潘立登
炼油、石化复杂过程建模与先进过程控制、闭环系统辨识、软测量技术应用和过程在线优化控制
个性化签名
- 姓名:潘立登
- 目前身份:
- 担任导师情况:
- 学位:
-
学术头衔:
博士生导师
- 职称:-
-
学科领域:
自动化仪器仪表与装置
- 研究兴趣:炼油、石化复杂过程建模与先进过程控制、闭环系统辨识、软测量技术应用和过程在线优化控制
浙江泰顺人,男,1938年3月生。1961年毕业于天津大学,现任北京化工大学教授,博士生导师,自动化研究所所长,中国自动化学会过程控制委员会常委、一些杂志编委和审稿人。1981年~1983年在加拿大多伦多大学作访问学者。1988年~1989年任美国3I公司仪器仪表副总工程师。讲授“先进控制理论与技术”,“系统辨识与建模”和“系统模型化与软测量技术”等课程,指导在读博士生8人,硕士生10人。在刊物和会议上发表论文150多篇。“对二甲苯模拟移动床计算机控制”、“化纤厂腈纶生产先进控制”和“中油克拉玛依石化公司Ⅰ套常减压蒸馏装置先进控制和优化控制应用”等项目,分别获得国家石油和化学工业局科技进步三等奖(证书号为98I-3-017-1)、中国石油化工集团公司科技进步二等奖(证书号为98-2-035)和北京市科技进步二等奖(证书号为2003工-2-015-01)。编写《化工对象动态特性测试方法》,《系统辨识与建模》等著作五本,合译著三本。负责并完成二十多个科研项目,目前在研项目5个,从事炼油、石化复杂过程建模与先进过程控制、闭环系统辨识、软测量技术应用和过程在线优化控制的研究与软件开发。
-
主页访问
3554
-
关注数
0
-
成果阅读
527
-
成果数
10
潘立登, 颜蒋国
,-0001,():
-1年11月30日
本文中我们提出一种跟踪人脸特征点的方法。使用一系列方向、频率、相位各不相同的Gabor小波,对测试序列第一帧中选定的人脸特征点进行小波变换,得到对应点的Jets,并将其作为后续帧的跟踪依据。对含有各种表情的视频序列进行测试,试验结果显示该方法是有效的。
小波, Gabor Jets, 弹性匹配, 人脸特征, 跟踪
-
68浏览
-
0点赞
-
0收藏
-
0分享
-
869下载
-
0评论
-
引用
潘立登, 李全善
,-0001,():
-1年11月30日
针对催化裂化复杂反应体系,提出了一种基于NLJ算法改进的随机搜索优化算法NLJ+,该方法引入了优化的中间结果和目标函数的变化来修正搜索范围,从而减少了搜索的随机性。该方法应用于催化裂化集总动力学模型轻燃料油反应网络动力学参数估计,降低了搜索算法对初值和实验误差的要求,保证了收敛稳定性。
催化裂化 集总 动力学 参数估计 NLJ优化方法
-
78浏览
-
0点赞
-
0收藏
-
0分享
-
208下载
-
0评论
-
引用
潘立登, 李全善, 王文新, 甄新平
,-0001,():
-1年11月30日
针对催化裂化先进控制难于长期投运的缺点,本文提出了一种基于OPC的数据采集技术和NLJ随机搜索算法,应用内模控制原理三者相结合的方法,对催化裂化PID控制回路进行参数优化。实际应用结果表明,该方法操作简洁实用,效果明显,为类似催化裂化装置的复杂控制系统的优化和先进控制提供了一种新思路。
催化裂化 IMC PID OPC NLJ 随机搜索算法方法
-
65浏览
-
0点赞
-
0收藏
-
0分享
-
364下载
-
0评论
-
引用
【期刊论文】常减压蒸馏装置双模型结构RBF神经网络建模及其应用
潘立登, 王文新, 李荣, 徐永新, 闻光辉
,-0001,():
-1年11月30日
在原油蒸馏过程中,侧线产品质量是重要的控制指标,也是过程优化模型中的关键约束条件。本文提出双模型结构RBF(Radial Basis Function)神经网络,结合工艺机理和相关分析法,筛选出影响较大的变量,对现场数据,用小波分析法,剔除噪声和故障数据,考虑各输入信号对软仪表影响时间的区别,分别采用不同的滞后时间,建立了常减压蒸馏装置质量软仪表模型,取得较好的结果。
RBF神经网络, 软仪表, 常减压蒸馏,, 双模型结构,, 滞后时间
-
70浏览
-
0点赞
-
0收藏
-
0分享
-
247下载
-
0评论
-
引用
潘立登, Na An, , Lideng Pan, Biaohua Chen*, Chengyue Li, Xuekun Niu
,-0001,():
-1年11月30日
A pilot scale reverse flow reactor for catalytic combustion of volatile organic compounds (VOCS) in contaminated air is studied and modeled. The quasi-steady state model of temperature profile for the reverse flow reactor is developed in terms of RBF (Radial Basis Function) neural networks. The deep knowledge repository with respect to temperature profile is yielded based on the determinant mathematical model, which increases the 'extrapolability' and 'reliability'. Additionally, the model's accuracy is improved by adjusting the model parameters advisably. For predicting and controlling the transient temperature, a real-time prognostic model of temperature profile is built based on dynamic RBF neural networks by using the Time Delay Neural Network (TDNN), which is to save the previous state in the time-delay cell. Simulation results have proved that the models presented in this paper are simple, highly accurate and can satisfy the control requirements.
VOCs, Reverse flow reactor, catalytic combustion, RBF neural networks, dynamic system, on-line correction
-
50浏览
-
0点赞
-
0收藏
-
0分享
-
243下载
-
0评论
-
引用
【期刊论文】The Application of Multiple Neural Networks in Software Instrument
潘立登, Pan Lideng, Ma Junying, Zhu Yuning
,-0001,():
-1年11月30日
The method of using Multiple Neural Networks based on RBF neural networks to build software instrument is introduced in this paper. A practical example of a viscosity software sensor is given to explain the procedure for developing the software instrument. The result proves Multiple Neural Networks is effective in process modeling.
multiple neural networks, RBF neural networks, software instrument
-
36浏览
-
0点赞
-
0收藏
-
0分享
-
62下载
-
0评论
-
引用
潘立登, Junying Ma, Wenxin Wang, Lideng Pan, Xueyuan Nie
,-0001,():
-1年11月30日
In this paper, the implement ot supervisory control, advanced process control and optimization control, which are applied to atmospheric and vacuum distillation unit in a plant, will be introduced as well as the scheme.
Atmospheric and Vacuum Distillation Unit,, Supervisory Control,, Advanced Process Control,, Optimization Control.,
-
49浏览
-
0点赞
-
0收藏
-
0分享
-
185下载
-
0评论
-
引用
【期刊论文】RBF Neural Networks And Its Application In Establishing Nonlinear Self-tuning Model
潘立登, Pan Lideng, Huang Xiaofeng, Ma Junying, Pan Yuying
,-0001,():
-1年11月30日
The principle and algorithm of neural networks using radial basis function (RBF) are discussed in this paper. The recursive least squares method is used to resolve the self-tuning problem of RBF neural network so that self-tuning models of nonlinear time-varying system is obtained. By using RBF neural networks, a self-tuning model of a reactor is established and compared with a BP neural networks model and a regression model. The results show that the RBF neural networks model is effective.
Neural network,, Radial Basis Function Networks,, Nonlinear Models,, Self-tuning,, Time-varying System,, Identification,, On-line
-
28浏览
-
0点赞
-
0收藏
-
0分享
-
84下载
-
0评论
-
引用
潘立登, Lideng Pan, Wenxin Wang, NingchuanWu, Junying Ma
,-0001,():
-1年11月30日
A design approach of IMC-PID in terms of robust stability and robust performance is developed, in which the process model is identified by closed-loop identification. Applying this software control system to certain atmospheric and vacuum distillation unit, the result is better than that of the traditional PID controller. Not only bear the virtues of internal model controller, but also have the simple structure like that of PID controller, the IMCPID controller cam be integrated into DCS (Distributed Control System).
Robust Stability,, Robust Performance,, Closed-loop,, Identification,, Atmospheric and Vacuum Distillation Unit,, Internal Model Controller (, IMC), ,, IMC-PID Controller.,
-
52浏览
-
0点赞
-
0收藏
-
0分享
-
193下载
-
0评论
-
引用
【期刊论文】AN OPTIMUM DISTRIBUTED GENETIC ALGORITHM FOR OPTIMIZATION OF A PROPYLENE HYDRATION REACTOR
潘立登, Huang Xiao-Feng, Ma Jun-Ying, Wu Chun-Yan, Pan Li-Deng∗
,-0001,():
-1年11月30日
Genetic algorithms(GAs) are general-purpose global optimization algorithms based on natural evolution principle. Real-coded genetic algorithms(RGAs) are concerned for its high precision and searching ability in whole space. This paper studies the efficiency of linear crossover operator in RGA by both mathematical analysis and simulation. A new linear crossover operator with optimum distribution is proposed, by which the son-individuals can reach uniform probability distribution in whole searching space. The application of the optimum distributed RGA in on-line optimization of a propylene hydration reactor is satisfied. Copyright 1999 IFAC
Genetic algorithms,, Efficient algorithms,, Distribution,, Parameters optimization,, Reactor control,, Chemical industry
-
31浏览
-
0点赞
-
0收藏
-
0分享
-
84下载
-
0评论
-
引用