Abstract
In this work, an artificial neural network (ANN) model was developed with the aim of predicting heat transfer coefficient for shell and tube heat exchanger. Using the model, the influence of the control parameter on the accuracy of forecasting was studied. The ANN was designed with two input layers. The first input layer contains historical process data including temperatures and material stream flow rates. The second input layer was supplied with future values of the control parameter. The prediction accuracy was compared with the work of the ANN without the second input layer by two statistical indicators: the mean absolute percentage error (MAPE) and the coefficient of determination (R2). The increase in values is MAPE = 4,0%, R2 = 0,06. The use of this approach improves the results of forecasting and makes it possible to develop an algorithm for selecting the optimal change in the control parameter.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
