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

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

Pd/C催化下碱木质素的高压加氢反应

中国造纸学报 2008年第4期23卷 48-52页

作者：叶结旺方桂珍浙江林学院工程学院浙江临安311300 东北林业大学生物质材料科学与技术教育部重点实验室黑龙江哈尔滨150040

为了提高碱木质素的反应活性,探讨了高压条件下,以Pd/C为催化剂,氢气对碱木质素的加氢反应。研究结果表明:在催化剂的负载量3%、用量10%,温度100℃,时间4 h,氢气压力3 MPa的条件下,反应后碱木质素的总羟基、醇羟基和酚羟基含量分别为15.... 详细信息

为了提高碱木质素的反应活性,探讨了高压条件下,以Pd/C为催化剂,氢气对碱木质素的加氢反应。研究结果表明:在催化剂的负载量3%、用量10%,温度100℃,时间4 h,氢气压力3 MPa的条件下,反应后碱木质素的总羟基、醇羟基和酚羟基含量分别为15.69%、11.45%、4.24%,较反应前分别提高了158.1%、310.4%、28.9%。1H-NMR分析显示,代表羰基和羧基的质子吸收减少,而代表酚羟基和醇羟基的质子吸收增加。GPC分析表明,碱木质素结构单元间的缩合减少,质均分子质量和数均分子质量在反应后都有所下降,碱木质素的多分散性增大。元素分析显示,C和H的含量在反应后都有所增加,而O含量降低,表明碱木质素发生了还原反应。

关键词： Pd/C催化剂碱木质素加氢反应改性

Peak Shaving Strategy of Concentrating Solar Power Generation Based on Multi-Time-Scale and Considering Demand Response

在线全文

学校读者我要写书评

暂无评论

Energy Engineering 2024年第3期121卷 661-679页

作者： Lei fang Haiying Dong Xiaofei zhen Shuaibing Li School of New Energy and Power Engineering Lanzhou Jiaotong UniversityLanzhou730070China

According to the multi-time-scale characteristics of power generation and demand-side response(DR)resources,as well as the improvement of prediction accuracy along with the approaching operating point,a rolling peak shaving optimization model consisting of three different time scales has been *** proposed peak shaving optimization model considers not only the generation resources of two different response speeds but also the two different DR resources and determines each unit combination,generation power,and demand response strategy on different time scales so as to participate in the peaking of the power system by taking full advantage of the fast response characteristics of the concentrating solar power(CSP).At the same time,in order to improve the accuracy of the scheduling results,the combination of the day-ahead peak shaving phase with scenario-based stochastic programming can further reduce the influence of wind power prediction errors on scheduling *** testing results have shown that by optimizing the allocation of scheduling resources in each phase,it can effectively reduce the number of starts and stops of thermal power units and improve the economic efficiency of system *** spinning reserve capacity is reduced,and the effectiveness of the peak shaving strategy is verified.

关键词： Peak shaving strategy concentrating solar power multi-time-scale demand-side response rolling optimization

超临界CO_2萃取除脂后再经纤维素酶辅助提取落叶松树皮原花青素

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

林产化学与工业 2014年第2期34卷 97-102页

作者：姜贵全方桂珍师振鑫张卓睿庞久寅北华大学木质材料科学与工程省重点实验室吉林吉林132013 东北林业大学生物质材料科学与技术教育部重点实验室黑龙江哈尔滨150040

将超临界流体萃取与纤维素酶法相结合,对落叶松树皮中原花青素的提取工艺进行了研究。首先,采用超临界CO2从落叶松树皮中提取脂溶性成分,采用萃取压力35 MPa、温度50℃,萃取130 min后,树脂平均得率为2.16%,然后将萃余物通过纤维素酶辅... 详细信息

将超临界流体萃取与纤维素酶法相结合,对落叶松树皮中原花青素的提取工艺进行了研究。首先,采用超临界CO2从落叶松树皮中提取脂溶性成分,采用萃取压力35 MPa、温度50℃,萃取130 min后,树脂平均得率为2.16%,然后将萃余物通过纤维素酶辅助提取原花青素,通过单因素和正交试验确定了原花青素提取的最佳工艺条件为：3 g脱脂树皮粉以缓冲液为溶剂,原料粒度为150-178μm,纤维酶加入量为原料质量的0.6%,液料比14：1（mL：g）,酶解pH值5,酶解温度40℃,酶解时间2 h后,原花青素的得率可以达到7.36%。通过扫描电子显微镜观察和傅立叶变换红外光谱分析表明,提取树脂后的树皮纤维结构有不同程度的破坏,从而促使胞内物质溶出,提高了得率,所获得的落叶松树皮原花青素分子中主要存在原花青定型结构单元,没有使有效成分的结构发生改变。

关键词：超临界CO2 纤维素酶落叶松树皮原花青素提取工艺

Identifying malicious traffic under concept drift based on intraclass consistency enhanced variational autoencoder

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第8期67卷 238-252页

作者： Xiang LUO Chang LIU Gaopeng GOU Gang XIONG zhen LI Binxing fang Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences School of Computer Science and Technology Harbin Institute of Technology (Shenzhen)

Accurate identification of malicious traffic is crucial for implementing effective defense countermeasures and has led to extensive research efforts. However, the continuously evolving techniques employed by adversaries have introduced the issues of concept drift, which significantly affects the performance of existing methods. To tackle this challenge, some researchers have focused on improving the separability of malicious traffic representation and designing drift detectors to reduce the number of false ***, these methods often overlook the importance of enhancing the generalization and intraclass consistency in the representation. Additionally, the detectors are not sufficiently sensitive to the variations among different malicious traffic classes, which results in poor performance and limited robustness. In this paper, we propose intraclass consistency enhanced variational autoencoder with Class-Perception detector(ICE-CP) to identify malicious traffic under concept drift. It comprises two key modules during training:intraclass consistency enhanced(ICE) representation learning and Class-Perception(CP) detector construction. In the first module, we employ a variational autoencoder(VAE) in conjunction with Kullback-Leibler(KL)-divergence and cross-entropy loss to model the distribution of each input malicious traffic flow. This approach simultaneously enhances the generalization, interclass consistency, and intraclass differences in the learned representation. Consequently, we obtain a compact representation and a trained classifier for nondrifting malicious traffic. In the second module, we design the CP detector, which generates a centroid and threshold for each malicious traffic class separately based on the learned representation, depicting the boundaries between drifting and non-drifting malicious traffic. During testing, we utilize the trained classifier to predict malicious traffic classes for the testing samples. Then, we use the CP det

关键词： concept drift malicious traffic identification variational autoencoder intrusion detection cyberspace security

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

在线全文

同方期刊数据库

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

在线全文

学校读者我要写书评

暂无评论

护生实习期间的职业道德教育

中华护理杂志 2000年第9期35卷 554-555页

作者：方桂珍杭州市第10人民医院护理部 310018

为了提高护生实习期间职业道德教育效果 ,在带教过程中结合实际工作 ,注重护生三个意识的培养 ,即 :服务意识、责任意识、以病人为中心的意识 ;重视职业道德教育的内容、形式和环境 ,使之形象化、具体化、生动化。经实践应用。

关键词：护生实习带教职业道德教育

HNO_3-H_2O_2两步法制备Pd/C催化剂及其对木质素改性的催化作用

在线全文

学校读者我要写书评

暂无评论

林产化学与工业 2014年第6期34卷 13-20页

作者：刘亮张盛明方桂珍东北林业大学材料科学与工程学院黑龙江哈尔滨150040

以HNO3-H2O2处理活性炭载体,以甲醛为还原剂,采用浸渍法制备了Pd/C催化剂,对催化体系进行表征,考察其对碱木质素改性的催化作用,并对木质素抗氧化性能进行研究。研究结果表明,用硝酸预处理,H2O2进行活化后,活性炭羧基含量1.31 mmol/g,... 详细信息

以HNO3-H2O2处理活性炭载体,以甲醛为还原剂,采用浸渍法制备了Pd/C催化剂,对催化体系进行表征,考察其对碱木质素改性的催化作用,并对木质素抗氧化性能进行研究。研究结果表明,用硝酸预处理,H2O2进行活化后,活性炭羧基含量1.31 mmol/g,较原料提高了5倍;通过原子吸收光谱(AAS)、扫描电子显微镜(SEM)、X射线衍射(XRD)和X射线光电子能谱(XPS)对催化剂进行表征,AAS表明Pd负载量为2.9%,SEM照片显示Pd呈圆球状均匀分布在载体表面;XRD和XPS数据分析表明催化体系中Pd以面心立方结构形式存在,主要为还原态Pd说明还原态Pd是催化的主要物种。反应后碱木质素总羟基、酚羟基和醇羟基分别提高了158.74%,4.21%和255.96%;凝胶渗透色谱(GPC)分析结果显示,反应后碱木质素重均相对分子质量(Mw)增大,数均相对分子质量(Mn)降低,分散度降低;抗氧化能力研究结果显示,反应后木质素的抗氧化性能有所提高,随着浓度增大,抗氧化能力提高,但均低于相同浓度条件下2,6-二叔丁基-4-甲基苯酚(BHT)的抗氧化能力。

关键词：碱木质素 HNO3-H2O2 处理活性炭 Pd/C催化剂催化活化

在线全文

学校读者我要写书评

暂无评论

碱木质素壳聚糖反应膜的制备与性能

功能材料 2013年第9期44卷 1353-1358页

作者：苏玲李珊珊方桂珍东北林业大学材料科学工程学院黑龙江哈尔滨150040 大连天宇制药有限公司辽宁大连110011

以壳聚糖和碱木质素为原料,以戊二醛作交联剂,制备碱木质素/壳聚糖反应膜,并测定薄膜的相关物理性能。研究结果表明,碱木质素/壳聚糖反应膜制备的最佳条件为羟甲基化碱木质素与壳聚糖的质量比为1∶2,加入质量比为0.3%戊二醛溶液作交联剂... 详细信息

以壳聚糖和碱木质素为原料,以戊二醛作交联剂,制备碱木质素/壳聚糖反应膜,并测定薄膜的相关物理性能。研究结果表明,碱木质素/壳聚糖反应膜制备的最佳条件为羟甲基化碱木质素与壳聚糖的质量比为1∶2,加入质量比为0.3%戊二醛溶液作交联剂,0.5%(质量分数)甘油,25℃反应6h后真空脱泡2h得到制膜液,铺膜,于50℃烘干制膜。膜的厚度为12～13μm,抗张力为27～28N,吸水溶胀度为28.4%。羟甲基化碱木质素在壳聚糖膜中的分布较为均匀。羟甲基化碱木质素的羟基或壳聚糖的羟基与戊二醛发生了交联反应。由于碱木质素具有较强的抗酸性能,同时羟甲基化碱木质素抗碱能力高于碱木质素,使碱木质素壳聚糖反应膜在强酸和强碱性溶液中均保持了使用性能。提高了反应膜的抗酸碱性能,适用范围为pH值=1～14时,扩大了膜的使用范围。

关键词：羟甲基化木质素壳聚糖反应膜性能