Development of an industry-applicable two-phase flow regime identification approach using flow-induced vibration acceleration signals

Accurate classification of two-phase flow regimes is essential for optimizing industrial pipeline operations and ensuring system safety. Flow-induced vibration (FIV) signals present a promising option for developing flow regime classifiers due to the non-intrusiveness and accessibility of force/acceleration sensors. However, conventional FIV measurement and classification approaches often suffer from the database’s limited representativeness and necessitate complex feature engineering, thereby impeding their practical application in industrial systems. This study proposes a novel methodology that integrates a specialized experimental setup with an end-to-end one-dimensional convolutional neural network (1D-CNN) to effectively classify two-phase flow regimes using FIV acceleration signals. Firstly, a more representative FIV acceleration database was constructed by a tightly fixed 90-degree elbow section, thereby ensuring that induced vibrations are predominantly attributable to two-phase flow rather than structural resonance. Leveraging this database, a multi-channel 1D-CNN model was developed, capable of autonomously extracting temporal patterns from high-frequency FIV signals without the necessity for extensive feature engineering. The model architecture incorporates an adaptive average pooling layer and is optimized through a Bayesian framework to enhance both computational efficiency and classification performance. Comprehensive evaluations using metrics such as precision, recall, accuracy, and F1-score demonstrate that the proposed 1D-CNN model surpasses feature-based methods. An average classification accuracy of 89.9% was achieved across all flow regimes. Notably, the model demonstrated superior capability in distinguishing bubbly and slug flow regimes, achieving precisions of 97.2% and 91.7% and recalls of 94.6% and 89.8%, respectively. Furthermore, visualization analysis of the proposed model further reveals that convolutional kernels with varying degrees of smoothness and symmetry effectively capture dominant frequency patterns. This work not only advances the accuracy and efficiency of two-phase flow regime classification but also establishes a robust foundation for future research aimed at broadening the applicability of deep learning models in complex industrial settings involving two-phase flows. • An industry-applicable two-phase flow regime identification method is developed. • Feature-based and 1D convolution-based machine learning schemes are compared. • The modified 1D-CNN achieves end-to-end and more accurate flow regime identification. • The interpretability of 1D-CNNs for extracting features from signals is investigated.