检索结果-南通市图书馆

Improved genetic algorithm based on reinforcement learning for electric vehicle front-end structure optimization design

在线全文

学校读者我要写书评

暂无评论

Advances in Manufacturing 2024年第3期12卷 556-575页

作者： feng-Yao Lyu Zhen-Fei Zhan gui-Lin zhou Ju Wang Jie Li Xin He Chongqing Jiaotong University Chongqing400074People’s Republic of China Changan Automobile Co.Ltd. Chongqing404100People’s Republic of China

The structural optimization of electric vehicles involves numerous design variables and constraints,making it a complex engineering optimization task over the past *** population-based evolutionary algorithms encounter issues such as converging to local optima and lacking population diversity when tackling such optimization ***,the solutions obtained for the optimization may be flawed or *** address these problems,an improved genetic algorithm(GA)based on reinforcement learning is proposed in this *** proposed method introduces a population delimitation method based on individual fitness *** population is divided into two parts:the excellent population and the ordinary population,and different selection and cross-mutation methods are applied to each part *** efficient crossover and mutation methods are then applied to the ordinary population to enhance the generation of excellent ***,the proposed approach replaces the traditional fixed crossover and mutation rates with a dynamic selection method based on reinforcement learning to enhance optimization efficiency.A markov decision process model is constructed based on GA environment in this *** population state determination method and reward method are designed for reinforcement learning in the GA environment,dynamically selecting the most appropriate genetic parameters based on the current state of the ***,the uncertainty in the manufacturing process is introduced into the optimization problem and the case study results demonstrate that the proposed reinforcement learning-based GA significantly outperforms other evolutionary algorithms when applied to solving the structural optimization of electric vehicles.

关键词： Structure optimization Genetic algorithm(GA) Q-learning

Plutonium utilization in a small modular molten-salt reactor based on a batch fuel reprocessing scheme

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2024年第4期35卷 15-28页

作者： Xue-Chao Zhao Rui Yan gui-feng Zhu Ya-Fen Liu Jian Guo Xiang-zhou Cai Yang Zou Shanghai Institute of Applied Physics Chinese Academy of SciencesShanghai 201800China CAS Innovative Academies in TMSR Energy System Chinese Academy of SciencesShanghai 201800China University of Chinese Academy of Sciences Beijing 100049China

A molten salt reactor(MSR)has outstanding features considering the application of thorium fuel,inherent safety,sustainability,and resistance to ***,fissile material^(233)U is significantly rare at the current stage,thus it is difficult for MSR to achieve a pure thorium-uranium fuel ***,using plutonium or enriched uranium as the initial fuel for MSR is more *** this study,we aim to verify the feasibility of a small modular MSR that utilizes plutonium as the starting fuel(SM-MSR-Pu),and highlight its advantages and ***,the structural design and fuel management scheme of the SM-MSR-Pu were ***,the neutronic characteristics,such as the graphite-irradiation lifetime,burn-up performance,and coefficient of temperature reactivity were calculated to analyze the physical characteristics of the *** results indicate that plutonium is a feasible and advantageous starting fuel for a SM-MSR;however,there are certain shortcomings that need to be *** a 250 MWth SM-MSR-Pu,approximately 288.64 kg^(233)U of plutonium with a purity of greater than 90% is produced while 978.00 kg is burned every ten *** temperature reactivity coefficient decreases from -4.0 to -6.5 pcm K^(-1) over the 50-year operating time,which ensures a long-term safe ***,the amount of plutonium and accumulation of minor actinides(MAs)would increase as the burn-up time increases,and the annual production and purity of^(233)U will *** achieve an optimal burn-up performance,setting the entire operation time to 30 years is ***,more than 3600 kg of plutonium eventually accumulate in the *** research is required to effectively utilize this accumulated plutonium.

关键词： Molten salt fuel Plutonium utilization ^(233)U TRUs mole fraction Temperature feedback coefficient

Evolutionary mechanisms and practical significance of reproductive success and clonal diversity in unisexual vertebrate polyploids

在线全文

学校读者我要写书评

暂无评论

Science China(Life Sciences) 2024年第3期67卷 449-459页

作者： Meng Lu Li zhou Jian-Fang gui State Key Laboratory of Freshwater Ecology and Biotechnology Hubei Hongshan Laboratorythe Innovation Academy of Seed DesignInstitute of HydrobiologyChinese Academy of SciencesWuhan 430072China University of Chinese Academy of Sciences Beijing 100049China

Unisexual reproduction is generally relevant to polyploidy, and unisexual vertebrates are often considered an evolutionary “dead end” due to the accumulation of deleterious mutations and absence of genetic diversity. However, some unisexual polyploids have developed strategies to avoid genomic decay, and thus provide ideal models to unveil unexplored evolutionary mechanisms, from the reproductive success to clonal diversity creation. This article reviews the evolutionary mechanisms for overcoming meiotic barrier and generating genetic diversity in unisexual vertebrates, and summarizes recent research advancements in the polyploid Carassius complex. Gynogenetic gibel carp(Carassius gibelio) is a unique amphitriploid that has undergone a recurrent autotriploidy and has overcome the bottleneck of triploid sterility via gynogenesis. Recently, an efficient strategy in which ploidy changes, including from amphitriploid to amphitetraploid, then from amphitetraploid to novel amphitriploid, drive unisexual-sexual-unisexual reproduction transition and clonal diversity has been *** on this new discovery, multigenomic reconstruction biotechnology has been used to breed a novel strain with superior growth and stronger disease resistance. Moreover, a unique reproduction mode that combines both abilities of ameiotic oogenesis and sperm-egg fusion,termed as ameio-fusiongensis, has been discovered, and it provides an efficient approach to synthesize sterile allopolyploids. In order to avoid ecological risks upon escape and protect the sustainable property rights of the aquaculture seed industry, a controllable fertility biotechnology approach for precise breeding is being developed by integrating sterile allopolyploid synthesis and gene-editing *** review provides novel insights into the origin and evolution of unisexual vertebrates and into the attempts being made to exploit new breeding biotechnologies in aquaculture.

关键词： unisexual vertebrates polyploidy reproduction transition clonal diversity precise breeding genomic reconstruction controllable fertility

Binary Hybrid Artificial Hummingbird with Flower Pollination Algorithm for Feature Selection in Parkinson’s Disease Diagnosis

在线全文

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2024年第2期21卷 1003-1021页

作者： Liuyan feng Yongquan zhou Qifang Luo College of Artificial Intelligence Guangxi University for NationalitiesNanning530006China Xiangsihu College of Guangxi University for Nationalities Nanning532100GuangxiChina Guangxi Key Laboratories of Hybrid Computation and IC Design Analysis Nanning530006China

Parkinson’s disease is a neurodegenerative disorder that inflicts irreversible damage on *** experimental data regarding Parkinson’s patients are redundant and irrelevant,posing significant challenges for disease ***,there is a need to devise an effective method for the selective extraction of disease-specific information,ensuring both accuracy and the utilization of fewer *** this paper,a Binary Hybrid Artificial Hummingbird and Flower Pollination Algorithm(FPA),called BFAHA,is proposed to solve the problem of Parkinson’s disease diagnosis based on speech ***,combining FPA with Artificial Hummingbird Algorithm(AHA)can take advantage of the strong global exploration ability possessed by FPA to improve the disadvantages of AHA,such as premature convergence and easy falling into local ***,the Hemming distance is used to determine the difference between the other individuals in the population and the optimal individual after each iteration,if the difference is too significant,the cross-mutation strategy in the genetic algorithm(GA)is used to induce the population individuals to keep approaching the optimal individual in the random search process to speed up finding the optimal ***,an S-shaped function converts the improved algorithm into a binary version to suit the characteristics of the feature selection(FS)*** this paper,10 high-dimensional datasets from UCI and the ASU are used to test the performance of BFAHA and apply it to Parkinson’s disease *** with other state-of-the-art algorithms,BFAHA shows excellent competitiveness in both the test datasets and the classification problem,indicating that the algorithm proposed in this study has apparent advantages in the field of feature selection.

关键词： Artificial Hummingbird Algorithm Flower pollination algorithm Feature selection Parkinson’s disease Meta-heuristic

Effect of FeSi additive in dual-chamber sample cup on thermal analysis characteristic values and vermiculating rate of compacted graphite iron

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Foundry 2024年第1期21卷 91-100页

作者： De-quan Shi Ze-yu Liu gui-li Gao Yi-cheng feng School of Materials and Chemistry University of Shanghai for Science and TechnologyShanghai 200093China School of Materials Science and Chemical Engineering Harbin University of Science&TechnologyHarbin 150040China School of Mechanical and Energy Engineering Shanghai Technical Institute of Electronics and InformationShanghai 201411China

Thermal analysis plays a key role in the online inspection of molten iron *** solidification process of molten iron can be reflected by thermal analysis curves,and silicon is one of important elements affecting the solidification of molten *** this study,FeSi75 was added in one chamber of the dual-chamber sample cup,and the influences of FeSi75 additive on the characteristic values of thermal analysis curves and vermiculating rate were *** results show that with the increase of FeSi75,the start temperature of austenite formation TALfirstly decreases and then increases,but the start temperature of eutectic growth TSEF,the lowest eutectic temperature TEU,temperature at maximum eutectic reaction rate TEM,and highest eutectic temperature TERkeep always an *** temperature at final solidification point TEShas little *** FeSi75 additive has different influences on the vermiculating rate of molten iron with different vermiculation,and the vermiculating rate increases for lower vermiculation molten iron while decreases for higher *** to the thermal analysis curves obtained by a dual-chamber sample cup with 0.30wt.%FeSi75 additive in one chamber,the vermiculating rate of molten iron can be evaluated by comparing the characteristic values of these *** time differenceΔtERcorresponding to the highest eutectic temperature TERhas a closer relationship with the vermiculating rate,and a parabolic regression curve between the time differenceΔtERand vermiculating rateηhas been obtained within the range of 65%to 95%,which is suitable for the qualified melt.

关键词： FeSi75 additive characteristic value vermiculating rate thermal analysis compacted graphite iron

Spatial Distribution Feature Extraction Network for Open Set Recognition of Electromagnetic Signal

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第4期139卷 279-296页

作者： Hui Zhang Huaji zhou Li Wang feng zhou The Ministry Key Laboratory of Electronic Information Countermeasure and Simulation Xidian UniversityXi’an710071China Science and Technology on Communication Information Security Control Laboratory Jiaxing314033China

This paper proposes a novel open set recognition method,the Spatial Distribution Feature Extraction Network(SDFEN),to address the problem of electromagnetic signal recognition in an open *** spatial distribution feature extraction layer in SDFEN replaces convolutional output neural networks with the spatial distribution features that focus more on inter-sample information by incorporating class center *** designed hybrid loss function considers both intra-class distance and inter-class distance,thereby enhancing the similarity among samples of the same class and increasing the dissimilarity between samples of different classes during ***,this method allows unknown classes to occupy a larger space in the feature *** reduces the possibility of overlap with known class samples and makes the boundaries between known and unknown samples more ***,the feature comparator threshold can be used to reject unknown *** signal open set recognition,seven methods,including the proposed method,are applied to two kinds of electromagnetic signal data:modulation signal and real-world *** experimental results demonstrate that the proposed method outperforms the other six methods overall in a simulated open ***,compared to the state-of-the-art Openmax method,the novel method achieves up to 8.87%and 5.25%higher micro-F-measures,respectively.

关键词： Electromagnetic signal recognition deep learning feature extraction open set recognition

A hybrid physics-informed data-driven neural network for CO_(2) storage in depleted shale reservoirs

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1期21卷 286-301页

作者： Yan-Wei Wang Zhen-Xue Dai gui-Sheng Wang Li Chen Yu-zhou Xia Yu-Hao zhou College of Construction Engineering Jilin UniversityChangchun130026JilinChina Institute of Intelligent Simulation and Early Warning for Subsurface Environment Jilin UniversityChangchun130026JilinChina School of Energy Resources China University of GeosciencesBeijing100083China Department of Safety Environmental Protection and Quality ManagementShengli OilfieldSinopecDongying257000ShandongChina Key Laboratory of Thermo-Fluid Science and Engineering of MOE School of Energy and Power EngineeringXi'an Jiaotong UniversityXi'an710049ShaanxiChina College of Computer Science and Technology China University of Petroleum(East China)Qingdao266580ShandongChina Department of Physics University of FribourgFribourg1700Switzerland

To reduce CO_(2) emissions in response to global climate change,shale reservoirs could be ideal candidates for long-term carbon geo-sequestration involving multi-scale transport ***,most current CO_(2) sequestration models do not adequately consider multiple transport ***,the evaluation of CO_(2) storage processes usually involves laborious and time-consuming numerical simulations unsuitable for practical prediction and *** this paper,an integrated model involving gas diffusion,adsorption,dissolution,slip flow,and Darcy flow is proposed to accurately characterize CO_(2) storage in depleted shale reservoirs,supporting the establishment of a training *** this basis,a hybrid physics-informed data-driven neural network(HPDNN)is developed as a deep learning surrogate for prediction and *** incorporating multiple sources of scientific knowledge,the HPDNN can be configured with limited simulation resources,significantly accelerating the forward and inversion ***,the HPDNN can more intelligently predict injection performance,precisely perform reservoir parameter inversion,and reasonably evaluate the CO_(2) storage capacity under complicated *** validation and test results demonstrate that the HPDNN can ensure high accuracy and strong robustness across an extensive applicability range when dealing with field data with multiple noise *** study has tremendous potential to replace traditional modeling tools for predicting and making decisions about CO_(2) storage projects in depleted shale reservoirs.

关键词： Deep learning Physics-informed data-driven neural network Depleted shale reservoirs CO_(2)storage Transport mechanisms

Audio Mixing Inversion via Embodied Self-supervised Learning

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第1期21卷 55-62页

作者： Haotian zhou feng Yu Xihong Wu Department of AI Music and Music Information Technology Central Conservatory of MusicBeijing 100031China Laboratory of Music Artificial Intelligence Laboratory of Philosophy and Social SciencesMinistry of EducationBeijing 100031China School of Intelligence Science and Technology Peking UniversityBeijing 100871China

Audio mixing is a crucial part of music *** analyzing or recreating audio mixing,it is of great importance to conduct research on estimating mixing parameters used to create mixdowns from music recordings,i.e.,audio mixing ***,approaches of audio mixing inversion are rarely explored.A method of estimating mixing parameters from raw tracks and a stereo mixdown via embodied self-supervised learning is *** this work,several commonly used audio effects including gain,pan,equalization,reverb,and compression,are taken into *** method is able to learn an inference neural network that takes a stereo mixdown and the raw audio sources as input and estimate mixing parameters used to create the mixdown by iteratively sampling and *** the sampling step,the inference network predicts a set of mixing parameters,which is sampled and fed to an audio-processing framework to generate audio data for the training *** the training step,the same network used in the sampling step is optimized with the sampled data generated from the sampling *** method is able to explicitly model the mixing process in an interpretable way instead of using a black-box neural network model.A set of objective measures are used for *** experimental results show that this method has better performance than current state-of-the-art methods.

关键词： Audio mixing inversion intelligent audio mixing self-supervised learning audio signal processing deep learning

Voltage-modulated polymer nanopore field-effect transistor for multi-sized nanoparticle 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

Nanotechnology and Precision Engineering 2024年第3期7卷 79-89页

作者： feng zhou Lin Li Qiannan Xue State Key Laboratory of Precision Measurement Technology and Instruments School of Precision Instruments and Optoelectronics EngineeringTianjin UniversityTianjin 300072China

Solid-state nanopores offer a range of distinct advantages over biological nanopores,such as structural diversity and greater stability and durability;this makes them highly promising for high-resolution nanoparticle *** nanopores can exhibit gating characteristics with stress-responsive switches and can demonstrate specificity toward particular *** inspiration from biological nanopores,this paper introduces a novel polymer nanopore with field-effect characteristics,leveraging a conductive polymer in its construction to showcase intriguing gating ***,in this device,the polymer layer serves as the gate,enabling precise control over the source–drain current response inside and outside the pore by simply adjusting the gate *** unique feature allows fine-tuning of the nanopore’s sensitivity to nanoparticles of varying sizes and facilitates its operation in multiple *** results reveal that the developed polymer nanopore field-effect transistor demonstrates remarkable selectivity in detecting nanoparticles of various sizes under different applied *** proposed single device demonstrates the exceptional ability to detect multiple types of nanoparticle,showcasing its immense potential for a wide range of applications in biological-particle analysis and medical diagnostics.

关键词： Nanopipette Polymer nanopore Voltage modulation Nanoparticle detection