Bilinear model predictive control of grade change operations in paper production plants

In this work the bilinear model predictive control method is applied to control the grade change operations in paper production plants. Because of the high nonlinearity of the grade change processes, control of the grade change operations has been performed manually by experienced engineers in the plants. In some cases the bilinear model can be very effective to represent nonlinear processes. In this study a bilinear model for paper plants is identified first. It is found that the bilinear model tracks the plant without significant discrepancy. Based on the multivariable bilinear plant model the optimal input variables are computed using the one-step ahead prediction method. Even for frequent changes in paper grades the bilinear model predictive control scheme exhibits good control performance.     

Prediction and quality control of the melt index during production of high-density polyethylene

In polyolefin processes the melt index (MI) is the most important control variable indicating product quality. Because of the difficulty in the on-line measurement of MI, a lot of MI estimation and correlation methods have been proposed. In this work a new dynamic MI estimation scheme is developed based on system identification techniques. The empirical MI estimation equation proposed in the present study is derived from the 1 ^st -order dynamic models. Effectiveness of the present estimation scheme was illustrated by numerical simulations based on plant operation data including grade change operations in high density polyethylene (HDPE) processes. From the comparisons with other estimation methods it was found that the proposed estimation scheme showed better performance in MI predictions. The virtual sensor model developed based on the estimation scheme was combined with the virtual on-line analyzer (VOA) to give a quality control system to be implemented in the actual HDPE plant. From the application of the present control system, significant reduction of transition time and the amount of off-spec during grade changes was achieved     

A recursive PLS-based soft sensor for prediction of the melt index during grade change operations in HDPE plant

An empirical model has been developed for the successful prediction of the melt index (MI) during grade change operations in a high density polyethylene plant. To efficiently capture the nonlinearity and grade-changing characteristics of the polymerization process, the plant operation data is treated with the recursive partial least square (RPLS) scheme combined with model output bias updating. In this work two different schemes have been proposed. The first scheme makes use of an arbitrary threshold value which selects one of the two updating methods according to the process requirement so as to minimize the root mean square error (RMSE). In the second scheme, the number of RPLS updating runs is minimized to make the soft sensor time efficient, while reducing, maintaining or normally increasing the RMSE obtained from first scheme up to some extent. These schemes are compared with other techniques to exhibit their superiority. This paper is dedicated to Professor Chang Kyun Choi to celebrate his retirement from the school of chemical and biological engineering of Seoul National University.     

Batch-to-batch optimal control of a batch polymerisation process based on stacked neural network models

A neural network based batch-to-batch optimal control strategy is proposed in this paper. In order to overcome the difficulty in developing mechanistic models for batch processes, stacked neural network models are developed from process operational data. Stacked neural networks have enhanced model generalisation capability and can also provide model prediction confidence bounds. However, the optimal control policy calculated based on a neural network model may not be optimal when applied to the true process due to model plant mismatches and the presence of unknown disturbances. Due to the repetitive nature of batch processes, it is possible to improve the operation of the next batch using the information of the current and previous batch runs. A batch-to-batch optimal control strategy based on the linearisation of stacked neural network model is proposed in this paper. Applications to a simulated batch polymerisation reactor demonstrate that the proposed method can improve process performance from batch to batch in the presence of model plant mismatches and unknown disturbances.     

A comparative study of models for molten carbonate fuel cell (MCFC) processes

The necessity of this work arose from the need for identification of a comprehensive plant model that can be used in the model-based control of the MCFC plant. Various models for molten carbonate fuel cell (MCFC) processes are presented and evaluated in this paper. Both a rigorous model based on mass and energy balances and implicit models based on operation data were investigated and analyzed. In particular, auto-regressive moving average (ARMA) model, least-squares support vector machine (LSSVM) model, artificial neural network (ANN) model and partial least squares (PLS) model for a MCFC system were developed based on input-output operating data. Among these models, the ARMA model showed the best agreement with plant operation data.     

水泥煅烧工段机理分析与神经网络预测方法

采用神经网络的方法建立水泥预分解窑煅烧工段的预测模型。选择合理的状态与控制变量,通过采集实际运行数据来训练神经网络。构建的基于BPNN神经网络的煅烧预测模型能够较好地拟合采样数据,具有较好的泛化能力。     

基于BP神经网络的臭氧精确投加控制系统

自来水厂采用臭氧化工艺时臭氧投加量通常由生产经验判断确定,缺乏一定的准确性和时效性。根据浙江省T水厂150组实际运行样本数据,选用BP神经网络构建臭氧投加系统的前馈控制模型,能够在给定的工艺参数条件下较好地预测出水水质情况,也可根据进水水质情况和预期出水水质目标对所需的臭氧投加量进行预测。结果表明:基于BP神经网络的臭氧投加模型可以满足不同的水质变化,模拟精度较高,具有明显的优越性,对进一步提高供水安全性、节约制水成本具有重要的推动作用,也为臭氧-活性炭深度处理运行的自动化控制提出了新的理论思路。     

厂际氢气网络多周期集成的分步优化方法

厂际氢气系统集成对于化工园区合理配置氢气系统和氢气资源具有重要意义。针对化工园区中多厂氢气网络多周期优化设计的问题,提出了一种三步求解策略优化设计多厂氢气网络的多周期优化设计。该方法首先采用厂际氢气网络的单周期优化模型获取各子周期下的氢气公用工程的传输量,然后采用单厂氢气网络的多周期优化设计模型获得各厂内的氢气系统结构,最后采用厂际氢气系统的多周期优化设计模型确定化工园区中厂际氢气系统的网络结构和氢气调度方案。研究表明,所提出的多厂氢气网络多周期优化设计方法可有效解决厂际氢气网络的优化设计问题,该策略在不增加氢气系统结构复杂度的前提下,可以获得较好的经济性,并可提高优化模型求解的计算效率。     

The control of MSF desalination plants based on inverse model control by neural network

In this paper, a nonlinear inverse model control strategy based on neural network is proposed for MSF desalination plant. Artificial neural networks (ANNs) can handle complex and nonlinear process relationships, and are robust to noisy data. The designed neural networks consist of three layers identified from input–output data and trained with a descent gradient algorithm. The set point tracking performance of the proposed method was studied when the disturbance is present in the MSF system. Three controllers are designed for controlling the top brine temperature, the level of last stage and salinity. These results show that a neural network inverse model control strategy (NNINVMC) is robust and highly promising to be implemented in such nonlinear systems. Also the comparison between the top brine temperature of the proposed model and NN predicted data from the literature supports the accuracy of the model.     

基于联立法的乙烯淤浆聚合牌号切换过程动态模拟

以乙烯淤浆聚合流程为研究对象,建立了包含动力学和热力学的动态机理模型,采用有限元正交配置法对控制变量和状态变量同步离散化,实现了全联立动态模拟。热力学物性计算采用Kriging函数估计,可适用于多个工况,最大误差不超过2%。利用Aspen Plus 5个牌号工况的数据,进行了模型稳态验证,并实现了牌号切换动态模拟,计算了平均分子量等质量指标,与Aspen Dynamic曲线吻合较好,为牌号切换的优化奠定了基础。     

Neural‐Networks‐Based Feedback Linearization versus Model Predictive Control of Continuous Alcoholic Fermentation Process

In this work advanced nonlinear neural networks based control system design algorithms are adopted to control a mechanistic model for an ethanol fermentation process. The process model equations for such systems are highly nonlinear. A neural network strategy has been implemented in this work for capturing the dynamics of the mechanistic model for the fermentation process. The neural network achieved has been validated against the mechanistic model. Two neural network based nonlinear control strategies have also been adopted using the model identified. The performance of the feedback linearization technique was compared to neural network model predictive control in terms of stability and set point tracking capabilities. Under servo conditions, the feedback linearization algorithm gave comparable tracking and stability. The feedback linearization controller achieved the control target faster than the model predictive one but with vigorous and sudden controller moves.     

An early warning generation and emergency advisory system and its application to power plants

Based on the fact that abnormal states continue prior to the breakage of the fault, an early warning system was developed by monitoring the variables in operation real-time, deciding on the operational status, and informing the operator of the process status in order to warn of an abnormal operation in advance. As the traditional system, operating based on threshold limits, separately monitors and manages each operating variable, the interaction/co-relationship among the variables is ignored. The proposed early warning system combines operating variables that interact with one another for each unit process or unit facility, producing a neural network model predicting the normal status values and generating warnings of abnormalities in the process in advance. A time extension function-linkage associative neural network model was designed and used taking consideration of the time lag. Based on the emergency advisory database established, an emergency advisory system was also developed that informs the operators of the cause, effect and emergency measures regarding abnormal operations recognized by the early warning system. The developed system was applied to the power plant operations, and it shows a good performance in early warning generation and provides good advice for the management of diagnosed abnormal situations.     

Using hybrid neural networks in scaling up an FCC model from a pilot plant to an industrial unit

The scaling up of a pilot plant fluid catalytic cracking (FCC) model to an industrial unit with use of artificial neural networks is presented in this paper. FCC is one of the most important oil refinery processes. Due to its complexity the modeling of the FCC poses great challenge. The pilot plant model is capable of predicting the weight percent of conversion and coke yield of an FCC unit. This work is focused in determining the optimum hybrid approach, in order to improve the accuracy of the pilot plant model. Industrial data from a Greek petroleum refinery were used to develop and validate the models. The hybrid models developed are compared with the pilot plant model and a pure neural network model. The results show that the hybrid approach is able to increase the accuracy of prediction especially with data that is out of the model range. Furthermore, the hybrid models are easier to interpret and analyze.     

人工神经网络在甲烷转化操作预报中的应用研究

利用人工神经网络中较经典的BP网络模型的网络结构和学习原理，对合成氨车间转化工段的数据利用神经网络模型进行指导操作调优。结果表明，该方法预报的结果与实际生产数据误差在合理范围之内，可作为甲烷转化工段生产控制、操作调优的辅助分析手段。     

Hybrid method integrating machine learning and particle swarm optimization for smart chemical process operations

Modeling and optimization is crucial to smart chemical process operations.However,a large number of nonlinearities must be considered in a typical chemical process according to complex unit operations,chemical reactions and separations.This leads to a great challenge of implementing mechanistic models into industrial-scale problems due to the resulting computational complexity.Thus,this paper presents an efficient hybrid framework of integrating machine learning and particle swarm optimization to overcome the aforementioned difficulties.An industrial propane dehydrogenation process was carried out to demonstrate the validity and efficiency of our method.Firstly,a data set was generated based on process mechanistic simulation validated by industrial data,which provides sufficient and reasonable samples for model training and testing.Secondly,four well-known machine learning methods,namely,K-nearest neighbors,decision tree,support vector machine,and artificial neural network,were compared and used to obtain the prediction models of the processes operation.All of these methods achieved highly accurate model by adjusting model parameters on the basis of high-coverage data and properly features.Finally,optimal process operations were obtained by using the particle swarm optimization approach.     

Melt index prediction by RBF neural network with an ICO‐VSA hybrid optimization algorithm

Melt index (MI) is considered as one of the most significant parameter to determine the quality and the grade of the practical polypropylene polymerization products. A novel ICO‐VSA‐RNN (RBF neural network with ICO‐VSA algorithm) MI prediction model is proposed based on radial basis function (RBF) neural network and improved chaos optimization (ICO), and variable‐scale analysis (VSA), where the ICO is first added and then combined with the VSA to overcome the defects of ICO and VSA, then the parameters of the RBF neural network are optimized with them. At last, the RBF neural network model for MI prediction model is developed. Further researches on the optimal RBF neural network model of MI prediction are carried out with the data from a real industrial plant, and the prediction results show that the performance of this prediction model is much better than the RBF neural network model without optimization. © 2012 Wiley Periodicals, Inc. J Appl Polym Sci, 2012     

HYBRID NEURAL MODELLING OF FLUIDISED BED DRYING PROCESS

The aim of this study was to investigate the applicability of hybrid neural models in modelling of drying process. A study aimed at extending a neural network mapping was also carried out. In this approach dimensionless numbers (Re, Ar, H/d) were used as inputs to predict the heat transfer coefficient in a fluidised bed drying process. To produce a data set necessary to train the networks, trials of drying different materials in a fluidised bed were carried out. On the basis of this network, a hybrid model describing the process of drying in a fluidised bed dryer was built. Results obtained were compared not only with available experimental data but also with results obtained using other types of models: a pseudo-dynamic neural model and a classical mathematical model. The analysis of results leads to a conclusion that hybrid models constitute a solid alternative method of process modelling.     

HYBRID NEURAL MODELLING OF FLUIDISED BED DRYING PROCESS

The aim of this study was to investigate the applicability of hybrid neural models in modelling of drying process. A study aimed at extending a neural network mapping was also carried out. In this approach dimensionless numbers (Re, Ar, H/d) were used as inputs to predict the heat transfer coefficient in a fluidised bed drying process. To produce a data set necessary to train the networks, trials of drying different materials in a fluidised bed were carried out. On the basis of this network, a hybrid model describing the process of drying in a fluidised bed dryer was built. Results obtained were compared not only with available experimental data but also with results obtained using other types of models: a pseudo-dynamic neural model and a classical mathematical model. The analysis of results leads to a conclusion that hybrid models constitute a solid alternative method of process modelling.     

重力热管振荡传热特性RBF神经网络动态建模

The work address the problem of modeling the dynamical oscillating behavior during both unstable and stable operations, of an experimental thermosyphon. A standard RBF artificial neural network-based prediction model was developed for predicting the oscillating heat transfer of thermosyphon by means of input-output experimental measurements with the characteristics of time series. A comparison of prediction values between the RBF network and the MLP network was giving. The precision of RBF network was higher than that of the other neural networks such as BP-MLP network etc. The dynamical model of RBF network could be used to describe, predict and control the heat transfer process of a thermosyphon or a heat pipe system.     

On‐Line PEMFC Control Using Parameterized Nonlinear Model‐Based Predictive Control

In this work, a fast nonlinear model‐based predictive control (NMPC) strategy is designed and experimentally validated on‐line on a real fuel cell. Regarding NMPC strategies, the most challenging part remains to achieve on‐line implementation, especially when dealing with fast dynamic systems. As previously demonstrated in a recent work, the proposed control strategy is ideally suited to address this problem. Indeed, it is 30 times faster than classical NMPC controllers. This strategy relies on a specific parameterization of the control actions to reduce the computational time and achieve on‐line implementation. Due to its short computational time compared to mechanistic models, an artificial neural network model is designed and experimentally validated. This model is employed as internal model in the NMPC controller to predict the system behavior. To confirm the applicability and the relevance of the proposed NMPC controller varying control scenarios are investigated on a test bench. The built‐in controller is overridden and the NMPC controller is implemented externally and executed on‐line. Experimental results exhibit the outstanding tracking capability and robustness against model‐process mismatch of the proposed strategy. The parameterized NMPC controller turns out to be an excellent candidate for on‐line applications.