Modeling and simulation of multi-stream heat exchanger using artificial neural network
MetadataShow full item record
A multi-stream heat exchanger (MSHE) is the heart of LNG plant where 40% of the entire energy is consumed in this section. Moreover, the plant operation is subject to number of variations from the plant inlet such as ambient temperature, pressure, feed flow or composition. In industrial application, the mitigating of these variations is usually performed using trial and error approaches. Thus developing a competent and accurate model to predict the performance of the MSHE is an inevitable step to overcome those variations. In this study, a model for the MSHE operation is developed using artificial neural network. The modeling is made in such a way that the information about the internals of heat exchanger could allow the MSHEs from any variation that arises from the process itself or upstream conditions. A number of simulation runs have been made by taking a case study for the MSHE operation. The developed model can predict and provide prior information for the MSHE in order to take action during the plant performance.
Showing items related by title, author, creator and subject.
Computational analysis of two-phase flow and heat transfer in parallel and counter flow double-pipe evaporatorsAbishek, Sridhar; King, Andrew; Narayanaswamy, Ramesh (2017)A computational study is carried out to compare the two-phase flow and heat transfer characteristics of a double-pipe evaporator operating under parallel and counter flow configurations for use in waste heat recovery and ...
Jung, Hyung-Chul; Krumdieck, S. (2014)Numerical models of a standard organic Rankine cycle (ORC) system and the heat exchangers comprising the system are developed as a design tool platform for a flexible design. The objective is design of an efficient, ...
Fung, C.; Sedev, Rossen; Connor, J. (2014)The affinity between a liquid and a solid is characterised by the contact angle. Traditional contact angle measurement techniques such as the sessile drop and Wilhelmy plate methods provide macroscopic information about ...