The quantitative analysis of dispersed phases (bubbles, droplets, and particles) in multiphase flow systems represents a persistent technological challenge in petroleum engineering applications, including CO₂-enhanced oil recovery, foam flooding, and unconventional reservoir development. Current characterization methods remain constrained by labor-intensive manual workflows and limited dynamic analysis capabilities, particularly for processing large-scale microscopy data and video sequences that capture critical transient behavior like gas cluster migration and droplet coalescence. These limitations hinder the establishment of robust correlations between pore-scale flow patterns and reservoir-scale production performance. This study introduces a novel computer vision framework that integrates foundation models with lightweight neural networks to address these industry challenges. Leveraging the segment anything model's zero-shot learning capability, we developed an automated workflow that achieves an efficiency improvement of approximately 29 times in bubble labeling compared to manual methods while maintaining less than 2% deviation from expert annotations. Engineering-oriented optimization ensures lightweight deployment with 94% segmentation accuracy, while the integrated quantification system precisely resolves gas saturation, shape factors, and interfacial dynamics, parameters critical for optimizing gas injection strategies and predicting phase redistribution patterns. Validated through microfluidic gas–liquid displacement experiments for discontinuous phase segmentation accuracy, this methodology enables precise bubble morphology quantification with broad application potential in multiphase systems, including emulsion droplet dynamics characterization and particle transport behavior analysis. This work bridges the critical gap between pore-scale dynamics characterization and reservoir-scale simulation requirements, providing a foundational framework for intelligent flow diagnostics and predictive modeling in next-generation digital oilfield systems.

The identification and recording of drilling conditions are crucial for ensuring drilling safety and efficiency. However, the traditional approach of relying on the subjective determination of drilling masters based on experience formulas is slow and not suitable for rapid drilling. In this paper, we propose a drilling condition classification method based on a neural network model. The model uses an improved Bidirectional Gated Recurrent Unit (BiGRU) combined with an attention mechanism to accurately classify seven common drilling conditions simultaneously, achieving an average accuracy of 91.63%. The model also demonstrates excellent generalization ability, real-time performance, and accuracy, making it suitable for actual production. Additionally, the model has excellent expandability, which enhances its potential for further application.