Artificial Intelligence-Based Performance Maps for Expander-Compressor Analysis in Energy Transition Applications

Limiting the global warming impact requires a drastic reduction of greenhouse gas emissions (GHG) to reach a zero-carbon growth by 2050. Against this backdrop, turbomachinery designers are asked to develop more compact, efficient, and reliable machines. So, improving the power plants efficiency and operability. the research focuses on developing machines able to reduce energy losses, thus improving power plants efficiency. To this end, expander-compressors (EC) seem to play a key role in the energy transition and appear promising for high-density plants, especially together with hydrogen (H2) or supercritical carbon dioxide (sCO2) as working fluid. However, a degradation in performance may be expected with slightly changes in operating condition thus reducing the machine efficiency. Industry requires a fast and reliable way in order to assess the operating point of the machine while facing changes in the operating conditions. Although the scientific literature shows several studies on mean-line approaches for expanders and centrifugal compressors, the joint use of 1D models with artificial neural networks (ANN) for a real-time monitoring of ECs is still overlooked. To fill this gap, Artificial Intelligence-based performance maps are here proposed. The tool has been tested on a case study based on a real EC. Results showed a rapid monitoring of EC efficiency while varying the operating conditions.