Vision-Ultrasound Robotic System based on Deep Learning for Gas and Arc Hazard Detection in Manufacturing

TL;DR

This paper introduces a deep learning-based robotic system that combines visual and ultrasonic acoustic sensing to detect and classify gas leaks and arc discharges in manufacturing environments, enhancing safety and operational efficiency.

Contribution

It presents a novel integrated vision-acoustic robotic system capable of onboard hazard detection and classification with high accuracy and real-time performance in complex industrial settings.

Findings

Achieved 99% accuracy in gas leak detection.

Outperformed conventional models by up to 44% in noisy environments.

Maintains real-time inference at 2.1 seconds on a mobile platform.

Abstract

Gas leaks and arc discharges present significant risks in industrial environments, requiring robust detection systems to ensure safety and operational efficiency. Inspired by human protocols that combine visual identification with acoustic verification, this study proposes a deep learning-based robotic system for autonomously detecting and classifying gas leaks and arc discharges in manufacturing settings. The system is designed to execute all experimental tasks entirely onboard the robot. Utilizing a 112-channel acoustic camera operating at a 96 kHz sampling rate to capture ultrasonic frequencies, the system processes real-world datasets recorded in diverse industrial scenarios. These datasets include multiple gas leak configurations (e.g., pinhole, open end) and partial discharge types (Corona, Surface, Floating) under varying environmental noise conditions. Proposed system integrates visual detection and a beamforming-enhanced acoustic analysis pipeline. Signals are transformed using STFT and refined through Gamma Correction, enabling robust feature extraction. An Inception-inspired CNN further classifies hazards, achieving 99% gas leak detection accuracy. The system not only detects individual hazard sources but also enhances classification reliability by fusing multi-modal data from both vision and acoustic sensors. When tested in reverberation and noise-augmented environments, the system outperformed conventional models by up to 44%p, with experimental tasks meticulously designed to ensure fairness and reproducibility. Additionally, the system is optimized for real-time deployment, maintaining an inference time of 2.1 seconds on a mobile robotic platform. By emulating human-like inspection protocols and integrating vision with acoustic modalities, this study presents an effective solution for industrial automation, significantly improving safety and operational reliability.