Characterization of transient differential pressure signal features and flow pattern identification in horizontal two-phase flow through a constriction with machine learning models

A new study titled "Characterization of transient differential pressure signal features and flow pattern identification in horizontal two-phase flow through a constriction with machine learning models" (DOI 10.1016/j.flowmeasinst.2025.102985) was published in July 2025 in the Flow Measurement and Instrumentation (Impact Factor 2.7) journal, volume 106, article 102985. The article was obtained through a collaboration between our program and the Federal University of Santa Catarina. We congratulate the authors, Tiago Francisconi Borges Camargo and Emilio Paladino, on their article, which addresses experimental development and artificial intelligence.

This work is one of the first to combine transient pressure signals with machine learning techniques for classifying flow regimes in industrial and laboratory systems. The application of these techniques can lead to more accurate and automated monitoring, with the potential to optimize processes in sectors such as oil and gas, wastewater treatment, and refrigeration systems.

The article can be found at https://www.sciencedirect.com/science/article/pii/S0955598625001773