Intelligent Approach for Fouling Detection in Phase Change Heat Exchanger

Fouling is the formation of unwanted material deposits on heat transfer equipment's inner surfaces during process heating and cooling, which leads to a reduction of the efficiency of the system and environmental effects. Because of this, fouling analysis becomes a very significant study topic for an effective and safe operation. It is challenging to analyze fouling when there is a phase change of fluids during heat transfer, such as in condensers and boilers, which are crucial units in industrial facilities. Machine learning algorithms have proven their reliability and robustness in different aspects of the industry. In this research, we propose an intelligent data-driven model to predict the location of the fouling given transient data like the rate of change of outlet temperature. Two scenarios were tested to predict fouling in a heat exchanger: one with uniform fouling in two segments and another with three fouling locations. Both models achieved a prediction accuracy of over 99%, indicating powerful prediction performance in fouling localization.