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

doi:10.3969/j.issn.1004-132X.2022.19.006

Abstract

Abstract: 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 42HRC 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 3HRC. 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 1100MPa 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.

Key words: machine learning, big data, petroleum equipment, large sectional component, martensite steel, optimized chemical composition

摘要： 为了满足超深层油气资源开发需求，针对石油装备用强度等级最高的低碳马氏体钢，结合成分性能大数据，基于四种不同机器学习方法分别建立了大截面高强韧低碳马氏体钢成分强度和成分硬度预测模型，分析表明，神经元层数为4、层深为64的人工神经网络模型的性能预测精度和拟合程度最好。采用遗传算法对材料成分进行智能最优化设计，获得CrNiMo和SiMnCrNiMo两种材料系中屈服强度大于1100 MPa、硬度大于42HRC、碳含量小于0.22%的最优成分，材料的端淬硬度分布曲线与预测值基本一致，最大误差小于3HRC。依据优化设计成分进行多批次产品生产制造后结果表明，150 mm直径的构件全截面获得95%以上的细小针状马氏体组织，屈服强度大于1100 MPa，低温冲击吸收能大于45 J，满足服役性能要求，预测结果与生产实验结果具有较高的一致性。将材料大数据与机器学习相结合实现了材料的智能化设计开发，为高性能材料的开发提供了新途径。

关键词: 机器学习, 大数据, 石油装备, 大截面构件, 马氏体钢, 成分优化

CLC Number:

TE921

LI Fangpo, LU Caihong, ZHAO Jingxiao, LI Xiucheng, SHANG Chengjia. Based on Machine Learning Intelligent Design and Properties Research of Large Sectional High Strength Martensite Steels for Petroleum Equipment[J]. China Mechanical Engineering, 2022, 33(19): 2325-2330.

李方坡, 路彩虹, 赵靖宵, 李秀程, 尚成嘉. 基于机器学习的石油装备用大截面高强韧马氏体钢智能设计与性能研究[J]. 中国机械工程, 2022, 33(19): 2325-2330.

References

［1］贾承造,庞雄奇,姜福杰.中国油气资源研究现状与发展方向［J］.石油科学通报,2016,1(1):2-23.
JIA Chengzao, PANG Xiongqi, JIANG Fujie. Research Status and Development Directions of Hydrocarbon Resources in China［J］.Petroleum Science Bulletin, 2016,1(1):2-23.
［2］李鹤林.李鹤林文集(上)——石油机械用钢专辑［M］.北京:机械工业出版社,2016:5.
LI Helin. Anthology of LI Helin(I)—Steel for Petroleum Machinery［M］.Bejing:China Machine Press,2016:5.
［3］吴炜,孙强.应用机器学习加速新材料的研发［J］.中国科学(物理学力学天文学),2018,48(10):58-70.
WU Wei, SUN Qiang. Applying Machine Learning to Accelerate New Materials Development［J］. Science in China(Series G), 2018,48(10):58-70.
［4］LOPEZ-BEZANILLA A, LITTLEWOOD P. Growing Field of Materials Informatics:Databases and Artificial Intelligence［J］.MRS Communications, 2020, 10(1):1-10.
［5］WEN C, ZHANG Y, WANG C, et al. Machine Learning Assisted Design of High Entropy Alloys with Desired Property［J］. Acta Materialia, 2019, 170:109-117.
［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［J］. Acta Materialia, 2020, 185:528-539.
［7］DONG G, LI X, ZHAO J, et al. Machine Learning Guided Methods in Building Chemical Composition-hardenability Model for Wear-resistant Steel［J］. Materials Today Communications, 2020:101332.
［8］CORREA-BAENA J P, HIPPALGAONKAR K, van DUREN J, et al. Accelerating Materials Development via Automation, Machine Learning, and High-performance Computing［J］. Joule, 2018, 2(8):1410-1420.
［9］RAMPRASAD R, BATRA R, PILANIA G, et al. Machine Learning in Materials Informatics:Recent Applications and Prospects［J］. NPJ Computational Materials, 2017, 3(1):1-13.
［10］WU X, KUMAR V, QUINLAN J R, et al. Top 10 Algorithms in Data Mining［J］. Knowledge and Information Systems, 2008, 14(1):1-37.
［11］QUINLAN J R. Induction of Decision Trees［J］. Machine Learning, 1986, 1(1):81-106.
［12］GOH G B, HODAS N O, VISHNU A. Deep Learning for Computational Chemistry［J］. Journal of Computational Chemistry, 2017, 38(16):1291-1307.
［13］BURGES C J C. A Tutorial on Support Vector Machines for Pattern Recognition［J］. Data Mining and Knowledge Discovery, 1998, 2(2):121-167.
［14］DING J, BAR-JOSEPH Z. MethRaFo:MeDIP-seq Methylation Estimate Using a Random Forest Regressor［J］. Bioinformatics, 2017, 33(21):3477-3479.
［15］DAI S, YU W, FENG C, et al. Design of New Biomedical Titanium Alloy Based on D-electron Alloy Design Theory and JMatPro Software［J］. Transactions of Nonferrous Metals Society of China, 2013, 23(10):3027-3032.
［16］DEB K, PRATAP A, AGARWAL S, et al. A Fast and Elitist Multiobjective Genetic Algorithm:NSGA-Ⅱ［J］. IEEE Transactions on Evolutionary Computation, 2002, 6(2):182-197.

[1]	WANG Ding, WU Deyu, YANG Daliang, CHEN Liting, YE Jinhua, WU Haibin. Air-bag Tactile Sensor with Pressure and Position Detection Functions [J]. China Mechanical Engineering, 2022, 33(14): 1691-1696,1706.
[2]	LIU Yongxing, TANG Xiaoqi, ZHONG Jinglong, ZHONG Zhenyu, ZHOU Xiangdong. Asymmetric Risk Injection Molding Product Size Prediction Model Based on LightGBM#br# [J]. China Mechanical Engineering, 2022, 33(08): 965-969.
[3]	LIU Daoyuan, GUO Yu, HUANG Shaohua, FANG Weiguang, YANG Nengjun, CUI Shiting. A SOM-FWFCM Based Feature Selection Algorithm for Order Remaining Completion Time Prediction#br# [J]. China Mechanical Engineering, 2021, 32(09): 1073-1079.
[4]	WENG Jian, ZHUANG Kejia, PU Donglin, DING Han, . Plunge Milling of Titanium Alloys Based on Machine Learning and Multi-objective Optimization [J]. China Mechanical Engineering, 2021, 32(07): 771-777.
[5]	CHEN Guangyao, LI Heng, HE Zirui, MA Jun, LI Guangjun, FU Ying. Effective Prediction and Compensation of Springbacks for Tube Bending Using Machine Learning Approach [J]. China Mechanical Engineering, 2020, 31(22): 2745-2752.
[6]	LI Minbo, XU Xinxing, LI Qiang, HAN Le. Multi-dimensional Analysis Method of Industrial Big Data Based on JSON Document Structure [J]. China Mechanical Engineering, 2020, 31(14): 1700-1707,1716.
[7]	YANG Bin, RAN Yan, ZHANG Genbao. Accuracy Analysis of Multi-axis CNC Machine Tools Based on Meta-action Module [J]. China Mechanical Engineering, 2020, 31(13): 1621-1628.
[8]	JIANG Shaofei;WU Tianji;PENG Xiang;LI Jiquan;LI Zhi;SUN Tao. Data Driven Fault Diagnosis Method Based on XGBoost Feature Extraction [J]. China Mechanical Engineering, 2020, 31(10): 1232-1239.
[9]	ZHANG Jie, WANG Junliang, LYU Youlong, BAO Jinsong. Big Data Driven Intelligent Manufacturing [J]. China Mechanical Engineering, 2019, 30(02): 127-133,158.
[10]	YAO Xifan, LEI Yi, GE Dongyuan, YE Jing. On Big Data Driving Manufacturing from “Internet Plus” to “AI Plus” [J]. China Mechanical Engineering, 2019, 30(02): 134-142.
[11]	ZHOU Yaqin, WANG Junliang, BAO Jinsong, ZHANG Jie. Study on General Data Models for Intelligent Control of Knitting Production [J]. China Mechanical Engineering, 2019, 30(02): 143-148,219.
[12]	LIU Weijie, JI Weixi, ZHANG Chaoyang, . Big Data Modeling Analysis Method for Intelligent Production Maintenance [J]. China Mechanical Engineering, 2019, 30(02): 159-166.
[13]	ZHANG Wei, DING Jinfu, JI Yangjian, XIA Wenjun, LAN Hu, ZHANG Jianhui. Modular Design of Intelligent Service Based on Industrial Big Data [J]. China Mechanical Engineering, 2019, 30(02): 167-173,182.
[14]	ZHANG Chen , LI Jia , WANG Haining, LI Siyue. Applications of Big Data in Equipment Health Status Prediction and Spare Parts Replenishment [J]. China Mechanical Engineering, 2019, 30(02): 183-187.
[15]	LI Minbo, DING Duo, YI Yong. Data Analysis of Tyre Quality Based on Improved FP-Growth Algorithm [J]. China Mechanical Engineering, 2019, 30(02): 244-251.