Work

Identification and diagnosis of flow instability in parallel channel systems using machine learning

Year: 2026

Type: article

Abstract: Density wave oscillations in parallel thermal-fluid systems threaten operational safety due to uneven flow and instability. Predicting these oscillations is a critical challenge for both forced and natural circulation systems. Here, we demonstrate an intelligent framework that accurately identifies such hazardous states. We combine numerical modeling of open and closed circulation systems with a hybrid method integrating Genetic Algorithm (GA) optimization and K-Nearest Neighbors (KNN) classification. For open systems, we map oscillation patterns across a wide operational space. For closed systems, we efficiently pinpoint DWO-sensitive regions. Our results show that the flow state recognition method, validated against manual and signal analysis, achieves an overall accuracy of 99.19%. Furthermore, GA-optimization of the KNN model achieved 96.4-100% accuracy with superior blind-test generalization, while spatial non-uniformity of heat load distribution critically governs instability patterns, informing differentiated safety strategies. This confirms the framework’s effectiveness and reliability for practical engineering applications. Cheng Peng and colleagues report an intelligent framework that identifies flow oscillations in parallel thermal-fluid systems. The method enables prediction of negative states in open and closed circulation for safer engineering design and operation.

Source: Communications Engineering

DOI: 10.1038/s44172-026-00690-9

Authors: Cheng Peng, Xingchen Wang, Runxin Tian, Jiang Wu, Jian Deng

Institutions: Shanghai University of Electric Power, Nuclear Power Institute of China

Language: English

Topic: Nuclear Engineering Thermal-Hydraulics

Subfield: Aerospace Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $2,190