jiao Tong UniversityShanghai 200240China

The parametric instability of a spar platform in irregular waves is analyzed. Parametric resonance is a phenomenon that may occur when a mechanical system parameter varies over time. When it occurs, a spar platform will have excessive pitch motion and may capsize. Therefore, avoiding parametric resonance is an important design requirement. The traditional methodology includes only a prediction of the Mathieu stability with harmonic excitation in regular waves. However, real sea conditions are irregular, and it has been observed that parametric resonance also occurs in non-harmonic excitations. Thus, it is imperative to predict the parametric resonance of a spar platform in irregular waves. A Hill equation is derived in this work, which can be used to analyze the parametric resonance under multi-frequency excitations. The derived Hill equation for predicting the instability of a spar can include non-harmonic excitation and random phases. The stability charts for multi-frequency excitation in irregular waves are given and compared with that for single frequency excitation in regular waves. Simulations of the pitch dynamic responses are carried out to check the stability. Three-dimensional stability charts with various damping coefficients for irregular waves are also investigated. The results show that the stability property in irregular waves has notable differences compared with that in case of regular waves. In addition, using the Hill equation to obtain the stability chart is an effective method to predict the parametric instability of spar platforms. Moreover, some suggestions for designing spar platforms to avoid parametric resonance are presented, such as increasing the damping coefficient, using an appropriate RAO and increasing the metacentric height.

关键词： spar platform instability parametric resonance Mathieu equation irregular waves dynamic responses

维普期刊数据库

Simulation and prediction in laser bending of silicon sheet

在线全文

学校读者我要写书评

暂无评论

Transactions of Nonferrous Metals Society of China 2011年第A01期21卷 188-193页

作者： WANG xu-yue xu Wei-xing xu Wen-ji HU Ya-feng LIANG Yan-de WANG Lian-ji Key Laboratory for Precision and Non-traditional Machining Technology of the Ministry of Education Dalian University of Technology Dalian 116024 China

The laser bending of single-crystal silicon sheet （0.2 mm in thickness） was investigated with JK701 Nd：YAG laser. The models were developed to describe the beam characteristics of pulsed laser. In order to simulate the process of laser bending, the FEM software ANSYS was used to predict the heat temperature and stress-strain fields. The periodic transformation of temperature field and stress-strain distribution was analyzed during pulsed laser scanning silicon sheet. The results indicate that the mechanism of pulsed laser bending silicon is a hybrid mechanism in silicon bending, rather than a simple mechanism of TGM or BM. This work also gets silicon sheet bent after scanning 6 times with pulsed laser, and its bending angle is up to 6.5°. The simulation and prediction results reach well agreement with the verifying experiments.

关键词： laser bending silicon sheet pulsed laser simulation

维普期刊数据库

The primary influence of shear band evolution on the slope bearing capacity

在线全文

学校读者我要写书评

暂无评论

Journal of Rock Mechanics and Geotechnical Engineering 2023年第4期15卷 1023-1037页

作者： Lanting Wei Qiang xu Shanyong Wang xu ji Chengdu University of Technology ChengduChina Priority Research Centre for Geotechnical Science and Engineering School of EngineeringUniversity of NewcastleNewcastleAustralia

Slope bearing capacity is one of the most important characteristics in slope engineering and is strongly influenced by weak planes,loading conditions,and slope *** presenting the evolution of slip surfaces,this paper explored how the slope bearing capacity is affected by widely observed influencing *** initiation and propagation of slip surfaces are presented in laboratory model tests of slope using the transparent soil *** band evolution under various weak planes,loading conditions,and slope geometries were experimentally presented,and slope bearing capacities were analyzed with the process of shear band *** paper verified that slip surface morphologies have a strong relation with the slope bearing *** same slip surface morphology can have different evolutionary *** this case,it is the shear band evolution that determines the slope bearing capacity,not the morphology of the slip *** influencing factors such as pre-existing weak planes,loading conditions,and slope geometry strongly affect the slope bearing capacity as these factors govern the process of shear band evolution inside the slope.

关键词： Slope bearing capacity Shear band evolution Failure mechanism Transparent soil

Gas–solid reactor optimization based on EMMS-DPM simulation and machine 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

Particuology 2024年第6期89卷 131-143页

作者： Haolei Zhang Aiqi Zhu ji xu Wei Ge State Key Laboratory of Mesoscience and Engineering Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China State Key Laboratory of Multiphase Complex Systems Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China School of Chemical Engineering University of Chinese Academy of SciencesBeijing 100049China Innovation Academy for Green Manufacture Chinese Academy of SciencesBeijing 100190China

Design,scaling-up,and optimization of industrial reactors mainly depend on step-by-step experiments and engineering experience,which is usually time-consuming,high cost,and high *** numerical simulation can reproduce high resolution details of hydrodynamics,thermal transfer,and reaction process in reactors,it is still challenging for industrial reactors due to huge computational *** this study,by combining the numerical simulation and artificial intelligence(AI)technology of machine learning(ML),a method is proposed to efficiently predict and optimize the performance of industrial reactors.A gas–solid fluidization reactor for the methanol to olefins process is taken as an example.1500 cases under different conditions are simulated by the coarse-grain discrete particle method based on the Energy-Minimization Multi-Scale model,and thus,the reactor performance data set is *** develop an efficient reactor performance prediction model influenced by multiple factors,the ML method is established including the ensemble learning strategy and automatic hyperparameter optimization technique,which has better performance than the methods based on the artificial neural ***,the operating conditions for highest yield of ethylene and propylene or lowest pressure drop are searched with the particle swarm optimization algorithm due to its strength to solve non-linear optimization *** show that decreasing the methanol inflow rate and increasing the catalyst inventory can maximize the yield,while decreasing methanol the inflow rate and reducing the catalyst inventory can minimize the pressure *** two objectives are thus conflicting,and the practical operations need to be compromised under different circumstance.

关键词： Discrete particle method Artificial intelligence Machine learning Particle swarm optimization Industrial reactor optimization

3D coarse-grained DPM simulation of the MIP reaction-regeneration loop

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6期89卷 57-66页

作者： Yanhao Ye Shuai Zhang ji xu Wei Ge State Key Laboratory of Mesoscience and Engineering(formerly State Key Laboratory of Multiphase Complex Systems) Institute of Process EngineeringChinese Academy of SciencesBeijing100190China School of Chemical Engineering University of Chinese Academy of SciencesBeijing100049China

The reactor-regenerator loop is the core facility of the maximizing iso-paraffin(MIP)*** the discrete particle method(DPM)simulation can provide detailed information at the particle scale,it has been unable to simulate such a complex loop system due to limitations of coarse-grained(CG)models,computing software,and *** this study,a newly proposed soft-shell CG-DPM model with a CG ratio of up to 800 is used to simulate a 3.5 Mt/a industrial-scale MIP reactor-regenerator *** solid fraction distribution obtained is found to agree well with in-situ *** properties including the distribution of solid fraction,gas and solid velocity,standard derivation of solid fraction with time,temporal distribution of the flow field,and particle residence time distribution are measured in the simulation,which are meaningful to better design and operate such systems in the future.

关键词： Discrete particle method Coarse-grain Maximizing iso-paraffins Full-loop Reaction-regeneration system

Attention-based long short-term memory fully convolutional network for chemical process fault diagnosis

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 Chemical Engineering 2023年第4期56卷 1-14页

作者： Shanwei Xiong Li Zhou Yiyang Dai xu ji School of Chemical Engineering Sichuan UniversityChengdu 610065China

A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively used and still have considerable potential. In recent years, methods based on deep neural networks have made significant breakthroughs, and fault diagnosis methods for industrial processes based on deep learning have attracted considerable research attention. Therefore, we propose a fusion deeplearning algorithm based on a fully convolutional neural network(FCN) to extract features and build models to correctly diagnose all types of faults. We use long short-term memory(LSTM) units to expand our proposed FCN so that our proposed deep learning model can better extract the time-domain features of chemical process data. We also introduce the attention mechanism into the model, aimed at highlighting the importance of features, which is significant for the fault diagnosis of chemical processes with many features. When applied to the benchmark Tennessee Eastman process, our proposed model exhibits impressive performance, demonstrating the effectiveness of the attention-based LSTM FCN in chemical process fault diagnosis.

关键词： Safety Fault diagnosis Process systems Long short-term memory Attention mechanism Neural networks

维普期刊数据库