乙炔加氢反应过程混合建模与优化

针对传统单一建模方法所构建的乙炔加氢反应器数学模型存在预测性能无法满足工业实际应用需求的问题,提出了一种机理与神经网络嵌套的建模方法,充分利用机理模型包含的能质约束信息降低神经网络模型的约束违反度,得到了能够良好描述实际工业乙炔加氢反应过程特性的混合模型。基于反应器混合模型,研究了以运行效益为目标函数的优化问题。主要决策变量包括:一段反应器进料中氢气与乙炔的摩尔比(RH/A)、进料温度和反应器运行周期等几个关键参数。针对反应器长期运行后,催化剂活性降低造成的处理能力下降的问题,提出了反应温度补偿机制和RH/A并行调节的运行优化策略,并采用序列法对反应器运行周期进行离散化处理。通过引入差异化变异策略、潜在解替代策略对两阶段差分算法进行改进,采用增量式编码法结合改进两阶段差分算法,对优化问题进行求解。结果证实了优化策略与改进算法的有效性,并据此确定了反应器最佳运行方案。     

乙炔加氢反应器全周期操作优化

乙炔加氢反应器作为乙烯工业流程的重要环节,其运行会很大程度上影响到乙烯产品的产量和纯度。在一个运行周期内,乙炔加氢反应器内催化剂活性会随时间推移而缓慢降低,使操作点偏移,乙烯产量会随之降低。为了实现全周期操作优化,通过研究催化剂的失活机理,提出了考虑绿油累积效果的催化剂失活动力学模型,进而改进了乙炔加氢反应器二维非均相模型。通过在gPROMS平台模拟反应器全周期运行验证了改进模型的正确性,在上层运用Matlab优化器与gPROMS平台交互求解一个运行周期的操作优化问题。优化结果表明,与定值温度补偿方案相比,全周期操作优化在经济效益和反应器再生周期两方面都要优于定值温度补偿方案,且同时优化入口温度与入口加氢量的全周期操作优化方案具有更大的优势。     

乙炔加氢反应器全周期操作优化

乙炔加氢反应器作为乙烯工业流程的重要环节,其运行会很大程度上影响到乙烯产品的产量和纯度。在一个运行周期内,乙炔加氢反应器内催化剂活性会随时间推移而缓慢降低,使操作点偏移,乙烯产量会随之降低。为了实现全周期操作优化,通过研究催化剂的失活机理,提出了考虑绿油累积效果的催化剂失活动力学模型,进而改进了乙炔加氢反应器二维非均相模型。通过在g PROMS平台模拟反应器全周期运行验证了改进模型的正确性,在上层运用Matlab优化器与g PROMS平台交互求解一个运行周期的操作优化问题。优化结果表明,与定值温度补偿方案相比,全周期操作优化在经济效益和反应器再生周期两方面都要优于定值温度补偿方案,且同时优化入口温度与入口加氢量的全周期操作优化方案具有更大的优势。     

基于Alopex的进化算法及其在乙炔加氢反应器建模中的应用

分析进化优化算法的共性,参考Alopex优化思想提出一种新的进化优化算法.给出该算法的具体步骤,将该算法与标准粒子群算法、遗传算法和差分算法在性能上做了仿真时比,并将其应用于乙炔加氢反应器出口乙炔浓度软测量的建模中.这种新的优化算法具有全局收敛能力,并具有较快的收敛速度.对典型函数的测试和基于神经网络的软测量建模表明:新算法具有较强的全局搜索能力,特别是对易于陷入局部最优的多峰函数能够有效地避免早熟收敛问题.     

工艺调度对乙炔加氢反应器优化运行策略的影响分析

乙炔加氢反应器是乙烯工业中用于除去高浓度乙烯流中的少量乙炔的重要装置,该装置一般持续运行较长时间,期间反应器内催化剂活性逐渐降低,直至活性难以满足工艺要求。乙炔加氢反应器全周期操作优化一般是针对装置的一个再生周期进行的,在装置运行周期内应按照操作优化方案进行。但是,在实际工业过程中,为了满足临时的工艺调度需求,乙炔加氢反应器在按照操作优化方案运行一定时间后,需要在剩余的运行周期内临时改变操作方案,这给操作优化问题带来了更多变化和挑战。基于裕量估计和慢时变系统的控制优化框架,研究了这类在运行周期中临时改变操作优化方案的全周期动态优化问题。改变操作优化方案的方式包括：变更运行周期、追求经济效益最大化和变更优化目标、追求运行周期最大化。通过对这两种改变操作优化方案的分析,发现前者变更的运行周期越接近原定运行周期,全周期总经济效益越高,后者切换时刻越早,反应器能维持的运行周期越长,但二者的全周期经济效益均不及原操作优化方案,临时的工艺调度对乙炔加氢反应器的全周期优化运行总体上是不利的。     

乙炔加氢串联反应器全周期乙炔转化率最优分配研究

在乙炔加氢反应器的实际生产运行过程中,乙炔加氢反应大部分在第一床层,加氢反应放出的大量热量使得床层内温度高于最佳反应温度范围,致使乙烯选择性降低,乙烯产量下降,而在进行全周期操作优化时并未考虑到此问题。因此,首先考虑温度对绿油累积的影响,修正了催化剂失活动力学方程;其次,为保证反应器各床层内温度都在最佳反应温度范围,从化学反应工程理论和实际生产过程中的安全性两个角度出发,给出两种反应器各床层乙炔转化率分配方案;最后,在常规全周期操作优化模型中添加乙炔转化率约束,建立全周期乙炔转化率分配操作优化模型,并对两种乙炔转化率分配方案进行全周期操作优化。优化结果表明,两种乙炔转化率分配方案操作优化的乙烯产量要远远高于常规操作优化,且乙炔转化率方案为33∶33∶33时,乙烯产量最高,而考虑实际生产过程中的安全性,乙炔转化率分配方案为43∶47∶10时具有更好的效果。     

乙炔加氢串联反应器全周期乙炔转化率最优分配研究

在乙炔加氢反应器的实际生产运行过程中,乙炔加氢反应大部分在第一床层,加氢反应放出的大量热量使得床层内温度高于最佳反应温度范围,致使乙烯选择性降低,乙烯产量下降,而在进行全周期操作优化时并未考虑到此问题。因此,首先考虑温度对绿油累积的影响,修正了催化剂失活动力学方程;其次,为保证反应器各床层内温度都在最佳反应温度范围,从化学反应工程理论和实际生产过程中的安全性两个角度出发,给出两种反应器各床层乙炔转化率分配方案;最后,在常规全周期操作优化模型中添加乙炔转化率约束,建立全周期乙炔转化率分配操作优化模型,并对两种乙炔转化率分配方案进行全周期操作优化。优化结果表明,两种乙炔转化率分配方案操作优化的乙烯产量要远远高于常规操作优化,且乙炔转化率方案为33∶33∶33时,乙烯产量最高,而考虑实际生产过程中的安全性,乙炔转化率分配方案为43∶47∶10时具有更好的效果。     

乙二醇装置草酸二甲酯加氢系统催化剂运行性能及产品品质影响因素分析

河南龙宇煤化工有限公司2×200 kt/a煤制乙二醇装置采用河南能源化工集团拥有自主知识产权的“羰基化、加氢两步间接合成法”生产工艺及Cu/SiO₂加氢催化剂，加氢催化剂使用寿命较短，催化剂运行性能(含使用寿命)又进一步影响乙二醇产品的品质。基于草酸二甲酯加氢反应机理与反应条件及加氢反应系统工艺流程，分析与探讨加氢催化剂装填高度、草酸二甲酯进料纯度、加氢反应器列管直径、氢酯比、草酸二甲酯进料浓度、加氢反应器入口温度、草酸二甲酯中水含量、加氢压力、草酸二甲酯中碳酸二甲酯含量、加氢催化剂床层压差等对草酸二甲酯加氢催化剂运行性能及乙二醇产品品质的影响，提出提高原料氢气及循环氢气的纯度、控制好氢酯比、选择合适的加氢反应器汽包温度和进料温度、严格控制进料浓度/水含量、降低草酸二甲酯进料中杂质含量等操作优化措施，以提升催化剂的运行性能、有效延长催化剂的使用寿命。     

催化剂失活条件下的碳二加氢反应器模拟与优化

乙炔加氢反应催化剂的活性与选择性随着使用时间变化而变化,操作参数需要相应的改变从而使得收益最大化。因此本文采集工业数据,通过遗传算法拟合了反应动力学模型和失活反应模型的参数;比较了国内最普遍使用的两种催化剂的选择性和活性保持方面的性能;针对串联使用的两台装填不同催化剂的反应器组合,以运行周期、乙烯产率最优为评价标准,提出了反应器3种组合优化、负荷分配优化等优化策略。将优化策略应用于实际工业装置的分析与运行,乙烯产率和总选择性提高,效果得到验证。     

单纯形-差分进化算法及其在软测量建模上的应用

针对差分进化算法（Differential Evolution Algorithm,DEA）容易陷入局部最优值且搜索效率不高的缺点,提出一种单纯形一差分进化算法（SM—DEA）。该算法在DEA中引入计算量小、搜索速度快且局部搜索能力很强的单纯形方法（Simplex Method,SM）,在迭代过程中交叉使用DEA和SM。对标准函数的测试表明,该算法具有很强的全局搜索能力和很高的搜索效率。将算法应用于乙炔加氢反应器出口乙炔浓度的软测量建模,结果表明该算法能提高模型的精确度,降低预测误差,具有较高的实用价值。     

考虑原油性质波动的炼厂氢气网络集成优化

针对原油性质的不确定性,提出了一种基于质量传递机理的随机规划建模框架,以实现炼厂氢气网络在经济效益和抗扰能力上的同步优化。该框架耦合了常减压蒸馏、加氢精制以及闪蒸分离等过程单元,从微观上解析原油性质波动对网络运行的影响;采用了代理模型技术增设脱硫模块,并利用了二阶段随机规划方法改造管网,从宏观上优化氢气网络以满足生产要求。为验证所提方法的有效性和适用性,对某一现有的炼厂氢网络进行了改造设计研究。结果表明,集成过程单元的多场景优化策略能够有效提升网络的经济性能,并且能使其灵活应对因原油性质波动引起的操作场景的改变。     

Dynamic On‐Line Reoptimization Control of a Batch MMA Polymerization Reactor Using Hybrid Neural Network Models

A hybrid neural network model based on‐line reoptimization control strategy is developed for a batch polymerization reactor. To address the difficulties in batch polymerization reactor modeling, the hybrid neural network model contains a simplified mechanistic model covering material balance assuming perfect temperature control, and recurrent neural networks modeling the residuals of the simplified mechanistic model due to imperfect temperature control. This hybrid neural network model is used to calculate the optimal control policy. A difficulty in the optimal control of batch polymerization reactors is that the optimization effort can be seriously hampered by unknown disturbances such as reactive impurities and reactor fouling. With the presence of an unknown amount of reactive impurities, the off‐line calculated optimal control profile will be no longer optimal. To address this issue, a strategy combining on‐line reactive impurity estimation and on‐line reoptimization is proposed in this paper. The amount of reactive impurities is estimated on‐line during the early stage of a batch by using a neural network based inverse model. Based on the estimated amount of reactive impurities, on‐line reoptimization is then applied to calculate the optimal reactor temperature profile for the remaining time period of the batch reactor operation. This approach is illustrated on the optimization control of a simulated batch methyl methacrylate polymerization process.     

OPTIMIZING THE FEED CONDITIONS IN A DIMETHYL ETHER PRODUCTION PROCESS TO MAXIMIZE METHANOL CONVERSION USING A HYBRID FIRST PRINCIPLE NEURAL NETWORK APPROACH

Modeling is a fundamental step in plant optimization and simulation. In this work, a new technique for modeling a gas-solid heterogeneous fixed-bed reactor is developed. Gas diffusion into the solid catalyst pellets requires solving the mass balance equations inside the catalyst. The computational load needed can be quite time-consuming due to system complexities and nonlinearities. This bottleneck prevents on-line optimization of the process. In this work, a trained three-layer neural network model is used to replace major parts of these computations. The model is then incorporated within the overall model of an adiabatic fixed-bed reactor to produce dimethyl ether (DME) from methanol dehydration over solid acidic catalysts. The performance of the reactor simulated using this procedure indicated good agreement with its experimental operation. Then an optimizer is employed to determine the best feed conditions. The proposed strategy can be applied to any heterogeneous fixed-bed reactor.     

Process modeling and optimization of industrial ethylene oxide reactor by integrating support vector regression and genetic algorithm

This article presents an artificial intelligence‐based process modeling and optimization strategies, namely support vector regression–genetic algorithm (SVR‐GA) for modeling and optimization of catalytic industrial ethylene oxide (EO) reactor. In the SVR‐GA approach, an SVR model is constructed for correlating process data comprising values of operating and performance variables. Next, model inputs describing process operating variables are optimized using Genetic Algorithm (GAs) with a view to maximize the process performance. The GA possesses certain unique advantages over the commonly used gradient‐based deterministic optimization algorithms The SVR‐GA is a new strategy for chemical process modeling and optimization. The major advantage of the strategies is that modeling and optimization can be conducted exclusively from the historic process data wherein the detailed knowledge of process phenomenology (reaction mechanism, kinetics, etc.) is not required. Using SVR‐GA strategy, a number of sets of optimized operating conditions leading to maximized EO production and catalyst selectivity were obtained. The optimized solutions when verified in actual plant resulted in a significant improvement in the EO production rate and catalyst selectivity.     

基于神经网络的丙烯腈流化床反应器的离线模拟与优化

A mathematical model is developed for an industrial acrylonitrile fluidized-bed reactor based on artificial neural networks.A new algorithm,which combines the characteristics of both genetic algorithm(GA) and generalized delta-rule(GDR) is used to train artificial neural network (ANN) in order to avoid search terminated at a local optimal solution.For searching the global optimum,a new algorithm called SM-GA,incorporating advantages of both simplex method (SM) and GA, is proposed and applied to optimize the operating conditions of an acrylonitrile fluidized-bed reactor in industry.     

Performance evaluation of an ANN–GA aided experimental modeling and optimization procedure for enhanced synthesis of marine biosurfactant in a stirred tank reactor

BACKGROUND: An improved resilient back‐propagation neural network modeling coupled with genetic algorithm aided optimization technique was employed for optimizing the process variables to maximize lipopeptide biosurfactant production by marine Bacillus circulans. RESULTS: An artificial neural network (ANN) was used to develop a non‐linear model based on a 2⁴ full factorial central composite design involving four independent parameters, agitation, aeration, temperature and pH with biosurfactant concentration as the process output. The polynomial model was optimized to maximize lipopeptide biosurfactants concentration using a genetic algorithm (GA). The ranges and levels of these critical process parameters were determined through single‐factor‐at‐a‐time experimental strategy. Improved ANN‐GA modeling and optimization were performed using MATLAB v.7.6 and the experimental design was obtained using Design Expert v.7.0. The ANN model was developed using the advanced neural network architecture called resilient back‐propagation algorithm. CONCLUSION: Process optimization for maximum production of marine microbial surfactant involving ANN‐GA aided experimental modeling and optimization was successfully carried out as the predicted optimal conditions were well validated by performing actual fermentation experiments. Approximately 52% enhancement in biosurfactant concentration was achieved using the above‐mentioned optimization strategy. © 2012 Society of Chemical Industry     

Dynamic mathematical modeling of a novel dual-type industrial ethylene oxide (EO) reactor

In this paper, the dynamic behavior of a novel dual-type industrial ethylene oxide reactor has been proposed with taking catalyst deactivation into account. The configuration of two catalyst beds instead of one single catalyst bed is developed for conversion of ethylene to ethylene oxide. In the first reactor which is an industrial fixed-bed water-cooled reactor, the feed gas is partly converted to ethylene oxide. This reactor functions at very high yield and at a higher than normal operating temperature. In the second converter, the reaction heat is used to preheat the feed gas to the first reactor and a milder temperature profile is observed. The potential possibilities of a two-stage catalyst bed system are analyzed using a 1D heterogeneous dynamic model to obtain necessary comparative estimates. A differential evolution (DE) algorithm is applied as an effective and robust method to optimize the reactors length ratio. The results obtained from the simulation demonstrate that there is a desirable catalyst temperature profile along the dual-type reactor (DR) compared with the conventional single-type reactor (SR). In this way, the catalysts are exposed to less extreme temperatures and thus, diminishing the catalyst deactivation via sintering. Results from this study provided beneficial information about the effects of reactors configuration on catalyst lifetime and ethylene oxide production rate simultaneously.     

基于改进Kalman滤波算法的多模型融合建模方法

针对聚合物生产过程重要质量控制指标或状态变量的软测量问题,提出了一种基于改进Kalman滤波算法的多模型融合建模方法。将混合核函数主元分析(K₂PCA)与人工神经网络(ANN)相结合,建立一种基于K₂PCA-ANN的数据驱动模型;利用改进Kalman滤波算法实现K₂PCA-ANN模型与机理模型融合,构建一种并联结构的混合模型;协调二次滤波(线性滑动平滑)和方差更新对混合模型进行优化处理,使混合模型的估计性能尽可能地达到最优,使混合模型的预测稳定性得到有效改善。将该多模型融合建模方法应用于氯乙烯聚合过程聚合速率软测量中,应用研究结果表明:与单一的机理模型或K₂PCA-ANN数据驱动模型的预测性能相比,该建模方法建立的聚合速率模型具有更佳的预测性能。该建模方法的运用为进一步开展聚合物生产过程优化与控制等研究提供基础条件。     

融合过程先验知识的递归神经网络模型及其应用

大部分化工过程具有非线性特性,一般的线性建模方法难以有效应用。针对非线性化工过程动态建模,提出了一种基于过程先验知识的递归神经网络模型,充分发掘化工过程隐含的先验知识,并将这些先验知识以非线性约束的形式嵌入NARMAX结构的前馈神经网络中,同时基于增广拉格朗日乘子法约束处理机制,用PSO-IPOPT混合优化算法对过程先验知识递归神经网络权值进行优化。该过程先验知识递归神经网络模型对非线性化工过程动态建模,不仅有良好的建模精度和预测外推能力,而且能避免零增益的出现和增益反转,确保网络模型在实际应用中的安全性。文中以环管式丙烯聚合反应过程实际工业数据验证了所提网络模型的有效性。     

DMOS优化软件及其在化工过程优化中的应用

DMOS软件综合运用了模式识别、支持向量机、人工神经网络、遗传算法、线性和非线性回归等多种数据挖掘技术,能有效解决复杂工业过程系统优化中普遍存在的多因子、高噪声、非线性、非高斯分布和非均匀分布的难题。将DMOS工业优化软件成功地应用于柴油加氢精制装置及丙烯腈反应装置的生产优化。根据装置DCS系统采集的生产数据,研究了装置优化操作的主要工艺参数,采用模式识别方法建立了装置生产优化操作的定性模型,并最终建立了优化目标的数学模型。