Multi-condition pipeline leak diagnosis based on acoustic image fusion and whale-optimized evolutionary convolutional neural network

This study proposes a multi-condition pipeline leak diagnosis method that utilizes pixel-level image fusion and an evolutionary convolutional neural network enhanced by the whale optimization algorithm. Firstly, the traditional one-dimensional leakage time series are transformed into two-dimensional acoustic images, which contain richer information. The signal characteristics, as well as the advantages and disadvantages of different image conversion methods, are compared and analyzed. Secondly, given that a single acoustic image conversion method struggles to achieve effective diagnostics across various working conditions, this study employs two pixel-level image fusion techniques: the principal component transformation method (PCA) and the Intensity-Hue-Saturation (IHS) method, to conduct a comparative study. The results indicate that the diagnostic performance of the fusion methods surpasses that of the unfused acoustic image conversion method, with the IHS method proving to be more suitable for pipeline leakage detection scenarios. In addition, to enhance the accuracy and robustness of pipeline leak detection under varying conditions, a Whale Optimized Evolutionary Convolutional Neural Network model (WOA-ECNN) has been developed for leak diagnosis research. The model was tested under five working conditions (two types of no leakage, 1 mm leakage, 3 mm leakage, and 5 mm leakage). The results demonstrate that the proposed pixel-level fusion method can accurately identify and differentiate between leakage and non-leakage states. Furthermore, multiple performance indicators show superior results compared to the single acoustic image conversion method. In addition, the diagnostic accuracy of the ECNN model, enhanced by whale optimization (WOA-ECNN), is significantly higher than that of the traditional CNN model.