Session: CT-19-01 AI, Data Engineering and Data Analysis-1

Paper Number: 154514

154514 - A Novel Method for Identification of Pipeline Stress Concentration Segment Based on Acsm and Imu In-Line Inspection Data 

Abstract: 

Pipeline stress concentration is a major factor leading to pipeline failure, often causing deformation and cracking, which further results in structural damage and secondary hazards such as oil and gas leakage. Therefore, accurately identifying stress concentration segments is crucial for ensuring the safe operation of pipelines. Currently, the widely used Inertial Measurement Unit (IMU) in-line inspection technology in engineering primarily focuses on bending strain analysis and struggles to identify stress concentration segments caused by longitudinal loads and local defects. The recent developed AC electromagnetic field Stress Measurement (ACSM) technology make it possible to derive the pipe axial stress directly, but there is few research focus to the in-depth data analysis. To address this, an intelligent classification algorithm based on deep learning models is proposed for the identification and classification of stress concentration segments based on both IMU and ACSM ILI data. ACSM and IMU data features of the pipe stress concentration segments marked by Magnetic Flux Leakage data and experts were extracted. Setting these extracted data as input, a deep learning model algorithm Transformer was trained to identify the stress concentration segments. A 30 km long gas pipeline was considered as an application object, the feasibility of the  model is evaluated and verified using multiple metrics, including accuracy, precision, recall, and F1 score. This research provides technical support and guidance for pipeline integrity assessment based on multi-source in-line inspection data.

Keywords: pipeline inline inspection, AC electromagnetic field Stress Measurement data; Inertial Measurement Unit data ; Deep Learning; Stress Concentration Segment Identification

Presenting Author: Mengkai Fu National Engineering Research Center for Pipeline Safety/MOE Key Laboratory of Petroleum Engineering/Beijing Key Laboratory of Urban Oil and Gas Distribution Technology, China University of Petroleum-Beijing, Beijing, 102249, China

Presenting Author Biography: A student major in oil and gas storage and transportation engineering, China University of Petroleum, Beijing

Authors:

Mengkai Fu National Engineering Research Center for Pipeline Safety/MOE Key Laboratory of Petroleum Engineering/Beijing Key Laboratory of Urban Oil and Gas Distribution Technology, China University of Petroleum-Beijing, Beijing, 102249, China
Jiaying Yu National Engineering Research Center for Pipeline Safety/MOE Key Laboratory of Petroleum Engineering/Beijing Key Laboratory of Urban Oil and Gas Distribution Technology, China University of Petroleum-Beijing, Beijing, 102249, China
Lei Guo National Engineering Research Center for Pipeline Safety/MOE Key Laboratory of Petroleum Engineering/Beijing Key Laboratory of Urban Oil and Gas Distribution Technology, China University of Petroleum-Beijing, Beijing, 102249, China
Kuan Fu National Engineering Research Center for Pipeline Safety/MOE Key Laboratory of Petroleum Engineering/Beijing Key Laboratory of Urban Oil and Gas Distribution Technology, China University of Petroleum-Beijing, Beijing, 102249, China
Pengchao Chen National Engineering Research Center for Pipeline Safety/MOE Key Laboratory of Petroleum Engineering/Beijing Key Laboratory of Urban Oil and Gas Distribution Technology, China University of Petroleum-Beijing, Beijing, 102249, China
Xiaoben Liu National Engineering Research Center for Pipeline Safety/MOE Key Laboratory of Petroleum Engineering/Beijing Key Laboratory of Urban Oil and Gas Distribution Technology, China University of Petroleum-Beijing, Beijing, 102249, China