| In the field of petroleum,pipelines are widely used to transport oil.Due to natural factors,human factors and other factors,it is very easy to cause oil leakage in pipeline transportation.The loss and harm caused by the leakage of the oil pipeline make people have to pay attention to the detection of the leakage of the oil pipeline.Therefore,the research of oil pipeline leakage detection technology has become a hot spot of research in both domestic and foreign industry and academia.At present,there are mature methods for leak detection of oil pipeline,but with the development of industrial technology,the accuracy of oil pipeline leak detection is also increasing.Therefore,the detection technology of oil pipeline leakage is put forward higher request.In this paper,firstly,the pipeline signal is decomposed and reconstructed by 3-layer wavelet and denoised.Then,the data is extracted and processed.The processed data is input into the BP neural network and simulated using MATLAB.The detection accuracy rate is 95.9%.Secondly,a deep learning model of pipeline leak detection is built based on stack self-coding network.This method takes raw data as input,and directly extracts the characteristics of pipeline data from low level to high level.In this paper,the depth learning model of 3,4 and 5 layers is constructed respectively for simulation experiments.Finally,the accuracy rate of detecting pipeline leakage in the deep learning model of 5 layers is up to 97.7%.The multi-layer deep learning oil pipeline leak detection model implemented in this paper uses empirical values of the parameters of each layer,and the weight parameters in training process need further optimization.The detection of data with complex background and invisible leakage of pipeline needs to be studied in depth. |
