Search

[Display omitted] • Demonstrates efficacy of simple linear dynamic models to model hydroprocessing units. • Suggests practitioners to use the right tool depending on the type of data. • Subspace identification for missing data approach generalized to handle missing data in inputs both during training and validation. Hydroprocessing units in petroleum refineries comprise of several complex interconnected network of unit operations, and perform the function of removing impurities from the crude, and cracking it to lighter products for subsequent operations. Modeling these units play a pivotal role in predicting future values of important variables, improving the control and optimization of the plant for efficient operation among several other applications. This paper presents the development and implementation of data-based models in estimating product qualities and other key monitoring variables in the hydroprocessing unit of an industrial refinery. Real industrial data from two different units was used and appropriate data-driven modeling strategies were formulated in order to address this problem. In one instance, the usefulness of Dynamic-Partial Least Squares (DPLS) over Partial Least Squares (PLS) in the estimation of important variables of the unit is demonstrated. In the other instance, subspace identification methodology is found to yield a superior model. The methods used in this study can also elegantly handle the missing data problem associated with real data sets, and thus demonstrate the ability, and the importance of using the right data driven technique for specific problems in the context of hydroprocessing refinery. [ABSTRACT FROM AUTHOR]

• A framework is presented to handle the problem of input data co-linearity in developing recurrent neural network based dynamic models for model predictive control (MPC). • Two specific solutions are developed- one that utilizes a principle component analysis as a pre-processor and another one that imposes specific constraints in the MPC implementation to handle model validity. • A re-identification based technique is developed that allows new training data to be generated that enables a larger range of model validity and improved closed-loop performance. This work addresses one aspect of the overparameterization problem in using artificial/recurrent neural networks (ANN/RNN) based dynamic models for model predictive control (MPC) implementations. The manuscript presents an approach to handle situations where the training data may not be sufficiently rich, and in particular, for handling historical data with correlated inputs. Two approaches are proposed. The key idea in the first method is to perform principal component analysis (PCA) on input space and then utilize the scores to build a PCA-RNN model. Next, a PCA-RNN-based MPC is designed to compute the optimal values of scores and subsequently determined the manipulated inputs. An alternative solution is proposed in the second approach by proposing a new constraint on squared prediction error (SPE) statistic in the RNN-based MPC to make prescribed inputs follow the PCA model constructed for training input data. Finally, an approach is presented that allows to break the correlation in the MPC implementation while maintaining model validity. This is done by first generating richer closed-loop data by implementing the SPE based MPC with slightly relaxed constraints (thus compromising only slightly on the closed loop performance). Then the new data is utilized to re-identify the model, and for use in the MPC. The efficacy of the proposed approaches to handle the problem of set-point tracking is evaluated using a chemical reactor example. The results are compared with a nominal MPC design, and the superior performance under the proposed formulations demonstrated. [ABSTRACT FROM AUTHOR]