EventFlow: Real-Time Neuromorphic Event-Driven Classification of Two-Phase Boiling Flow Regimes

2025-11-07

AI Summary

Traditional optical imaging methods suffer from poor real-time performance and high computational latency in two-phase boiling flow pattern identification. To address this, we propose EventFlow—the first event-driven classification framework specifically designed for boiling flow regime recognition. EventFlow leverages neuromorphic event cameras to capture dynamic flow boundary changes with microsecond-level temporal resolution, eliminating the need for full-frame reconstruction. It enables continuous, low-latency prediction via asynchronous event stream processing and a sliding-window majority-voting mechanism. Our custom event-driven LSTM model achieves 97.6% classification accuracy while requiring only 0.28 ms per inference—over two orders of magnitude faster than frame-based approaches. This marks the first demonstration of millisecond-level online boiling flow regime identification, establishing a new paradigm for real-time perception in intelligent thermal management under high-heat-flux conditions.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Flow boiling is an efficient heat transfer mechanism capable of dissipating high heat loads with minimal temperature variation, making it an ideal thermal management method. However, sudden shifts between flow regimes can disrupt thermal performance and system reliability, highlighting the need for accurate and low-latency real-time monitoring. Conventional optical imaging methods are limited by high computational demands and insufficient temporal resolution, making them inadequate for capturing transient flow behavior. To address this, we propose a real-time framework based on signals from neuromorphic sensors for flow regime classification. Neuromorphic sensors detect changes in brightness at individual pixels, which typically correspond to motion at edges, enabling fast and efficient detection without full-frame reconstruction, providing event-based information. We develop five classification models using both traditional image data and event-based data, demonstrating that models leveraging event data outperform frame-based approaches due to their sensitivity to dynamic flow features. Among these models, the event-based long short-term memory model provides the best balance between accuracy and speed, achieving 97.6% classification accuracy with a processing time of 0.28 ms. Our asynchronous processing pipeline supports continuous, low-latency predictions and delivers stable output through a majority voting mechanisms, enabling reliable real-time feedback for experimental control and intelligent thermal management.

Problem

• Real-time monitoring of flow regime transitions in boiling systems
• Overcoming limitations of conventional optical imaging methods
• Developing low-latency classification using neuromorphic event-based data

Innovation

• Neuromorphic sensors detect brightness changes for motion detection
• Event-based LSTM model achieves high accuracy and speed
• Asynchronous processing enables continuous low-latency predictions