Applying Convolutional Neural Networks to Detect Natural Gas Leaks in Wellhead Images

Abstract

Detecting natural gas leaks is one of the most important measures in the oil industry for preventing accidents. The literature provides different techniques for detecting natural gas leaks. However, except for previous studies by the authors on this topic, there remains a gap in the literature on leak detection of natural gas using digital images, without the need for sensors or special cameras calibrated for the spectrum of methane molecules. These previous studies used image-processing techniques associated with a novelty filter classifier to detect the presence or absence of visible cloud of hydrocarbon vapors, that is, a natural gas plume in Closed Circuit Television (CCTV) frames installed in onshore wellheads. In this paper, we present a new method for detecting natural gas leaks in oil facilities that enhances the results obtained previously, along with the Gradient-weighted Class Activation Mapping Algorithm (Grad-CAM) to identify natural gas leaks. In this new method, convolutional neural networks (CNN) are applied to classify images (CCTV frames) as belonging to classes with or without natural gas leaks in onshore wellheads. Experimental results showed that the best performance model presented an accuracy of 99.78% and false negative rate of 0.00%.

Development of an AI-based image/ultrasonic convergence camera system for accurate gas leak detection in petrochemical plants

“…Wang et al [ 68 ] used optical gas imaging (OGI) along with a convolutional neural network (CNN) to detect gas leakage from an image. Similarly, Melo et al [ 69 ] proposed the use of normal closed-circuit camera (CCTV) videos for gas-leak classification. These CNN-based approaches only classify gas leaks.…”

Multi-scene pipeline leakage video detection based on C3D-RF with TRCE loss joint supervision method

“…Then they used LSTM to model the change trend of each possible local area, so as to realize the pipeline oil leakage detection. For natural gas leakage detection in wellhead scenes, R.O.Melo et al [8] proposed a convolution neural network (CNN), which could effectively realize natural gas warning. They used the gradientweighted class activation mapping algorithm to identify the location of the leakage natural gas in the original image.…”

Advanced Computer Vision-Based Subsea Gas Leaks Monitoring: A Comparison of Two Approaches

“…Previous works have pointed out that the convolutional neural network (CNN) is capable of effectively extracting the spatial features of image datasets and accurately learning these features. Therefore, for industrial anomaly detection, researchers have proposed many automatous and intelligent methods for real-time anomaly detection, such as natural gas leak detection [35,36], machine fault detection [37,38], and structure crack detection [39,40]. These works realize the automatic detection of anomaly events without manual intervention, which greatly improves the effectiveness and accuracy of anomaly detection.…”