Affiliation:
1. College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
Abstract
Aimed at the detection difficulty of local abnormal signals during pipeline operation, this paper takes the local abnormal signals as the detected targets, and proposes a new method based on target detection to extract abnormal signals with different amplitude and shape; and for the case where there are few actual leak samples, combined with the characteristics that the training samples of each module of the model itself are derivative samples of the original sample, so as to realize the small sample training of the model. Finally, a new pipeline leak detection and location method is proposed by combining the 1D-faster R-CNN with the cross-correlation location method based on signal matching. The experimental results show that the proposed method effectively extracts local abnormal signals, accurately alarms leak signals, and eliminates the false alarms caused by the recognition errors of normal signals.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. YOLO-PD: Abnormal Signal Detection in Gas Pipelines Based on Improved YOLOv7;IEEE Sensors Journal;2023-09-01
2. Pipeline Leakage Detection Method Based on Convolutional Neural Network;2023 International Conference on Advances in Electrical Engineering and Computer Applications (AEECA);2023-08-18