Data-driven systematic methodology for predicting optimal heat pump integration based on temperature levels and refrigerants

Abstract

In the context of the industrial shift towards carbon neutrality and electrification, high temperature heat pumps have emerged as feasible solutions for decarbonizing the heat supply at temperatures previously associated only to fired or resistive heating technologies (>100°C). The integration of high temperature heat pumps into industrial processes reduces the cooling and heating demand, while it capitalizes on the waste heat, which eventually enhances the overall energy efficiency. However, a heat pump device typically interacts with other competing energy systems, such as fired boilers and electric heaters. This renders the synthesis, design and optimization more complex. Moreover, the characterization of the grand composite curve of the industrial process is necessary to select the best levels of temperatures and refrigeration fluids that minimize the total operating cost of the systems. Mixed integer nonlinear programming approaches can be used to optimize the integration of a heat pump superstructure into any type of grand composite curve, bearing in mind economic and thermodynamic constraints. However, these problems are challenging to solve particularly as computational limitations become evident with larger problem sizes. Since the grand composite curve is a representation of the amount and temperature of the waste heat available through the industrial process, supervised machine learning techniques can be used, as a preprocessing step, to train and automate the selection of the best heat pump configurations based on the characteristics of that curve, instead of relying only on the expertise of the engineer. In other words, the model developed can identify distinctive patterns within the grand composite curve that influence the selection of specific heat pump structures and parameters. This approach streamlines the selection of temperature levels and refrigerant fluids, enhancing the efficiency and ease of the decision-making process. As a result, energy savings up to 60% are found in a case study if a set of heat pump technologies is optimally designed and integrated.