Neural model for forecasting temperature in a distribution network of cooling water supplied to systems producing petroleum products

This article presents the application of a neural model of heat transfer for the purpose of forecasting temperature at selected points of a circulating water ring network. The purpose of a circulating water system is to lower the temperature of petroleum products manufactured on numerous petrochemical lines at a Polish petrochemical plant. Temperature forecasting at 96 nodes of the circulating water system, significant from the point of view of system operation, is carried out using SVM neural networks. Neural networks learn based on archival data recorded in the process parameter monitoring system. Thermal, hydraulic and control parameters of the cooling process, as well as weather variables, constitute crucial input data for the neural model. The temperature forecasting algorithm has been implemented in a computer program that was then applied and remains in use for temperature forecasting in a maintenance department of an industrial plant.