基于工业色谱仪的精馏脱炔烃塔软测量建模

提出一种基于工业色谱仪的软测量建模方法,并针对碳五馏分分离过程中的精馏脱炔烃塔塔底成分估计问题,建立了合适的工业软测量模型。介绍了工业色谱仪在线质量检测原理和LM-BP神经网络模型的建立,并利用工业色谱仪在线检测的质量数据进行系统的在线和周期性模型更新,提高了软测量模型的在线估计精度。研究结果表明,基于工业色谱仪的LM-BP神经网络模型是一种有效的软测量建模方法。     

Terminal composition control of a binary distillation column

Terminal composition control of a pilot scale binary distillation column operated under the control of an IBM 1800 digital computer has been studied for disturbances in feed flow rate. Conventional two point control, whereby the overhead composition is controlled by reflux flow rate and bottom composition by means of steam rate, was demonstrated to be unsatisfactory. Two alternate control systems, namely a noninteracting control system and a ratio control system were evaluated. The noninteracting control system was constructed from a transfer function representation of the distillation column dynamics, determined from a series of on-line pulse tests. The results show that a very significant improvement in the control of both compositions is achieved by using noninteracting control or the ratio control scheme suggested by Rijnsdorp compared to the behavior that results using conventional two point feedback control. However, the control performance obtained using noninteracting control was only marginally better than that using the ratio control scheme.     

Closed-loop optimal operation of batch distillation columns

Often, the main source of disturbance for a batch distillation system is an upset in the feed to the process. If the operation of a batch column is carried out on the basis of the nominal value of the feed composition, a high degree of uncertainty in the initial conditions to the batch may lead to run the column suboptimally, with a possibly large economic penalty. In this paper, a three-step strategy is proposed for the closed-loop implementation of optimal operating policies for batch rectifiers. First, the optimal reflux rate is calculated off-line for several feed compositions. Then, a correlation is developed off-line between the optimal reflux rate and the composition profile in the column at the end of the startup phase. Finally, the detection of the composition profile is performed on-line during the startup phase, so that the optimal reflux rate can be calculated and implemented in a closed-loop fashion. This allows operating the column optimally even though the actual feed composition is not known. Since the calculations to be performed on-line are straightforward, the computational demand is kept to a minimum. Results for binary and ternary systems indicate that, by using the proposed procedure, the column performance can be improved by as much as 30% with respect to a conventional open-loop optimal strategy.     

Tracking the predefined optimal policies for multiple-fraction batch distillation by using adaptive control

Predefined optimal policies will be tracked with control systems to realize the optimum of multiple-fraction batch distillation. Adaptive control is proposed to carry out this task. Characteristics of batch distillation control are analyzed and a proper system is designed for controlling such processes. Besides tracking the optimal reflux ratio profile, the maximum vapor load will be maintained during the batch. In addition, a changing temperature profile of the condenser should be followed to reduce the operating energy with a possibly minimum subcooling. Recursive least square estimation (RLSE) with a variable forgetting factor is applied to the on-line identification of the plant to follow the changing dynamics of the process. Generalized predictive control (GPC) is used to track the predefined policies. The effectiveness of the control strategy is verified with a pilot batch column and the tracking performance is compared with that of PID controllers.     

基于神经网络的软测量技术在精馏塔上的应用

针对扬子石化公司丁二烯精馏塔原控制系统存在的问题, 利用从集散控制系统(DCS)采集的大量现场数据和用机理模型得到的模拟数据, 运用前向反馈(BP)神经网络软测量技术，构造了产品丁二烯和总炔含量的自适应软测量仪表, 设计了一套控制系统. 实际监测数据表明, 这套控制系统可实现产品质量的闭环控制.     

用夹紧区原理确定多元恒回流比分批精馏最小回流比

夹紧区是精馏塔内出现的浓度几乎不变的区域,对于三元物系来说,根据夹紧区在塔内出现的位置可分为：上、中和下加紧区.在无穷板数和任一瞬时釜浓下选择不同的回流比可使分批精馏处于不同夹紧区下操作.文中讨论了三元恒回流比分批精馏过程中夹紧区的演变,在Rayleigh方程的基础上建立了应用夹紧区原理确定多元恒回流比分批精馏最小回流比的方法.该方法并不要求相对挥发度为常数,并且能准确计算顶浓,克服了通常所采用的Underwood公式法的缺陷,为多元分批精馏的简捷设计奠定了基础.     

Control of a binary distillation column utilizing a simple control law

Multivariable control of overhead and bottoms composition of a binary distillation column subjected to feed flow disturbances has been studied. The study has been performed using a pilot scale column, equipped with overhead and bottoms composition analyzers, operated under the control of an IBM 1800 digital computer. The column dynamic behavior, for control law calculation, was approximated by a two state variable model. Experimental results employing multivariable feedback and multivariable feedforward-feedback control laws are presented.     

Composition estimation of multicomponent reactive batch distillation with optimal sensor configuration

An inferential state estimation scheme based on extended Kalman filter (EKF) with optimal selection of sensor locations using principal component analysis (PCA) is presented for composition estimation in multicomponent reactive batch distillation. The properties of PCA are exploited to provide the most sensitive dynamic temperature measurement information of the process to the estimator for accurate estimation of compositions. The state estimator is supported by a simplified dynamic model of reactive batch distillation that includes component balance equations together with thermodynamic relations and reaction kinetics. The performance of the proposed scheme is evaluated by applying it for composition estimation on all trays, reboiler, reflux drum and products of a reactive batch distillation column, in which ethyl acetate is produced through an esterification reaction between acetic acid and ethanol. This quaternary system with azeotropism is highly nonlinear and typically suited for implementation of the proposed scheme. The results demonstrate that the proposed EKF estimation scheme with optimal temperature sensor configuration is effective for inferential estimation of compositions in multicomponent reactive batch distillation.     

A Design methodology of a soft sensor based on local models

A soft sensor is an empirical model, which estimates variables that is infeasible to measure on-line from other correlated variables. Because constructing a soft sensor is a process of data based empirical modeling, the homogeneity in the training data set is very important. If a process experiences a wide operation range or lasting significant disturbances, the data homogeneity is damaged and frequently results in several sub-clusters, which causes the prediction power of a soft sensor to be degraded. In this paper, we proposed a modeling procedure that involves classification of training data and subclass modeling. PLS and NLPLS are adopted selectively as the subclass modeling algorithm and wavelet coefficients thresholding is used to remove noises contained in signals without severe distortion of the signals. Also, weighted X variables based on Variable Importance to Projection(VIP) through exploratory PLS are used to enhance the performance of the subclass models. The proposed methodology has been illustrated using an application to the development of a soft sensor for composition estimation of a binary distillation column simulated with HYSYS. The soft sensor based on the proposed scheme has shown better performance and robustness.     

基于神经网络的常压塔柴油凝点软测量的研究与应用

研究某炼油厂常压塔三线柴油凝点的软测量建模问题,分析过程变量对柴油凝点的影响。基于在线分析仪6min采样数据,利用前向网络和时延前向网络(TDNN)分别建立了三线柴油凝点的静态软测量模型和动态软测量模型,并结合在线分析仪对模型实现了在线修正。通过两种模型的仿真和在线实施效果,表明基于神经网络的软测量模型取得了较好的应用效果,而且动态模型的实施效果优于静态模型。     

分批精馏最小过渡馏分量及过渡馏分脉冲控制法的研究

研究了分批精馏最小过渡馏分量 ,在此基础上针对分批精馏过渡馏分段的特点采用了全回流 全馏出交替进行的脉冲控制法。该法以动态模拟确定了全回流时间 ,统计法确定了全馏出时间。采用正己烷 环己烷物系进行对比实验结果表明 :与传统的恒回流比操作法相比 ,脉冲操作法可明显减少过渡馏分量、缩短操作时间和提高分离效率     

丙烯精馏塔智能控制系统设计及应用

针对乙烯生产装置丙烯精馏塔的工艺特征和操作特点,利用支持向量机在小样本数据建模中的优势,提出一种基于支持向量机丙烯浓度软测量技术,解决了塔釜建模数据样本少的问题,实现了塔釜丙烯浓度在线测量。在上述软测量系统的基础上,设计了丙烯浓度智能控制系统。该系统采用模糊PID作为丙烯浓度控制器,其输出量作为灵敏板温度控制器的设定值,与灵敏板温度控制构成串级调节系统,同时为了克服进料量对灵敏板温度造成的干扰,设计了进料流量前馈控制器。丙烯浓度智能控制系统对塔釜丙烯指标进行实时控制,提高了塔釜丙烯浓度的控制平稳度,解决了塔釜丙烯浓度超标问题。现场应用效果表明,该丙烯浓度软测量系统测量精度高,控制系统可以有效控制塔釜丙烯浓度,取得了良好的控制效果,满足了工业现场运行的需要。     

Soft sensor modeling method based on hybrid model of nearest neighbor and neural network

Soft-sensing modeling can effectively solve the problems of large measurement lag, high price, and complex maintenance of online analytical instruments in the production process. At present, neural network based on data-driven is one of the main tools of soft sensor. In the process of modeling data collection, the collection of dominant variables is much more difficult than that of auxiliary variables, resulting in a large amount of unlabeled data. However, traditional soft sensor modeling methods ignore these unlabeled data and only use a small amount of labeled data for modeling, which has negative effect on the prediction accuracy of the model. To solve the problem of label missing, the nearest neighbor algorithm is used to pseudo label the unlabeled data. At the same time, a network structure is designed by combining convolution operation and gated recurrent unit neural network (GRU) to further utilize the unlabeled data, extract the dynamic feature from data at different time, and improve the prediction accuracy of the neural network. Finally, the method is applied to the prediction of propane concentration on the top of propylene distillation column. The results show that the model can solve the problem of label missing in the nonlinear dynamic system and has higher prediction accuracy.     

基于最近邻与神经网络融合模型的软测量建模方法

软测量建模能够有效地解决生产过程中在线分析仪表测量滞后大、价格昂贵、维护保养复杂等问题。目前,基于数据驱动的神经网络是软测量建模的主要工具之一。而在建模数据的采集过程中,主导变量的采集相对辅助变量要困难得多,由此产生了大量缺失标签的数据。但传统的软测量建模方法却忽视了这些无标签数据,只利用少量的有标签数据建模,从而影响了模型的预测精度。为了解决标签缺失的问题,采用最近邻算法对无标签数据进行伪标记,同时设计了由卷积操作与门限循环单元神经网络（GRU）结合的网络结构来进一步利用无标签数据,提取不同时刻数据中的动态特征,提高神经网络的预测精度。最后将该方法应用于丙烯精馏塔塔顶丙烷浓度的预测,实验结果表明该模型能有效处理非线性动态系统的标签缺失问题,具有更高的预测精度。     

Real-time monitoring of an industrial batch process

This paper describes the development of a real-time monitoring system for a batch process operated by Aroma and Fine Chemicals Limited. The process shares many similarities with other batch processes in that cycle times can vary considerably, instrumentation is limited and inefficient laboratory assays are required to determine the end-point of each batch. The aim of the work conducted in this study was to develop a data driven system to accurately identify the end-point of the batch. This information can then be used to reduce the overall cycle time of the process. Novel approaches based upon multivariate statistical techniques are shown to provide a soft sensor that can estimate the product quality throughout the batch and provide a long-term estimate of the likely cycle time. This system has been implemented on-line and initial results indicate that it offers potential to significantly reduce operating costs.     

常压塔产品质量在线估计的非线性主元分析方法

提出一种新的软测量方法,通过建立过程变量非线性主元得分与产品质量参数之间的三层前向神经网络模型,得到产品质量参数的预测值。实际应用表明,该方法比常规的线性主元分析方法和神经网络方法具有更好的预测性能。     

双溶剂进口的双釜间歇萃取精馏

提出了带有塔底回收釜及双溶剂进口的间歇萃取精馏操作方式。在新操作方式中,塔内回流液不流回塔釜,而是流入塔底回收釜,再经简单蒸馏气相返回塔釜,回收后的溶剂返回精馏塔中。以乙二醇作溶剂分离乙醇-水物系的实验结果表明,当间歇操作次数为2时,产品采出率最大,单位产品消耗的新鲜溶剂量最少。新操作方式具有塔釜温度变化平稳,新鲜溶剂用量相对较少等优点。     

基于自适应神经模糊推理系统的间歇反应精馏组分估算(英文)

Composition estimation plays very important role in plant operation and control. Extended Kalman filter (EKF) is one of the most common estimators, which has been used in composition estimation of reactive batch distillation, but its performance is heavily dependent on the thermodynamic modeling of vapor-liquid equilibrium, which is difficult to initialize and tune. In this paper an inferential state estimation scheme based on adaptive neuro-fuzzy inference system (ANFIS), which is a model base estimator, is employed for composition estimation by using temperature measurements in multicomponent reactive batch distillation. The state estimator is supported by data from a complete dynamic model that includes component and energy balance equations accompanied with thermodynamic relations and reaction kinetics. The mathematical model is verified by pilot plant data. The simulation results show that the ANFIS estimator provides reliable and accurate estimation for component concentrations in reactive batch distillation. The estimated states form a basis for improving the performance of reactive batch distillation either through decision making of an operator or through an automatic closed-loop control scheme.     

多频率系统动态插值神经网络软测量建模

针对某些化工过程关键变量难以在线测量的问题,提出了一种基于多采样率系统的时间序列神经网络的软测量建模方法,建立了动态插值神经网络模型,并利用增强粒子群算法实现了网络参数的优化。将此方法用于实验室模拟建模,实现了变量的在线预估,并对网络的训练效果和泛化性能进行了分析,表明其建模效果明显优于普通静态神经网络。     

Intelligent control system for extractive distillation columns

We developed and implemented an intelligent control system to be used in an extractive distillation column that produces anhydrous ethanol using ethylene glycol as solvent. The concept of artificial neural networks (ANN) was used to predict new setpoints after disturbances, and proved to be a fast and feasible solution. The developed control system receives data from temperature, flowrate and composition measurements of the azeotrope feed, and the ANN estimates the new set-points of the controllers to maintain 99.5 mol% of ethanol at the top and less than 0.1mol% at the bottom; feed composition was also estimated using an ANN. All ANN were trained to provide output data corresponding to an optimized operating condition. The results showed that the intelligent control system can predict a new operating condition for any disturbance in the column feed and presented superior performance when compared with the control system without ANN.