Review and classification of recent observers applied in chemical process systems

Intensive review of AI applied as estimators in chemical process systems.Provide guidelines to select and design AI-based estimators.Discussed the advantages, limitations and compare each algorithm.Future suggestions and directions of the research. The versatility of Artificial Intelligence (AI) in process systems is not restricted to modelling and control only, but also as estimators to estimate the unmeasured parameters as an alternative to the conventional observers and hardware sensors. These estimators, also known as software sensors have been successfully applied in many chemical process systems such as reactors, distillation columns, and heat exchanger due to their robustness, simple formulation, adaptation capabilities and minimum modelling requirements for the design. However, the various types of AI methods available make it difficult to decide on the most suitable algorithm to be applied for any particular system. Hence, in this paper, we provide a broad literature survey of several AI algorithms implemented as estimators in chemical systems together with their advantages, limitations, practical implications and comparisons between one another to guide researchers in selecting and designing the AI-based estimators. Future research suggestions and directions in improvising and extending the usage of these estimators in various chemical operating units are also presented.

Artificial Intelligence techniques applied as estimator in chemical process systems - A literature survey

Machine learning has attracted extensive interest in the process engineering field, due to the capability of modeling complex nonlinear process behavior. This work presents a method for combining neural network models with first-principles models in real-time optimization (RTO) and model predictive control (MPC) and demonstrates the application to two chemical process examples. First, the proposed methodology that integrates a neural network model and a first-principles model in the optimization problems of RTO and MPC is discussed. Then, two chemical process examples are presented. In the first example, a continuous stirred tank reactor (CSTR) with a reversible exothermic reaction is studied. A feed-forward neural network model is used to approximate the nonlinear reaction rate and is combined with a first-principles model in RTO and MPC. An RTO is designed to find the optimal reactor operating condition balancing energy cost and reactant conversion, and an MPC is designed to drive the process to the optimal operating condition. A variation in energy price is introduced to demonstrate that the developed RTO scheme is able to minimize operation cost and yields a closed-loop performance that is very close to the one attained by RTO/MPC using the first-principles model. In the second example, a distillation column is used to demonstrate an industrial application of the use of machine learning to model nonlinearities in RTO. A feed-forward neural network is first built to obtain the phase equilibrium properties and then combined with a first-principles model in RTO, which is designed to maximize the operation profit and calculate optimal set-points for the controllers. A variation in feed concentration is introduced to demonstrate that the developed RTO scheme can increase operation profit for all considered conditions.

/pdf/real-time-optimization-and-control-of-nonlinear-processes-22ymo4gfs1.pdf

Real-Time Optimization and Control of Nonlinear Processes Using Machine Learning

In this paper, prediction interval (PI)-based modelling techniques are introduced and applied to capture the nonlinear dynamics of a polystyrene batch reactor system. Traditional NN models are developed using experimental datasets with and without disturbances. Simulation results indicate that traditional NNs cannot properly handle disturbances in reactor data and demonstrate a poor forecasting performance, with an average MAPE of 22% in the presence of disturbances. The lower upper bound estimation (LUBE) method is applied for the construction of PIs to quantify uncertainties associated with forecasts. The simulated annealing optimization technique is employed to adjust NN parameters for minimization of an innovative PI-based cost function. The simulation results reveal that the LUBE method generates quality PIs without requiring prohibitive computations. As both calibration and sharpness of PIs are practically and theoretically satisfactory, the constructed PIs can be used as part of the decision-making and control process of polymerization reactors.

Prediction interval-based neural network modelling of polystyrene polymerization reactor – A new perspective of data-based modelling

Precise and reliable modelling of polymerization reactor is challenging due to its complex reaction mechanism and non-linear nature. Researchers often make several assumptions when deriving theories and developing models for polymerization reactor. Therefore, traditional available models suffer from high prediction error. In contrast, data-driven modelling techniques provide a powerful framework to describe the dynamic behaviour of polymerization reactor. However, the traditional NN prediction performance is significantly dropped in the presence of polymerization process disturbances. Besides, uncertainty effects caused by disturbances present in reactor operation can be properly quantified through construction of prediction intervals (PIs) for model outputs. In this study, we propose and apply a PI-based neural network (PI-NN) model for the free radical polymerization system. This strategy avoids assumptions made in traditional modelling techniques for polymerization reactor system. Lower upper bound estimation (LUBE) method is used to develop PI-NN model for uncertainty quantification. To further improve the quality of model, a new method is proposed for aggregation of upper and lower bounds of PIs obtained from individual PI-NN models. Simulation results reveal that combined PI-NN performance is superior to those individual PI-NN models in terms of PI quality. Besides, constructed PIs are able to properly quantify effects of uncertainties in reactor operation, where these can be later used as part of the control process.

Prediction interval-based modelling of polymerization reactor: A new modelling strategy for chemical reactors

A novel Structure Approaching Hybrid Neural Network (SAHNN) approach to model batch reactors is presented. The Virtual Supervisor−Artificial Immune Algorithm method is utilized for the training of SAHNN, especially for the batch processes with partial unmeasurable state variables. SAHNN involves the use of approximate mechanistic equations to characterize unmeasured state variables. Since the main interest in batch process operation is on the end-of-batch product quality, an extended integral square error control index based on the SAHNN model is applied to track the desired temperature profile of a batch process. This approach introduces model mismatches and unmeasured disturbances into the optimal control strategy and provides a feedback channel for control. The performance of robustness and antidisturbances of the control system are then enhanced. The simulation result indicates that the SAHNN model and model-based optimal control strategy of the batch process are effective.

X. Guang Li

Papers

Dynamic Modeling and Optimal Control of Batch Reactors, Based on Structure Approaching Hybrid Neural Networks