基于机器学习算法的超声波预测TP2铜材晶粒度模型优化研究

岳峰丽; 郭威; 刘明华; 陈大勇; 刘劲松; 刘欢; 宋鸿武; 王松伟; 褚晓光

doi:10.3969/j.issn.1674-6457.2025.09.018

PDF(1596 KB)

精密成形工程 ›› 2025, Vol. 17 ›› Issue (9) : 185-194. DOI: 10.3969/j.issn.1674-6457.2025.09.018

铜合金成形

基于机器学习算法的超声波预测TP2铜材晶粒度模型优化研究

岳峰丽^1a, 郭威^1a, 刘明华^1b, 陈大勇^2,*, 刘劲松^1b, 刘欢^1a, 宋鸿武², 王松伟², 褚晓光³

作者信息 +

Optimization of Ultrasonic Prediction of TP2 Copper Grain Size Model Based on Machine Learning Algorithm

YUE Fengli^1a, GUO Wei^1a, LIU Minghua^1b, CHEN Dayong^2,*, LIU Jinsong^1b, LIU Huan^1a, SONG Hongwu², WANG Songwei³, CHU Xiaoguang³

Author information +

文章历史 +

摘要

目的借助机器学习算法对超声波衰减系数-平均等效晶粒尺寸模型（AC-AGS）进行优化,以实现高效准确的铜材晶粒尺寸预测。方法通过超声检测设备获得不同温度热处理后的TP2铜材的界面波幅值以及一次底面回波幅值,并通过幅值数据计算衰减系数,采用截点法获得铜材的晶粒尺寸。为优化铜材晶粒尺寸的预测模型,引入3种机器学习优化算法,即粒子群算法（PSO）、遗传算法（GA）以及差分进化算法（DE）,对TP2铜材的晶粒度预测模型进行优化。结果耦合机器学习算法的AC-AGS模型可以实现精密铜材平均晶粒尺寸的评测,PSO算法在本文优化结果中表现最佳,其验证结果的决定系数R²为0.904 5,均方根误差（Root Mean Square Error,RMSE）为20.85,平均绝对误差（Mean Absolute Error,MAE）为20.569。结论结合机器学习优化算法的超声波衰减系数与平均晶粒尺寸模型,实现了对TP2铜材晶粒尺寸的精确预测。该模型不仅为铜材晶粒尺寸的无损检测提供了一个高效、准确的预测工具,还为其他材料的晶粒尺寸预测提供了新的思路和方法。

Abstract

The work aims to optimize the ultrasonic attenuation coefficient-average equivalent grain size model (AC-AGS) with the help of machine learning algorithms, so as to achieve efficient and accurate prediction of copper grain size, and provide key technical support in industrial production. The interface amplitude and the primary bottom echo amplitude of TP2 copper after heat treatment at different temperature were obtained by ultrasonic testing equipment, the attenuation coefficient was calculated by amplitude data, and the grain size of copper was obtained by the intercept method. In order to optimize the prediction model of copper grain size, three machine learning optimization algorithms, namely particle swarm optimization (PSO), genetic algorithm (GA) and differential evolution algorithm (DE), were introduced to optimize the grain size prediction model of TP2 copper. Results showed that the AC-AGS model coupled with the machine learning algorithm could realize the evaluation of the average grain size of precision copper. It was found that the PSO algorithm performed the best in the optimization results in this paper, and its coefficient of determination R² was 0.904 5, the Root Mean Square Error (RMSE) was 20.85, and the Mean Absolute Error (MAE) was 20.569. In conclusion, combined with the ultrasonic attenuation coefficient and the average grain size model of the machine learning optimization algorithm, the accurate prediction of the grain size of TP2 copper is realized. This model not only provides an efficient and accurate prediction tool for the non-destructive testing of copper grain size, but also provides new ideas and methods for the grain size prediction of other materials.

导出引用

岳峰丽, 郭威, 刘明华, 陈大勇, 刘劲松, 刘欢, 宋鸿武, 王松伟, 褚晓光. 基于机器学习算法的超声波预测TP2铜材晶粒度模型优化研究[J]. 精密成形工程. 2025, 17(9): 185-194 https://doi.org/10.3969/j.issn.1674-6457.2025.09.018

YUE Fengli, GUO Wei, LIU Minghua, CHEN Dayong, LIU Jinsong, LIU Huan, SONG Hongwu, WANG Songwei, CHU Xiaoguang. Optimization of Ultrasonic Prediction of TP2 Copper Grain Size Model Based on Machine Learning Algorithm[J]. Journal of Netshape Forming Engineering. 2025, 17(9): 185-194 https://doi.org/10.3969/j.issn.1674-6457.2025.09.018

中图分类号： TP181

参考文献

[1] TIAN Y Z, REN Y P, GAO S, et al.Two-Stage Hall-Petch Relationship in Cu with Recrystallized Structure[J]. Journal of Materials Science & Technology, 2020, 48: 31-35.
[2] 崔桂彬, 鞠新华, 杨瑞, 等. 基于离子研磨技术的超低碳钢中铁素体晶粒的显示[J]. 理化检验-物理分册, 2021, 57(12): 8-11.
CUI G B, JU X H, YANG R, et al.Display of Ferrite Grains in Ultra-Low Carbon Steel Based on Ion Milling Technology[J]. Physical Testing and Chemical Analysis (Part A (Physical Testing)), 2021, 57(12): 8-11.
[3] 汪炳叔, 辛仁龙, 黄光杰, 等. EBSD分析技术在镁合金晶粒尺寸表征中的应用[J]. 电子显微学报, 2009, 28(1): 20-22.
WANG B S, XIN R L, HUANG G J, et al.Applications of EBSD in Measuring the Grain Size of Magnesium Alloy[J]. Journal of Chinese Electron Microscopy Society, 2009, 28(1): 20-22.
[4] GOUSKOV A M, GRIGORYEV Y V, PYAE P A.Torsional Waveguide Modeling of an Ultrasonic Medical Instrument[J]. Journal of Physics: Conference Series, 2021, 1902(1): 012009.
[5] 李雄兵, 宋永锋, 胡宏伟, 等. 基于衰减速率的晶粒尺寸超声评价方法[J]. 机械工程学报, 2015, 51(14): 1-7.
LI X B, SONG Y F, HU H W, et al.Evaluation of Grain Size Using the Ultrasonic Attenuation Rate[J]. Journal of Mechanical Engineering, 2015, 51(14): 1-7.
[6] 白雪, 马健, 许万卫, 等. 基于激光超声的金属增材制造在线检测技术研究[J]. 航空制造技术, 2022, 65(20): 70-82.
BAI X, MA J, XU W W, et al.Research on Online Testing Technology for Metal Additive Manufacturing Based on Laser Ultrasonic[J]. Aeronautical Manufacturing Technology, 2022, 65(20): 70-82.
[7] BAHARI-SAMBRAN F, CARREÑO F, CEPEDA- JIMÉNEZ C M, et al. Predicting Grain Size-Dependent Superplastic Properties in Friction Stir Processed ZK30 Magnesium Alloy with Machine Learning Methods[J]. Journal of Magnesium and Alloys, 2024, 12(5): 1931-1943.
[8] NGUYEN H G, LE T D, NGUYEN H G, et al.Mechanical Properties of AlCoCrCuFeNi High-Entropy Alloys Using Molecular Dynamics and Machine Learning[J]. Materials Science and Engineering: R: Reports, 2024, 160: 100833.
[9] 侯怀书, 李金好, 陆顶, 等. 基于连续小波变换的超声衰减法评估薄壁304L钢焊管晶粒尺寸[J]. 机械工程材料, 2022, 46(8): 46-52.
HOU H S, LI J H, LU D, et al.Grain Size Assessment of Thin-Walled 304L Steel Welded Tube by Ultrasonic Attenuation Method Based on Continuous Wavelet Transform[J]. Materials for Mechanical Engineering, 2022, 46(8): 46-52.
[10] XIE Y, GUO J J, MA X W.Digital Inclusive Financial and Household Fertility: Discoveries Based on Dual Machine Learning Algorithm[J]. International Review of Economics & Finance, 2025, 97: 103747.
[11] SHAHIDIAN N, ABREU P, SANTOS D, et al.Short-Term Forecasting of Emergency Medical Services Demand Exploring Machine Learning[J]. Computers & Industrial Engineering, 2025, 200: 110765.
[12] KUMARI N, SARANGI S K.Accelerated Discoveries of Mechanical Properties of Boron Nitride Nanosheets Using Machine Learning[J]. Surface Review and Letters, 2024: 2550084.
[13] SRIKANTH G, NIMMA D, LALITHA R V S, et al. Food Security Based Marine Life Ecosystem for Polar Region Conditioning: Remote Sensing Analysis with Machine Learning Model[J]. Remote Sensing in Earth Systems Sciences, 2025, 8(1): 65-73.
[14] 温丽涛, 陈勇. 基于机器学习的铝及其合金晶粒细化研究[J]. 智能计算机与应用, 2021, 11(4): 170-172.
WEN L T, CHEN Y.Research on Grain Refinement of Aluminum and Its Alloys Based on Machine Learning[J]. Intelligent Computer and Applications, 2021, 11(4): 170-172.
[15] 闫碧霄, 朱雪彤, 吴钢, 等. 基于机器学习的Cu-Ni- Co-Si合金固溶处理晶粒尺寸预测[J]. 铜业工程, 2024(2): 18-22.
YAN B X, ZHU X T, WU G, et al.Prediction of Grain Size in Cu-Ni-Co-Si Alloy Solid Solution Treatment Based on Machine Learning[J]. Copper Engineering, 2024(2): 18-22.
[16] ARISOY Y M, ÖZEL T.Machine Learning Based Predictive Modeling of Machining Induced Microhardness and Grain Size in Ti-6Al-4V Alloy[J]. Materials and Manufacturing Processes, 2015, 30(4): 425-433.
[17] 刘劲松, 张良利, 王松伟, 等. 基于双温度场耦合的铜板坯水平连铸过程有限元模拟[J]. 铸造技术, 2022, 43(7): 511-518.
LIU J S, ZHANG L L, WANG S W, et al.Finite Element Simulation of Copper Slab Horizontal Continuous Casting Process Based on Double Temperature Field Coupling[J]. Foundry Technology, 2022, 43(7): 511-518.
[18] 刘劲松, 孙扬乐, 陈大勇, 等. 工艺参数对三辊行星旋轧铜管尺寸定量影响研究[J]. 精密成形工程, 2024, 16(9): 1-12.
LIU J S, SUN Y L, CHEN D Y, et al.Quantitative Effect of Process Parameters on the Size of Three-Roll Planetary Rolling Copper Tube[J]. Journal of Netshape Forming Engineering, 2024, 16(9): 1-12.
[19] 国家质量监督检验检疫总局, 中国国家标准化管理委员会. 金属平均晶粒度测定方法: GB/T 6394— 2017[S]. 北京: 中国标准出版社, 2017.
General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China, Standardization Administration of the People's Republic of China. Determination of Estimating the Average Grain Size of Metal: GB/T 6394—2017[S]. Beijing: Standards Press of China, 2017.
[20] 周正干, 李文涛, 李洋, 等. 相控阵超声水浸C扫描自动检测系统的研制[J]. 机械工程学报, 2017, 53(12): 28-34.
ZHOU Z G, LI W T, LI Y, et al.Development of Ultrasonic Phased Array Immersion C-Scan Automatic Detection System[J]. Journal of Mechanical Engineering, 2017, 53(12): 28-34.
[21] 曹永朋, 张先锋, 陆杨星, 等. 水浸超声线聚焦探头发射声场测量方法[J]. 应用声学, 2024, 43(4): 775-782.
CAO Y P, ZHANG X F, LU Y X, et al.The Measurement Method of Emission Acoustic Field of Water Immersion Ultrasonic Line Focusing Probe[J]. Journal of Applied Acoustics, 2024, 43(4): 775-782.
[22] JAIN S, RANI R, JANGIR P, et al.Divided Opposition Strategy in Particle Swarm Framework for Constrained Optimization Problem[J]. Results in Control and Optimization, 2025, 18: 100508.
[23] 杨维, 李歧强. 粒子群优化算法综述[J]. 中国工程科学, 2004, 6(5): 87-94.
YANG W, LI Q Q.Survey on Particle Swarm Optimization Algorithm[J]. Engineering Science, 2004, 6(5): 87-94.
[24] 张铃, 张钹. 遗传算法机理的研究[J]. 软件学报, 2000, 11(7): 945-952.
ZHANG L, ZHANG B.Research on the Mechanism of Genetic Algorithms[J]. Journal of Software, 2000, 11(7): 945-952.
[25] OUYANG Z L, ZOU Z J.Nonparametric Modeling of Ship Maneuvering Motion Based on Gaussian Process Regression Optimized by Genetic Algorithm[J]. Ocean Engineering, 2021, 238: 109699.
[26] 杨启文, 蔡亮, 薛云灿. 差分进化算法综述[J]. 模式识别与人工智能, 2008, 21(4): 506-513.
YANG Q W, CAI L, XUE Y C.A Survey of Differential Evolution Algorithms[J]. Pattern Recognition and Artificial Intelligence, 2008, 21(4): 506-513.
[27] 刘波, 王凌, 金以慧. 差分进化算法研究进展[J]. 控制与决策, 2007, 22(7): 721-729.
LIU B, WANG L, JIN Y H.Advances in Differential Evolution[J]. Control and Decision, 2007, 22(7): 721-729.
[28] WANG H Y, WANG J C, ZHAO Y Q, et al.Tunneling Parameters Optimization Based on Multi-Objective Differential Evolution Algorithm[J]. Soft Computing, 2021, 25(5): 3637-3656.
[29] 温丽涛. 基于机器学习的合金形核过冷度及晶粒尺寸预测研究[D]. 衡阳: 南华大学, 2021.
WEN L T.Prediction of Undercooling and Grain Size of Alloy Nucleation Based on Machine Learning[D]. Hengyang: University of South China, 2021.