Based on Machine Learning Intelligent Design and Properties Research of Large Sectional High Strength Martensite Steels for Petroleum Equipment

被引：0
|
作者：
Li F. [1 ]
Lu C. [1 ]
Zhao J. [2 ]
Li X. [2 ]
Shang C. [2 ]
机构：
[1] CNPC Tubular Goods Research Institute, State Key Laboratory for Performance and Structure Safety of Petroleum Tubular Goods and Equipment Materials, Xi'an
[2] Collaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing
来源：
Zhongguo Jixie Gongcheng/China Mechanical Engineering | 2022年 / 33卷 / 19期
关键词：
big data; large sectional component; machine learning; martensite steel; optimized chemical composition; petroleum equipment;
D O I：
10.3969/j.issn.1004-132X.2022.19.006
中图分类号：
学科分类号：
摘要：
In order to develop new materials and meet the requirements of ultra-deep petroleum and gas development, four prediction models for composition-yield strength and composition-hardness of large cross-sectional martensitic steel with the highest strength grade for equipment components were established based on machine learning and composition performance big data herein. The results show that the artificial neural network model with 4 layers of neurons and 64 layers depth has the best fitting degree for property predicting, and two optimized martensitic steels chemical composition design with yield strength greater than 1100 MPa, hardness greater than 42 HRC and carbon content less than 0. 22% are formed based on genetic algorithm. The experimental results show that the hardening distribution curve of designed materials is basically consistent with the predicted values, and the maximum error is less than 3 HRC. According to the optimized composition, 35 batches of products were manufactured and testing results show that the materials may meet the performance requirements of 150 mm cross-sectional drilling rig components. More than 95% uniform fine acicular martensite may be obtained in the full cross-sections, yield strength is greater than 1100 MPa and impact absorbed energy is greater than 45 J which meets the service requirements of petroleum equipment. The results of prediction performance are consistent with that of experiments. Material big data is combined with machine learning, which provides a new way for developing high performance petroleum equipment materials. © 2022 China Mechanical Engineering Magazine Office. All rights reserved.
引用
收藏
页码：2325 / 2330
页数：5
相关论文
共 16 条
  • [1] JIA Chengzao, PANG Xiongqi, JIANG Fujie, Research Status and Development Directions of Hydrocarbon Resources in China, Petroleum Science Bulletin, 1, 1, pp. 2-23, (2016)
  • [2] LI Helin, Anthology of LI Helin(I)-Steel for Petroleum Machinery, (2016)
  • [3] WU Wei, SUN Qiang, Applying Machine Learning to Accelerate New Materials Development, Science in China(Series G), 48, 10, pp. 58-70, (2018)
  • [4] LOPEZ-BEZANILLA A, LITTLEWOOD P., Growing Field of Materials Informatics: Databases and Artificial Intelligence, MRS Communications, 10, 1, pp. 1-10, (2020)
  • [5] WEN C, ZHANG Y, WANG C, Et al., Machine Learning Assisted Design of High Entropy Alloys with Desired Property, Acta Materialia, 170, pp. 109-117, (2019)
  • [6] ZHANG Y, WEN C, WANG C, Et al., Phase Prediction in High Entropy Alloys with a Rational Selection of Materials Descriptors and Machine Learning Models, Acta Materialia, 185, pp. 528-539, (2020)
  • [7] DONG G, LI X, ZHAO J, Et al., Machine Learning Guided Methods in Building Chemical Compositionhardenability Model for Wear-resistant Steel, Materials Today Communications, (2020)
  • [8] CORREA-BAENA J P, HIPPALGAONKAR K, van DUREN J, Et al., Accelerating Materials Development via Automation, Machine Learning, and High-performance Computing, Joule, 2, 8, pp. 1410-1420, (2018)
  • [9] RAMPRASAD R, BATRA R, PILANIA G, Et al., Machine Learning in Materials Informatics: Recent Applications and Prospects, NPJ Computational Materials, 3, 1, pp. 1-13, (2017)
  • [10] WU X, KUMAR V, QUINLAN J R, Et al., Top 10 Algorithms in Data Mining, Knowledge and Information Systems, 14, 1, pp. 1-37, (2008)
12