Session: 06-04-01 Strain Capacity

Paper Number: 134223

134223 - A Novel Strain Capacity Prediction Model of Girth Welded Joints of High-Grade Steel Pipeline Via Machine Learning Techniques and Refined FE Model 

Abstract: 

Abstract: In recent years, incidents of fracture failure in girth welds of high-grade steel pipelines have been increasingly frequent, posing a serious threat to the safe operation of these pipelines. Consequently, there is an urgent need to comprehensively investigate the ultimate strain capacity of pipeline girth welds. In addressing this concern, the research focuses on the girth weld of a high-grade steel pipeline with a circumferential root crack. The study establishes a three-dimensional finite element simulation model for the crack driving force of the girth weld using ABAQUS, employing parametric programming to quantitatively assess the influence of material properties (the yield-to-tensile strength ratio of the base metal, the softening rate of the heat-affected zone, the strength matching coefficient of the weld), geometric structure (misalignment, crack length, crack depth), and load parameters (distal strain) on the crack driving force. Via parameterized calculation and processing of Python programs and parallel computing, a database of girth weld crack driving forces with 13514 samples is constructed. Additionally, a regression prediction model for the crack propagation driving force of full-size pipeline girth welds, accounting for the influence of multiple factors, is developed using neural network techniques. The results of Charpy impact tests (CVN value) serve as the apparent fracture toughness, enabling the determination of the ultimate strain capacity of the pipeline girth weld. Validation data from curved wide plate tests are employed to verify the model. Comparative analysis with the evaluation results of internationally recognized strain capacity prediction models (Pipeline Research Council International - Center for Reliable Energy Systems, PRCI-CRES & Exxon Mobil) reveals that the prediction model proposed in this study achieves a minimal average relative error, consistently below 15%. These research findings offer valuable insights for the design and safety assessment of girth welds in high-grade steel pipelines, and further ensure the safe operation of pipelines.

Presenting Author: Xiaoben Liu China University Of Petroleum(Beijing)

Presenting Author Biography: Liu Xiaoben, Ph.D., Associate Professor, Doctoral Supervisor, and Director of the Department of Oil and Gas Storage and Transportation Engineering at China University of Petroleum (Beijing). As the young leader of the safety team for oil and gas storage and transportation facilities, I have been engaged in teaching and research on the intrinsic safety and integrity evaluation of oil and gas storage and transportation facilities for a long time. I have led 5 national/provincial level vertical projects, more than 40 enterprise and public research projects, published more than 60 papers as the first/corresponding author, and more than 30 top or important international journal papers in this field. I have obtained 3 software works, 5 patents, participated in the approval of 1 ISO standard, and 1 national standard, 2 industry standards, published 1 translated work, and won 1 provincial and ministerial level special prize, 2 first prizes, and 2 second prizes. In recent years, research has been focused on major demand issues in the field of oil and gas storage and transportation safety in China, such as the failure of circumferential welds in high-grade pipelines, the interaction between geological disasters and pipelines, the safety evaluation of station pipeline systems and facilities, and the evaluation of foundation settlement and integrity of large storage tanks; At the same time, we are committed to promoting numerical simulation of oil and gas pipeline structures, digital twin technology, and exploring digital technologies for pipeline intrinsic safety based on multi-source perception of the industrial Internet of Things.

Authors:

Xiaoben Liu China University Of Petroleum(Beijing)
Dong Zhang China University of Petroleum (Beijing)
Haonan Zhang China University of Petroleum (Beijing)
Qingshan Feng China Oil & Gas Pipeline Network Corporation
Dongying Wang Technical Center, PipeChina Beijing Pipeline Company
Chong Wang Technical Center, PipeChina Beijing Pipeline Company
Yue Yang China University of Petroleum (Beijing)
Hong Zhang China University of Petroleum (Beijing)