检索结果-南通市图书馆

Online complex nonlinear industrial process operating optimality assessment using modified robust total kernel partial M-regression

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2018年第4期26卷 775-785页

作者： fei chu Wei Dai Jian Shen Xiaoping Ma Fuli Wang School of Information and Control Engineering China University of Mining and Technology Xuzhou 221116 China State Key Laboratory of Integrated Automation for Process Industries Northeastern University Shenyang 110819 China College of Information Science and Engineering Northeastern University Shenyang 110819 China

Although industrial processes often perform perfectly under design conditions, they may deviate from the optimal operating point owing to parameters drift, environmental disturbances, etc. Thus, it is necessary to develop efficacious strategies or procedure to assess the process performance online. In this paper, we explore the issue of operating optimality assessment for complex industrial processes based on performance-similarity considering nonlinearities and outliers simultaneously, and a general enforced online performance assessment framework is proposed. In the offline part, a new and modified total robust kernel projection to latent structures algorithm,T-KPRM, is proposed and used to evaluate the complex nonlinear industrial process, which can effectively extract the optimal-index-related process variation information from process data and establish assessment models for each performance grades overcoming the effects of outlier. In the online part, the online assessment results can be obtained by calculating the similarity between the online data from a sliding window and each of the performance grades. Furthermore, in order to improve the accuracy of online assessment, we propose an online assessment strategy taking account of the effects of noise and process uncertainties. The Euclidean distance between the sliding data window and the optimal evaluation level is employed to measure the contribution rates of variables, which indicate the possible reason for the non-optimal operating performance. The proposed framework is tested on a real industrial case: dense medium coal preparation process, and the results shows the efficiency of the proposed method comparing to the existing method.

关键词：复杂工业过程评价模型操作性能非线性联机柔韧修改欧几里德几何学

Trimmable bandgap reference circuit with exponential curvature compensation

在线全文

学校读者我要写书评

暂无评论

电子科技学刊:英文版 2023年第3期21卷 52-62页

作者： Hong-Zhuan Chen fei chu Wen-Tao Lu Tie-Liang Zhang Wen-Chang Li Wei Gao College of Economics and Management Nanjing University of Aeronautics and AstronauticsNanjing210016China Beijing Microelectronics Technology Institute Beijing100076China Institute of Semiconductors Chinese Academy of SciencesBeijing100085China The Ninth Academy of China Aerospace Science and Technology Corporation Beijing100094China

This paper proposes an improved exponential curvature-compensated bandgap reference circuit to exploit the exponential relationship between the current gainβof the bipolar junction transistor(BJT)and the temperature as well as reduce the influence of resistance-temperature dependency.Considering the degraded circuit performance caused by the process deviation,the trimmable module of the temperature coefficient(TC)is introduced to improve the circuit stability.The circuit has the advantages of simple structure,high linear stability,high TC accuracy,and trimmable TC.It consumes an area of 0.09 mm^(2)when fabricated by using the 0.25-μm complementary metal-oxide-semiconductor(CMOS)process.The proposed circuit achieves the simulated power supply rejection(PSR)of about-78.7 dB@1 kHz,the measured TC of~4.7 ppm/℃over a wide temperature range from-55℃to 125℃with the 2.5-V single-supply voltage,and the tested line regulation of 0.10 mV/V.Such a high-performance bandgap reference circuit can be widely applied in high-precision and high-reliability electronic systems.

关键词： Bandgap reference Exponential curvature compensation Temperature coefficient(TC) Trimmable

基于沙漏注意力高分辨率网络的人体姿态评估实验

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

实验室研究与探索 2024年第1期43卷 204-208,222页

作者：云霄褚菲张晓光程小舟中国矿业大学信息与控制工程学院江苏徐州221116

基于人体关键点检测的方法需要融合由高分辨率到低分辨率子网络生成的表示,以提高关键点检测的准确性。设计了一种基于沙漏注意力高分辨率网络的人体姿态评估方法实验,在深度高分辨率表示学习的基础上构建沙漏注意力特征模块,并设计特... 详细信息

基于人体关键点检测的方法需要融合由高分辨率到低分辨率子网络生成的表示,以提高关键点检测的准确性。设计了一种基于沙漏注意力高分辨率网络的人体姿态评估方法实验,在深度高分辨率表示学习的基础上构建沙漏注意力特征模块,并设计特征回传模块和多阶段监督算法,用融合中继监督和自蒸馏的方式实现高分辨率网络的监督训练。与经典方法在标准数据集上完成人体姿态评估实验对比,并在硬件设备上进行了真实场景实验,实现了行人姿态评估和危险行为报警。

关键词：人体姿态评估关键点检测注意力机制自蒸馏多阶段监督

Biochemical, molecular, and morphological variations of flight muscles before and after dispersal flight in a eusocial termite, Reticulitermes chinensis

在线全文

学校读者我要写书评

暂无评论

Insect Science 2021年第1期28卷 77-92页

作者： Zhen-Yu Zhang Jing Ren fei chu Jun-Xia Guan Guang-Yu Yang Yu-Tong Liu Xin-Ying Zhang Si-Qin Ge Qiu-Ying Huang Hubei Insect Resources Utilization and Sustainable Pest Management Key Laboratory College of Plant Science and TechnologyHuazhong Agricultural UniversityWuhanChina Key Laboratory of Zoological Systematics and Evolution Institute of ZoologyChinese Academy of SciencesBeijingChina

Swarming behavior facilitates pair formation,and therefore mating,in many eusocial termites.However,the physiological adjustments and morphological transformations of the flight muscles involved in flying and flightless insect forms are still unclear.Here,we found that the dispersal flight of the eusocial termite Reticulitermes chinensis Snyder led to a gradual decrease in adenosine triphosphate supply from oxidative phospho・rylation,as well as a reduction in the activities of critical mitochondrial respiratory enzymes from preflight to dealation.Correspondingly,using three-dimensional reconstruction and transmission electron microscopy(TEM),the flight muscles were found to be gradually deteriorated during this process.In particular,two tergo-pleural muscles(IItpm5 and IIItpm5)necessary to adjust the rotation of wings for wing shedding behavior were present only in flying alates.These findings suggest that flight muscle systems vary in function and morphology to facilitate the swarming flight procedure,which sheds light on the important role of swarming in successful extension and fecundity of eusocial termites.

关键词： dispersal flight eusocial termite flight muscle mitochondrial oxidative phosphorylation swarming behavior three-dimensional reconstruction

基于多源域适应JYPLS迁移的间歇过程质量预测

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

控制工程 2024年第1期31卷 32-39页

作者：王润褚菲马小平贾润达陆宁云中国矿业大学信息与控制工程学院江苏徐州221116 中国矿业大学地下空间智能控制教育部工程研究中心江苏徐州221116 中国矿业大学人工智能研究院江苏徐州221116 东北大学信息科学与工程学院辽宁沈阳110819 南京航空航天大学自动化学院江苏南京210016

针对间歇过程数据不足,单源域迁移存在模型偏移,跨域信息损失导致建模效果不佳、负迁移等问题,结合域适应学习和多源域学习方法的优势,提出一种基于多源域适应联合Y偏最小二乘(joint-Y partial least squares,JYPLS)迁移的间歇过程质量... 详细信息

针对间歇过程数据不足,单源域迁移存在模型偏移,跨域信息损失导致建模效果不佳、负迁移等问题,结合域适应学习和多源域学习方法的优势,提出一种基于多源域适应联合Y偏最小二乘(joint-Y partial least squares,JYPLS)迁移的间歇过程质量预测方法。该方法通过迁移学习使用相似旧过程的数据辅助新过程建模,提高建模效率和模型预测精度;采用多源域适应的方式,通过引入多个源域,有效避免了负迁移;基于域适应思想减少源域和目标域之间的边缘概率分布差异,使得源域知识在目标域更好地泛化。最后,通过青霉素发酵过程的仿真案例验证了所提方法的有效性。

关键词：间歇过程质量预测多源域迁移学习域适应

基于虚实结合实验平台的控制类综合实验课程建设

在线全文

学校读者我要写书评

暂无评论

实验室研究与探索 2024年第2期43卷 163-168页

作者：褚菲云霄卢新宇王雪松尤富强中国矿业大学信息与控制工程学院江苏徐州221116 东北大学信息科学与工程学院沈阳110819

以控制类综合实验课程为基础,构建多层次的实验教学内容,并提出了基于虚拟仿真实验环境与便携式综合实验集成实验箱进行实验验证的虚实结合的实验教学模式。控制类综合实验内容以加热铜块和直流伺服电动机为被控对象,利用KeilμVision4... 详细信息

以控制类综合实验课程为基础,构建多层次的实验教学内容,并提出了基于虚拟仿真实验环境与便携式综合实验集成实验箱进行实验验证的虚实结合的实验教学模式。控制类综合实验内容以加热铜块和直流伺服电动机为被控对象,利用KeilμVision4集成环境与Visual Studio2012加载Measurement Studio工具箱完成代码编写,根据Matlab/Simulink对被控对象进行模型辨识与仿真分析完成控制器参数的设计。同时建立一套完整的课程考核体系,学生以小组形式充分利用线上与线下的时间、集中与分散的场地灵活地进行数据采集、代码调试、算法设计和实际操控以完成整个实验课程内容。

关键词：新工科课程建设实验教学平台虚实结合

Universal cooling patterns of the butterfly wing scales hierarchy deduced from the heterogeneous thermal and structural properties of Tirumala limniace(Lepidoptera:Nymphalidae,Danainae)

在线全文

学校读者我要写书评

暂无评论

Insect Science 2022年第6期29卷 1761-1772页

作者： chu-fei Tang Fan-Fan Li Ye Cao Huai-Jian Liao Institute of Leisure Agriculture Jiangsu Academy of Agricultural SciencesNanjingChina Key Laboratory of Urban Agriculture Ministry of Agriculture and Rural AffairsShanghaiChina

The radiative cooling of butterfly wing scales hierarchy has great value in understanding how poikilotherms adapt to the environment and developing bionic ma-terials.However,it remains unclear what the cooling system is like and how the vari-ation of hierarchy affects the cooling efficiency.Therefore,the correlation between the variations of the structure and emissivity of scale hierarchy is thoroughly investigated in Tirumala limniace(Cramer,1775),whose thermal properties are highly heteroge-neous among different wings and regions but similar between males and females.Pat-terns were deduced from the biological and model simulation experiments.The scale hierarchy varies at the micro-to nanolevel on both surface and section,correspond-ing to the variating emissivity.Scales on wing veins and margins have large nanostruc-tured units with small lumens and are distinctly thickened,which bring extraordinarily high emissivity.The variations of light and dark scales,respectively,lead to the high emissivity of the middle region of wings and the front wings.Generally,the elevation of the inner surface area and the thickness of the chitin is the key to enhancing the cooling efficiency.For the first time,the effects of the variation of hierarchy toward emissivity of the mid-infrared spectrum are systematically clarified.It is demonstrated that wing scales integrally differentiate in coping with the heterogeneous cooling needs,which may benefit in balancing multifunctions and the development toward the adap-tation to the abiotic environment.The study provides insights into the comprehensive thermoregulation system of butterflies and the further development of radiative cooling materials.

关键词： butterfly emissivity heterogeneous hierarchy radiative cooling wing scales

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

基于精英反向学习与正余弦算法优化的蛇算法

计算机仿真 2024年第6期41卷 455-461页

作者：储飞王加阳田福林中南大学计算机学院湖南长沙410006

针对蛇算法求解精度不高和收敛速度慢等缺点,提出一种基于精英反向学习策略和正余弦算法优化的蛇算法(ESSO)首先在初始化种群时,引入精英反向学习策略生成初始种群,以增加初始个体的多样性;在战斗模式下,引入正余弦算法对蛇个体的位置... 详细信息

针对蛇算法求解精度不高和收敛速度慢等缺点,提出一种基于精英反向学习策略和正余弦算法优化的蛇算法(ESSO)首先在初始化种群时,引入精英反向学习策略生成初始种群,以增加初始个体的多样性;在战斗模式下,引入正余弦算法对蛇个体的位置进行更新,使其有效地避免陷入局部最优,并引入自适应权重,平衡全局和局部搜索能力;最后基于12个基准函数进行测试以评估改进算法的效率。结果表明,改进算法与其它6种算法相比,具有更好的全局搜索能力和稳定性,同时,寻优精度和收敛速度也相较原算法有所增强。

关键词：蛇优化反向学习正余弦算法

基于对齐性和均匀性约束的图神经网络会话推荐方法

在线全文

学校读者我要写书评

暂无评论

应用科技 2024年第2期51卷 90-98页

作者：唐韬韬楚飞汪炅贾彩燕北京交通大学计算机与信息技术学院北京100044 交通数据分析与挖掘北京市重点实验室北京100044

会话推荐(session-based recommendation,SBR)旨在匿名状态下通过用户的短期历史行为序列来预测下一个待点击的项目。为解决现有基于图神经网络(graph neural networks,GNNs)的会话推荐方法忽略会话中不同位置相同项目之间差异的问题,... 详细信息

会话推荐(session-based recommendation,SBR)旨在匿名状态下通过用户的短期历史行为序列来预测下一个待点击的项目。为解决现有基于图神经网络(graph neural networks,GNNs)的会话推荐方法忽略会话中不同位置相同项目之间差异的问题,在图卷积获得项目表示后,进一步考虑该项目与相邻项目之间的相关性,生成邻域相关的项目表示。此外,鉴于对齐性和均匀性在对比学习中的起到的重要作用,还提出了一种适用于会话推荐的对齐性和均匀性损失方法,以约束生成的会话表示和项目表示。在3个公开数据集上的实验表明,文中提出的模型TAU-GNN的推荐性能优于对比的主流会话推荐模型。

关键词：会话推荐图神经网络对齐性均匀性对比学习交叉熵损失匿名会话邻域信息

维普期刊数据库博看期刊