Real-Time Identification of Natural Gas Pipeline Leakage Apertures Based on Lightweight Residual Convolutional Neural Network
Xiufang Wang, Yuan Liu, Chunlei Jiang, Yueming Li, Hongbo Bi
Abstract
Deep-learning techniques have been widely used in pipeline leakage aperture identification. However, most are designed and implemented for offline data, with problems such as large parameters, high memory consumption, and poor noise immunity. To solve the problem, this article presents a lightweight residual convolutional neural network (L-Resnet) applied to a real-time detection platform to achieve real-time identification of pipeline leakage apertures. First, based on the depth separable technique, two different separable residual modules are constructed to realize the feature extraction of signals; then, a more efficient activation function is applied to the high-dimensional space to enhance the nonlinear capability of the model; after that, a lightweight attention mechanism is used to weight the features to distinguish the importance of different features; finally, the classification results are obtained by a classifier. The real-time detection platform consists of Jetson Nano, the signal acquisition module, and the processing circuit. The results indicated that the method could accurately identify the pipeline leakage apertures in real time. Moreover, the number of parameters is only 14.71 kb, and the model has good computing efficiency and robustness compared to other methods.