Abstract
Shell and tube heat exchangers are essential for many industries, as they allow to control of temperatures in industrial processes. Designing shell and tube heat exchangers is a complex task as they are governed by differential equations and influenced by numerous variables. Calculating the performance of a heat exchanger, based on variables such as the shape, number, and length of tubes, requires solving time-consuming differential equations or using simplified estimates requiring specialist expertise. This paper introduces a novel approach using deep neural networks to predict the required shell and tube heat exchanger variables based on the customer’s required capacities and pressures. This is achieved through two sequential phases: a pre-training on estimated values and, subsequently, a fine-tuning on a smaller dataset comprising measurements collected from real-world products. This method eliminates the need for iterative processes and complex equations, offering faster and accurate predictions. In addition, the paper highlights the phenomenon of "double descent" in neural networks, as it was crucial for optimizing performance. This approach enables companies to customize reliable exchangers efficiently, reducing time and specialist efforts.