Journal of the Taiwan Institute of Chemical Engineers
Prediction interval-based modelling of polymerization reactor: A new modelling strategy for chemical reactors
Introduction
Traditionally, free radical polymerization (FRP) processes are modelled by using mass and energy balance equations as well as differential algebraic equations [1]. Traditional modelling techniques used for industrial polymerization processes are reviewed by Muller et al. [2]. They divide the polymerization model into four sub-models. The four sub-models are reaction kinetics, thermodynamics, mass transport and particle kinetics model. Among these four sub-models, the mathematical models of reaction kinetics and mass transport are still limited. The reactions of polymerization are complex and diffusion limitation (glass and gel effect in high temperature) in mass transport affects both chemical rate constant and interphase mass transport.
In 1972, Ray presented a complete set of mathematical equations to describe the batch FRP systems under some assumptions [3]. In the following years, many research studies appeared in the literature to improve the mathematical model of polymerization reactors. Over the last century or so, researchers developed extensive mathematical models to present the dynamic behaviour of different polymerization systems [4], [5], [6], [7], [8]. Kiparissides [9] summarized the recent development of mathematical modelling for FRP in batch and continuous reactor. Many researchers also reviewed the modelling of FRP processes [10], [11].
Polystyrene (PS) polymerization in batch reactor is taken into account as a case study in this work. As mentioned earlier, Ray [3] described a complete set of mathematical equations for PS polymerization reactions. Many researchers followed this model for control study purpose due to the lack of available mechanistic models and to avoid the complexity of batch FRP reactors [12], [13], [14].
In the mathematical model, the major uncertainties lie in obtaining reasonable estimates of the termination rate parameters and the rate constants for transfer reactions, especially the ones representing transfer to large polymer molecules. There are lots of difficulties involved in kinetic modelling, such as systematic kinetic investigations are required, and often the type of data required is difficult to obtain due to poor precision, lack of well-developed procedures, and frequently practical problems such as the insolubility of branched polymers in common solvents. Therefore, researchers usually consider a lot of assumptions to develop a kinetic model for polymerization reactors due to above reasons [15], [16]. Moreover, there are no universal kinetic parameters for FRP and many researchers estimated and used different kinetic parameters for the same systems. Another disadvantage of mathematical model for polymerization system is that most available models fail to describe the reactor dynamics in the presence of disturbances [17]. In addition, the complete mathematical model cannot be utilized in control system due to equation complexity and huge computational load. This limitation leads to searching alternative modelling techniques such as data-based or hybrid modelling strategy to describe nonlinear batch reactors [15], [18].
Many studies have shown the importance of data-based modelling techniques to model industrial polymerization processes in the last two decades [19], [20], [21], [22], [23]. The traditional mathematical model cannot describe the kinetic model of FRP properly due to the complex reaction mechanism [17]. In the termination stage of FRP reaction, most of the reactions are neglected in traditional modelling techniques to avoid mathematical complications as well as lack of detailed knowledge of termination reaction behaviour. This limitation can easily be eliminated with the help of data-based modelling. Usually data-based modelling techniques such as neural networks (NNs) are used to model unknown parameters as well as reaction kinetics of FRP.
In a recent study, Noor et al. [17] reviewed the NN application in various polymerization processes. They started from the initial ideas of NNs and described the recent development of NNs for better performance. They also summarized different types of NNs that are used in polymerization systems. These include feed forward NN, staked NN, bootstrap aggregated NN, recurrent NN, internal recurrent NNs, and neural fuzzy networks. NNs can be used to model and describe the nonlinear, complex and unknown parts of the polymerization processes as a standalone model or part of a bigger model. A hybrid model for batch polymerization reactor utilizing artificial NN in mechanistic model is developed by Hosen et al. [15]. They used a NN modelling strategy to describe the complex kinetic parameters. Many similar hybrid applications and NN individual models can be found in the literature for chemical reactors [24], [25], [26], [27], [28], [29].
It is well known that the performance of NNs significantly drops in the presence of large process disturbances [30]. In addition, there is no indication of performance accuracy in traditional NN forecasts. To eliminate these limitations, a new modelling technique, named prediction interval-based NN (PI-NN) model is proposed here for polymerization reactor. In contrast to traditional modelling techniques that just produce point forecasts, this strategy predicts an interval (consists of an upper and lower bound) with a prescribed confidence level (CL). Studies on construction, optimization, and applications of PIs in different fields of science and engineering can be found in the literature [31], [32], [33].
PI-based NNs allow us to quantify uncertainties due to the disturbing presence in non-linear system. Literature has proposed four methods for construction of NN-based PIs. These include bootstrap [34], Bayesian [35], mean-variance estimation [36], and delta methods [37]. Regardless of their implementation differences, the main principle is the same for these four methods. All of these methods use a traditional error-based cost function to train NNs. After developing NN models, PIs are constructed using these trained NNs without changing their structure. It has been argued that the quality of PIs constructed in this way is questionable [38]. In addition, the main strategy of all these methods is to minimize the prediction error, instead of trying to improve the PIs quality (such as PI coverage probability and width).
To effectively cope with these problems Khosravi et al. [38] recently developed another method named lower upper bound estimation (LUBE) to construct PIs. They used a PI-based cost function rather than error-based cost function to train a NN with two outputs. These outputs are the upper and lower bounds of a PI. Moreover, this technique optimizes the NN structure for a particular CL to construct PIs. The PI-based cost function not only increases the PIs coverage probability, but also decreases the PI width to ensure quality PIs.
In the present work, several traditional NNs are developed with and without including disturbances present in the polymerization process system. As NN prediction is poor, mean absolute percentage error (MAPE) > 20% in the presence of disturbances, an extended version of LUBE method is used to generate quality NN-based PIs. Metaheuristic optimization methods, such as simulated annealing (SA) is applied to optimize the PI-based cost function in LUBE method. It is established that NN performance intimately depends on initial parameters as well as perturbation of NN parameters. Due to this, NN prediction performance fluctuates from one replicate of training to the other one. Hence, aggregation of forecasts obtained from a couple of NNs is the best solution for improving forecast accuracies compared to the case of using individual NNs [39]. Many researchers claim that an ensemble of NNs can greatly improve the overall representation accuracy, generalization, and robustness of NN predictions [40], [41]. The effects of a poor prediction from one NN in combined networks is simply minimized by effects of good predictions obtained from the other NNs [24].
As the key contribution of this paper, we extend the concept of forecast aggregation to the field of PI construction. This is done with the purpose of enhancing the quality of PIs constructed using individual NNs in the LUBE method. The arithmetic mean and median are applied as the aggregation tool for developing combined PIs. Firstly, several NNs for the polymerization reactor are developed using the LUBE method to construct PIs for 90% CL. Then, NNs are ranked and shortlisted based on the quality of PIs constructed for the validation set. The performance of the proposed method for generating quality aggregated PIs is compared with the performance of individual NNs for construction of PIs.
The rest of this paper is organized in the following manner. Section 2 briefly describes the PI-NN techniques to model nonlinear system, followed by a discussion about PI-based cost function. The procedure for construction of combined PIs is discussed in Section 3. Section 4 describes the polymerization reactor system and its parameters used in this work. This section also provides the data and parameters used in proposed method. Section 5 demonstrates and discusses the simulation results of the traditional point-based and PI-based NN model. Section 6 concludes the finding in the present study with some future directions.
Section snippets
PI-NN modelling technique
Generally polymerization processes are modelled using mathematical equations by employing mass and energy balance or from experimental data. In the existing literature, three modelling techniques can be found for polymerization system. These include mathematical modelling, data-based modelling, and hybrid modelling techniques. These modelling techniques predict the process outputs with a single value (point forecast). Models may exactly predict the targets, however, they quite often
NN ensemble PIs
Though NNs are popular to model nonlinear processes, they have some limitations in terms of their optimal structure. A trained optimal NN is not always optimal for a whole range of data or for different data sets. Even retraining a NN results in a different set of parameters, as the search space is nonconvex. This is because the NN performance is sensitive to the initial training parameters as well as the perturbation of NN parameters. Moreover, many local minima is present for particular
Polystyrene polymerization system
A polystyrene batch reactor is considered as the case study in this research work. Fig. 3 shows a lab scale batch polymerization reactor system [48]. This is a 2 l glass jacketed reactor. The reactor consists of an agitator motor, heater, thermocouples and reflux condenser. An electric heater is used to heat up the reactor mixture. The heater power can be varied from 0 to 500 W. Jacket with coolant (water) flow is considered to remove excessive heat from the reactor as the polymerization reaction
Traditional neural network
Before developing the prediction interval-based NN, several traditional point forecast-based NNs are developed to evaluate the prediction performance of NN to capture the PS reactor dynamic. Different data sets (with and absence of disturbances) are used to develop traditional point-based NN. Error-based cost function, mean square error (MSE) is used as the cost function to optimize the NN parameters. Levenberg–Marquardt algorithm is applied to minimize the MSE by adjusting the NN parameters
Conclusion
PS polymerization reaction is complex and non-linear in nature. Operation of a real PS plant is highly affected by disturbances making its modelling problematic and prone to large errors. As large prediction errors (MAPE > 20%) of traditional point-based NN model to describe this type of nonlinear model in the presence of process disturbances, PI-based NN modelling technique is proposed and developed in this work. The LUBE method is used to construct PIs. SA global optimization algorithm is
Acknowledgment
This research was fully supported by the Centre for Intelligent Systems Research (CISR) at Deakin University, Australia.
References (66)
- et al.
Modelling of vinylidene fluoride emulsion polymerization
- et al.
Integration of control aspects and uncertainty in the process design of polymerization reactors
Chem Eng J
(2007) - et al.
Development of a multi-scale, multi-phase, multi-zone dynamic model for the prediction of particle segregation in catalytic olefin polymerization FBRs
Chem Eng Sci
(2008) - et al.
Modeling and simulation of an industrial slurry-phase catalytic olefin polymerization reactor series
Chem Eng Sci
(2010) Challenges in particulate polymerization reactor modeling and optimization: a population balance perspective
J Process Control
(2006)Polymerization reactor modeling: a review of recent developments and future directions. chemical Engineering Science
(1996)- et al.
Self-tuning PID control of jacketed batch polystyrene reactor using genetic algorithm
Chem Eng J
(2008) - et al.
Kinetics of styrene free radical polymerisation in the spinning disc reactor
Chem Eng J
(2008) - et al.
Neural network based modelling and control in batch reactor
Chem Eng Res Des
(2006) - et al.
A methodology for modeling batch reactors using generalized dynamic neural networks
Chem Eng J
(2010)
Batch-to-batch optimal control of a batch polymerisation process based on stacked neural network models
Chem Eng Sci
Multi-objective optimization of a stacked neural network using an evolutionary hyper-heuristic
Appl Soft Comput
Inferential estimation of polymer quality using bootstrap aggregated neural networks
Neural Netw
A new selective neural network ensemble method based on error vectorization and its application in high-density polyethylene (HDPE) cascade reaction process
Chin J Chem Eng
Particle swarm optimization for construction of neural network-based prediction intervals
Neurocomputing
Quantifying uncertainties of neural network-based electricity price forecasts
Appl Energy
A neural network-GARCH-based method for construction of prediction intervals
Electric Power Syst Res
Optimal control of batch processes using particle swam optimisation with stacked neural network models
Comput Chem Eng
Performance analysis of three advanced controllers for polymerization batch reactor: an experimental investigation
Chem Eng Res Des
Non-linear generalised predictive control of a jacketed well mixed tank as applied to a batch process – a polymerisation reaction
Appl Therm Eng
Generalized delta rule (GDR) algorithm with generalized predictive control (GPC) for optimum temperature tracking of batch polymerization
Chem Eng Sci
Optimal temperature control in a batch polymerization reactor using fuzzy-relational models-dynamics matrix control
Comput Chem Eng
Control of polystyrene batch reactors using neural network based model predictive control (NN-MPC): an experimental investigation
Control Eng Pract
Designing a neural network for forecasting financial and economic time series
Neurocomputing
Performance of the Levenberg–Marquardt neural network training method in electronic nose applications
Sens Actuators B: Chem
Performance analysis of three controllers for the polymerisation of styrene in a batch reactor
Chem Prod Process Model
Polymerization reactor modeling in industry – an overview of concepts and tools
Macromol Symp
On the mathematical modelling of polymerization reactors
J Macromol Sci: Rev Macromol Chem
Mathematical modeling of dispersion polymerization of methyl methacrylate in supercritical carbon dioxide
Ind Eng Chem Res
Toward the development of a general framework for modeling molecular-weight and compositional changes in free-radical copolymerization reactions
J Macromol Sci: Rev Macromol Chem Phys
Application of experimental non-linear control based on generic algorithm to a polymerization reactor
Korean J Chem Eng
Reactor modeling for polymerization processes
Ind Eng Chem Res
Hybrid modelling and kinetic estimation for polystyrene batch reactor using Artificial Neutral Network (ANN) approach
Asia-Pac J Chem Eng
Cited by (12)
NN-based Prediction Interval for Nonlinear Processes Controller
2021, International Journal of Control, Automation and SystemsFuzzy optimization approach for the synthesis of polyesters and their nanocomposites in in-situ polycondensation reactors
2017, Industrial and Engineering Chemistry ResearchPrediction interval-based controller for Chemical Reactor
2017, Canadian Conference on Electrical and Computer EngineeringPrediction interval with examples of similar pattern and prediction strength
2017, Canadian Conference on Electrical and Computer EngineeringPrediction Interval Estimation Model of User Concurrent Requests for Cloud Service in Cloud Environment
2017, Jisuanji Xuebao/Chinese Journal of Computers
- 1
Tel.: +61 3 5227 1352.