Published Paper Details:

Heat exchangers are essential equipment in a wide variety of industrial processes, and they are a central component of such industries as power generation, petrochemical and chemical processing, and heating, ventilation, and air conditioning (HVAC) systems. The equipment enables efficient transfer of thermal energy from fluids, and it is therefore crucial to the operational efficiency and energy economy of most processes. But as the equipment operates continuously day and night over extended periods, their efficiency declines steadily. Fouling is one of the main reasons for this decline--a process in which unwanted substances such as scale, biological material, or corrosion products precipitate out of solution and accumulate on the inner surfaces of heat exchangers. The main aim of this project is to develop and implement a predictive maintenance system for heat exchangers with particular emphasis on machine learning algorithms. The system uses several machine learning approaches, including Support Vector Machines (SVM), Artificial Neural Networks (ANN), and hybrid models utilizing SVM and Particle Swarm Optimization (PSO). The algorithms are created to simulate and predict fouling behavior under different operating conditions effectively.