| description abstract | The advancement of machine learning offers a promising solution for diagnosing both the extent of leakage and the precise location of natural gas transmission pipeline leaks. While pipeline leaks often manifest through sound-related signals, leveraging machine learning for signal classification is still in its nascent stages. We propose a hybrid technological approach for detecting and pinpointing gas pipeline leaks, which is rooted in machine learning principles. In this paper, we simulate and classify the degree of pipe-line leakage by adjusting the bolt aperture. We analyze and select original data acquired through acquisition and processing using eigenvalue methods. Subsequently, we employ a deep learning algorithm for training and testing the data post feature extraction, enabling the realization of pipeline leakage diagnosis and classification. To fully leverage the information embedded in the original data, we adopt the radial basis function neural network (RBF-NN) machine learning technique. Moreover, we utilize the genetic algorithm (GA) for optimization, resulting in the generation of a radial basis function neural network model (GA-RBF) optimized through genetic algorithmic techniques. We compare the predictive performance of the GA-RBF model with that of BP-NN and RBF-NN. The diagnostic F1 scores of the GA-RBF model under various operational conditions of gas pipelines are as follows: 98.30%, 97.50%, 95.10%, and 95.80%, respectively, with an overall accuracy of 96.68%. The diagnostic outcomes align well with theoretical expectations, demonstrating the superior performance of the GA-RBF model in gas pipe-line leakage diagnosis. | |
