China Mechanical Engineering ›› 2026, Vol. 37 ›› Issue (4): 900-912.DOI: 10.3969/j.issn.1004-132X.2026.04.014
Previous Articles Next Articles
LIANG Qiang1(
), CHEN Hong1, ZHENG Yinpeng2, WANG Bing2, DU Yanbin1, LONG Shuai3
Received:2025-10-27
Online:2026-04-25
Published:2026-05-11
Contact:
LIANG Qiang
梁强1(
), 陈红1, 郑银鹏2, 王兵2, 杜彦斌1, 龙帅3
通讯作者:
梁强
作者简介:梁强*(通信作者),男,1988年生,副教授。研究方向为精密塑性成形工艺及设计、模具制造及再制造。E-mail:2017015@ctbu.edu.cn。
基金资助:CLC Number:
LIANG Qiang, CHEN Hong, ZHENG Yinpeng, WANG Bing, DU Yanbin, LONG Shuai. Interpretable Modeling and Optimization of Laser Hardening Process Parameters for QT550-5[J]. China Mechanical Engineering, 2026, 37(4): 900-912.
梁强, 陈红, 郑银鹏, 王兵, 杜彦斌, 龙帅. 面向QT550-5激光硬化工艺参数的可解释性模型构建与优化[J]. 中国机械工程, 2026, 37(4): 900-912.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.cmemo.org.cn/EN/10.3969/j.issn.1004-132X.2026.04.014
| 网格尺寸 | 最大 单元 尺寸/ mm | 最小 单元 尺寸/ mm | 最大单元 增长率 | 狭窄区域分辨率 | h/μm | H/μm | t/s |
|---|---|---|---|---|---|---|---|
| M1 | 0.18 | 0.004 | 1.30 | 0.85 | 225 | 495 | 18 108 |
| M2 | 0.20 | 0.010 | 1.35 | 0.90 | 215 | 510 | 10 296 |
| M3 | 1.20 | 0.150 | 1.45 | 0.95 | 280 | 640 | 6592 |
Tab.1 Mesh independence verification
| 网格尺寸 | 最大 单元 尺寸/ mm | 最小 单元 尺寸/ mm | 最大单元 增长率 | 狭窄区域分辨率 | h/μm | H/μm | t/s |
|---|---|---|---|---|---|---|---|
| M1 | 0.18 | 0.004 | 1.30 | 0.85 | 225 | 495 | 18 108 |
| M2 | 0.20 | 0.010 | 1.35 | 0.90 | 215 | 510 | 10 296 |
| M3 | 1.20 | 0.150 | 1.45 | 0.95 | 280 | 640 | 6592 |
| w(C) | w(Si) | w(Mn) | w(P) | w(S) | w(Cu) | w(Fe) |
|---|---|---|---|---|---|---|
| 3.5~3.9 | 2.2~2.7 | <0.4 | <0.06 | <0.02 | 0.04~0.08 | 其余 |
Tab.2 Principal chemical composition of QT550-5
| w(C) | w(Si) | w(Mn) | w(P) | w(S) | w(Cu) | w(Fe) |
|---|---|---|---|---|---|---|
| 3.5~3.9 | 2.2~2.7 | <0.4 | <0.06 | <0.02 | 0.04~0.08 | 其余 |
| 序号 | P/W | v/ (mm·s | δ/% | h/μm | H/μm |
|---|---|---|---|---|---|
| 1 | 345 | 12 | 70 | 410 | 550 |
| 2 | 364 | 5 | 63 | 520 | 680 |
| 3 | 116 | 13 | 68 | 0 | 0 |
| 4 | 458 | 8 | 90 | 540 | 700 |
| 5 | 443 | 10 | 76 | 520 | 680 |
| 6 | 233 | 7 | 84 | 140 | 270 |
| 7 | 326 | 6 | 81 | 445 | 600 |
| 8 | 213 | 14 | 75 | 140 | 290 |
| 9 | 111 | 13 | 71 | 0 | 0 |
| 10 | 413 | 13 | 66 | 485 | 630 |
| 11 | 302 | 9 | 86 | 380 | 510 |
| 12 | 262 | 9 | 73 | 290 | 420 |
| 13 | 388 | 10 | 89 | 480 | 620 |
| 14 | 316 | 9 | 61 | 390 | 540 |
| 15 | 138 | 6 | 64 | 0 | 105 |
| 16 | 477 | 14 | 62 | 515 | 670 |
| 17 | 487 | 11 | 84 | 530 | 685 |
| 18 | 185 | 7 | 86 | 20 | 185 |
| 19 | 251 | 11 | 80 | 255 | 385 |
| 20 | 149 | 15 | 66 | 0 | 80 |
| 21 | 285 | 11 | 74 | 325 | 450 |
| 22 | 206 | 10 | 78 | 170 | 305 |
| 23 | 394 | 6 | 69 | 525 | 710 |
| 24 | 434 | 14 | 82 | 480 | 610 |
| 25 | 177 | 7 | 78 | 105 | 260 |
Tab.3 Experimental program and simulation results
| 序号 | P/W | v/ (mm·s | δ/% | h/μm | H/μm |
|---|---|---|---|---|---|
| 1 | 345 | 12 | 70 | 410 | 550 |
| 2 | 364 | 5 | 63 | 520 | 680 |
| 3 | 116 | 13 | 68 | 0 | 0 |
| 4 | 458 | 8 | 90 | 540 | 700 |
| 5 | 443 | 10 | 76 | 520 | 680 |
| 6 | 233 | 7 | 84 | 140 | 270 |
| 7 | 326 | 6 | 81 | 445 | 600 |
| 8 | 213 | 14 | 75 | 140 | 290 |
| 9 | 111 | 13 | 71 | 0 | 0 |
| 10 | 413 | 13 | 66 | 485 | 630 |
| 11 | 302 | 9 | 86 | 380 | 510 |
| 12 | 262 | 9 | 73 | 290 | 420 |
| 13 | 388 | 10 | 89 | 480 | 620 |
| 14 | 316 | 9 | 61 | 390 | 540 |
| 15 | 138 | 6 | 64 | 0 | 105 |
| 16 | 477 | 14 | 62 | 515 | 670 |
| 17 | 487 | 11 | 84 | 530 | 685 |
| 18 | 185 | 7 | 86 | 20 | 185 |
| 19 | 251 | 11 | 80 | 255 | 385 |
| 20 | 149 | 15 | 66 | 0 | 80 |
| 21 | 285 | 11 | 74 | 325 | 450 |
| 22 | 206 | 10 | 78 | 170 | 305 |
| 23 | 394 | 6 | 69 | 525 | 710 |
| 24 | 434 | 14 | 82 | 480 | 610 |
| 25 | 177 | 7 | 78 | 105 | 260 |
| 目标 | RF | XGBOOST | BPNN | MTNN | BO-MTNN | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| R2 | eMA | eRMS | R2 | eMA | eRMS | R2 | eMA | eRMS | R2 | eMA | eRMS | R2 | eMA | eRMS | |
| h | 0.793 | 67.83 | 85.96 | 0.887 | 56.23 | 63.44 | 0.992 | 11.54 | 13.54 | 0.969 | 8.25 | 43.11 | 0.993 | 5.33 | 6.35 |
| H | 0.797 | 82.27 | 109.23 | 0.864 | 69.79 | 89.43 | 0.993 | 15.52 | 19.74 | 0.968 | 22.9 | 67.48 | 0.997 | 14.19 | 19.36 |
Tab.4 Comparison of model accuracy
| 目标 | RF | XGBOOST | BPNN | MTNN | BO-MTNN | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| R2 | eMA | eRMS | R2 | eMA | eRMS | R2 | eMA | eRMS | R2 | eMA | eRMS | R2 | eMA | eRMS | |
| h | 0.793 | 67.83 | 85.96 | 0.887 | 56.23 | 63.44 | 0.992 | 11.54 | 13.54 | 0.969 | 8.25 | 43.11 | 0.993 | 5.33 | 6.35 |
| H | 0.797 | 82.27 | 109.23 | 0.864 | 69.79 | 89.43 | 0.993 | 15.52 | 19.74 | 0.968 | 22.9 | 67.48 | 0.997 | 14.19 | 19.36 |
| 评价指标 | MOHOA | MOPSO | NSGA-II |
|---|---|---|---|
| HV | 3.71×105 | 2.14×105 | 2.57×105 |
| IGD | 4.24 | 5.39 | 4.63 |
Tab.5 Algorithm performance comparison
| 评价指标 | MOHOA | MOPSO | NSGA-II |
|---|---|---|---|
| HV | 3.71×105 | 2.14×105 | 2.57×105 |
| IGD | 4.24 | 5.39 | 4.63 |
| 序号 | P/W | v/(mm·s | δ/% | H/μm | h/μm | Gi |
|---|---|---|---|---|---|---|
| 1 | 201.8 | 5.0 | 86.9 | 245.9 | 73.5 | 0.62 |
| 2 | 207.6 | 5.0 | 88.5 | 243.2 | 72.5 | 0.61 |
| 3 | 207.6 | 5.1 | 88.5 | 243 | 72.3 | 0.59 |
| 4 | 206.6 | 5.3 | 87.6 | 250.3 | 79.3 | 0.56 |
| 5 | 208 | 5.4 | 82.8 | 304.5 | 135.8 | 0.54 |
Tab.6 Top 5 groups of solutions ranked by comprehensive evaluation
| 序号 | P/W | v/(mm·s | δ/% | H/μm | h/μm | Gi |
|---|---|---|---|---|---|---|
| 1 | 201.8 | 5.0 | 86.9 | 245.9 | 73.5 | 0.62 |
| 2 | 207.6 | 5.0 | 88.5 | 243.2 | 72.5 | 0.61 |
| 3 | 207.6 | 5.1 | 88.5 | 243 | 72.3 | 0.59 |
| 4 | 206.6 | 5.3 | 87.6 | 250.3 | 79.3 | 0.56 |
| 5 | 208 | 5.4 | 82.8 | 304.5 | 135.8 | 0.54 |
| 目标 | 实验结果 | 模型预测 | 模拟结果 |
|---|---|---|---|
| h | 65 | 74 | 71 |
| H | 225 | 246 | 243 |
Tab.7 Comparison between simulation, prediction and experimental results
| 目标 | 实验结果 | 模型预测 | 模拟结果 |
|---|---|---|---|
| h | 65 | 74 | 71 |
| H | 225 | 246 | 243 |
| 1.建立决策矩阵和标准矩阵 |
|---|
| 式中:帕累托解集组成决策矩阵 A =[aij ] m×n,共m组待决策工艺参数组合,m=50,n个评价指标,n=2; B =[bij ] m×n,为正向化处理得到的矩阵; γ 为标准矩阵。 |
| 2.计算各目标权重值 |
| 式中: |
| 3.计算欧氏距离并输出综合评分 |
| 式中: |
Fig.14 Procedures for the comprehensive evaluation method of EWM-TOPSIS
| 1.建立决策矩阵和标准矩阵 |
|---|
| 式中:帕累托解集组成决策矩阵 A =[aij ] m×n,共m组待决策工艺参数组合,m=50,n个评价指标,n=2; B =[bij ] m×n,为正向化处理得到的矩阵; γ 为标准矩阵。 |
| 2.计算各目标权重值 |
| 式中: |
| 3.计算欧氏距离并输出综合评分 |
| 式中: |
| 元素 | 点 | 基体 | 熔凝层 | 硬化层 |
|---|---|---|---|---|
| w(C) | 1 | 3.69 | 13.43 | 9.91 |
| 2 | 3.36 | 13.33 | 9.38 | |
| 3 | 4.06 | 13.61 | 10.09 | |
| 平均值 | 3.70 | 13.46 | 9.79 | |
| w(Si) | 1 | 2.27 | 2.75 | 1.91 |
| 2 | 1.87 | 2.69 | 2.01 | |
| 3 | 2.05 | 2.80 | 1.88 | |
| 平均值 | 2.06 | 2.75 | 1.93 | |
| w(Mn) | 1 | 0.19 | 0.08 | 0.34 |
| 2 | 0.16 | 0.09 | 0.25 | |
| 3 | 0.14 | 0.10 | 0.30 | |
| 平均值 | 0.16 | 0.09 | 0.30 | |
| w(Fe) | 其余 | 其余 | 其余 |
Tab.8 Quantitative EDS point analysis results from different regions
| 元素 | 点 | 基体 | 熔凝层 | 硬化层 |
|---|---|---|---|---|
| w(C) | 1 | 3.69 | 13.43 | 9.91 |
| 2 | 3.36 | 13.33 | 9.38 | |
| 3 | 4.06 | 13.61 | 10.09 | |
| 平均值 | 3.70 | 13.46 | 9.79 | |
| w(Si) | 1 | 2.27 | 2.75 | 1.91 |
| 2 | 1.87 | 2.69 | 2.01 | |
| 3 | 2.05 | 2.80 | 1.88 | |
| 平均值 | 2.06 | 2.75 | 1.93 | |
| w(Mn) | 1 | 0.19 | 0.08 | 0.34 |
| 2 | 0.16 | 0.09 | 0.25 | |
| 3 | 0.14 | 0.10 | 0.30 | |
| 平均值 | 0.16 | 0.09 | 0.30 | |
| w(Fe) | 其余 | 其余 | 其余 |
| [1] | MARTÍNEZ S, LAMIKIZ A, UKAR E, et al. Analysis of the Regimes in the Scanner-based Laser Hardening Process[J]. Optics and Lasers in Engineering, 2017, 90: 72-80. |
| [2] | ZAMMIT A, ABELA S, BETTS J C, et al. Discrete Laser Spot Hardening of Austempered Ductile Iron[J]. Surface and Coatings Technology, 2017, 331: 143-152. |
| [3] | GHAINI F M, AMERI M H, TORKAMANY M J. Surface Transformation Hardening of Ductile Cast Iron by a 600w Fiber Laser[J]. Optik, 2020, 203: 163758. |
| [4] | REDA AL-SAYED S, ELGAZZAR H, NOFAL A. Metallographic Investigation of Laser-treated Ductile Iron Surface with Different Laser Heat Inputs[J]. Ain Shams Engineering Journal, 2023, 14(10): 102189. |
| [5] | CHEN Z, YU X, DING N, et al. Wear Resistance Enhancement of QT700-2 Ductile Iron Crankshaft Processed by Laser Hardening[J]. Optics & Laser Technology, 2023, 164: 109519. |
| [6] | 唐亮, 王文健, 张亚龙, 等. 激光淬火工艺对QT700-2球墨铸铁表面硬度与硬化层深度的影响[J]. 机械工程材料, 2020, 44(5): 82-86. |
| TANG Liang, WANG Wenjian, ZHANG Yalong, et al. Effect of Laser Quenching Process on Surface Hardness and Hardened Layer Depth of QT700-2 Ductile Cast Iron[J]. Materials for Mechanical Engineering, 2020, 44(5): 82-86. | |
| [7] | VESELÝ Z, HONNEROVÁ P, HRUŠKA M, et al. Analysis of Laser Surface Absorptivity Modification for Selective Laser Hardening[J]. International Journal of Thermal Sciences, 2024, 200: 108982. |
| [8] | 杨仁人, 林英华, 彭龙生, 等. 连续高功率激光辐照对55号钢组织和硬度的影响[J]. 中国激光, 2023, 50(16): 155-166. |
| YANG Renren, LIN Yinghua, PENG Longsheng, et al. Effect of Continuous High-power Laser Irradiation on Microstructure and Hardness of 55 Steel[J]. Chinese Journal of Lasers, 2023, 50(16): 155-166. | |
| [9] | 郭怡晖, 刘继常, 卢远志, 等. 球墨铸铁QT600-3激光相变硬化数值模拟研究[J]. 强激光与粒子束, 2010, 22(8): 1755. |
| GUO Yihui, LIU Jichang, LU Yuanzhi, et al. Numerical Simulation of Laser Transformation Hardening of Ductile Cast Iron QT600-3[J]. High Power Laser and Particle Beams, 2010, 22(8): 1755. | |
| [10] | DJURDJEVIC M, JOVANOVIC V, STOPIC S. Quantifying Latent Heat in AlSi5Cu Alloys (with 1, 2, and 4% of Cu by Mass) via DSC, Thermal Analysis, and Commercial Software[J]. Metals, 2025, 15(9): 1045. |
| [11] | MOHAJERANI S, MILLER J D, TUTUNEA-FATAN O R, et al. Thermo-physical Modelling of Track Width during Laser Polishing of H13 Tool Steel[J]. Procedia Manufacturing, 2017, 10: 708-719. |
| [12] | DAVIS M, KAPADIA P, DOWDEN J, et al. Heat Hardening of Metal Surfaces with a Scanning Laser Beam[J]. Journal of Physics D: Applied Physics, 1986, 19(10): 1981. |
| [13] | TEMMLER A, LIU D, PREUßNER J, et al. Influence of Laser Polishing on Surface Roughness and Microstructural Properties of the Remelted Surface Boundary Layer of Tool Steel H11[J]. Materials & Design, 2020, 192: 108689. |
| [14] | DING T, LIU S, WANG Z, et al. A Novel Mixture Sampling Strategy Combining Latin Hypercube Sampling with Optimized One Factor at a Time Method: a Case Study on Mixtures of Antibiotics and Pesticides[J]. Journal of Hazardous Materials, 2024, 461: 132568. |
| [15] | BOURCET J, KUBILAY A, DEROME D, et al. Representative Meteorological Data for Long-term Wind-driven Rain Obtained from Latin Hypercube Sampling- Application to Impact Analysis of Climate Change[J]. Building and Environment, 2023, 228: 109875. |
| [16] | VOŘECHOVSKÝ M. Hierarchical Refinement of Latin Hypercube Samples[J]. Computer-Aided Civil and Infrastructure Engineering, 2015, 30(5): 394-411. |
| [17] | MA S, CHEN Z, ZHANG D, et al. Interpretable Multi-task Neural Network Modeling and Particle Swarm Optimization of Process Parameters in Laser Welding[J]. Knowledge-Based Systems, 2024, 300: 112116. |
| [18] | GUNNING D, STEFIK M, CHOI J, et al. XAI—Explainable Artificial Intelligence[J]. Science Robotics, 2019, 4(37): eaay7120. |
| [19] | BELLE V, PAPANTONIS I. Principles and Practice of Explainable Machine Learning[J]. Frontiers in Big Data, 2021, 4: 688969. |
| [20] | TJOA E, GUAN C. A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(11): 4793-4813. |
| [21] | NOVAKOVSKY G, DEXTER N, LIBBRECHT M W, et al. Obtaining Genetics Insights from Deep Learning via Explainable Artificial Intelligence[J]. Nature Reviews Genetics, 2023, 24(2): 125-137. |
| [22] | AMIRI M H, MEHRABI HASHJIN N, MONTAZERI M, et al. Hippopotamus Optimization Algorithm: a Novel Nature-inspired Optimization Algorithm[J]. Scientific Reports, 2024, 14: 5032. |
| [23] | 郑文祥, 刘静, 陈家辉. HOA和SPEA2结合的边缘云计算任务卸载优化[J]. 计算机技术与发展, 2025, 35(4): 7-14. |
| ZHENG Wenxiang, LIU Jing, CHEN Jiahui. Optimization of Edge Cloud Computing Task Offloading Combining HOA and SPEA2[J]. Computer Technology and Development, 2025, 35(4): 7-14. | |
| [24] | LV J, SUN Y, ZHANG Z, et al. Optimization of Operational Parameters of Marine Methanol Dual-fuel Engine Based on RSM-MOPSO[J]. Process Safety and Environmental Protection, 2024, 191: 2634-2652. |
| [25] | 蒋荣超, 刘大维, 王登峰. 基于熵权TOPSIS方法的整车动力学性能多目标优化[J]. 机械工程学报, 2018, 54(2): 150-158. |
| JIANG Rongchao, LIU Dawei, WANG Dengfeng. Multi-objective Optimization of Vehicle Dynamics Performance Based on Entropy Weighted TOPSIS Method[J]. Journal of Mechanical Engineering, 2018, 54(2): 150-158. |
| [1] | XIAO Wei, ZHANG Cong, CHEN Xubing. Energy Consumption Prediction of Industrial Robots Based on Bayesian Optimized Temporal Convolutional Network [J]. China Mechanical Engineering, 2026, 37(4): 831-836. |
| [2] | GUO Yuqin, YIN Hang, YANG Dongjie, LIU Chenxi, LI Fuzhu. A Design Method of Wide Blade Ultrasonic Sonotrodes for Both of End and Side Faces Working by Cooperating Frequency Offset Compensation with Stepwise Hierarchical Optimization [J]. China Mechanical Engineering, 2025, 36(12): 2903-2910. |
| [3] | Zhi WANG, Shanfu LI, Jing TIAN, Mengkang YUE. Design and Experimental Study of Stiffness Self-tuning Wideband Dynamic Vibration Absorbers [J]. China Mechanical Engineering, 2025, 36(11): 2593-2600. |
| [4] | ZHENG Yan. Research on Processing Parameter Optimization of Rail Repair by Abrasive Waterjet [J]. China Mechanical Engineering, 2025, 36(05): 1132-1141. |
| [5] | XU Ping, LUO Jing, YU Yinghua, SHEN Jiaxing, LI Wenli. Study on Performance and Optimal Design of Friction Pairs of Textured Disk [J]. China Mechanical Engineering, 2024, 35(10): 1774-1782. |
| [6] | CHENG Aiguo1, WANG Chao1, LU Rijin2, HE Zhicheng1, YU Wanyuan3. Holistic Topology and Parameter Lightweight Design of Composite Tailgate Structures [J]. China Mechanical Engineering, 2024, 35(10): 1824-1833. |
| [7] | LIU Xiaobao, YAN Qingxiu, YI Bin, YAO Tingqiang, GU Wenjuan. Optimization of Process Parameters in Process Manufacturing Based on Ensemble Learning and Improved Particle Swarm Optimization Algorithm [J]. China Mechanical Engineering, 2023, 34(23): 2842-2853. |
| [8] | TANG Yang, ZHANG Wudi, ZHANG Yulin, WANG Yuan, . Simulation and Experimental Study on Slip Bearing Performance and Pipe Wall Damage Characteristics of Pipeline Plugging Robots [J]. China Mechanical Engineering, 2023, 34(22): 2758-2771. |
| [9] | ZHANG Mingliang, YANG Dawei, LI Mingyuan, YANG Xinmeng, LIU Liru, ZHANG Lianpeng. Levitation Force Characteristics and Parameter Optimization of Permanent Magnet Tracks [J]. China Mechanical Engineering, 2023, 34(19): 2370-2380. |
| [10] | HU Bo, LUO Weitao, WANG Shaofei, LAN Xiwang. Quantitative Study on Magnetic Anomaly of Superalloy Surface Defects Based on Parameter Optimization of SVM [J]. China Mechanical Engineering, 2023, 34(17): 2058-2064. |
| [11] | SUN Jiale, LUO Chen, ZHOU Yijun, WANG Wei, ZHANG Gang. Calibration Parameter Optimization and Accuracy Evaluation of Complex Visual Measurement Systems [J]. China Mechanical Engineering, 2023, 34(14): 1741-1748,1755. |
| [12] | LI Guolong, ZHU Guohua, JIANG Lin, TAO Yijie, JIA Yachao. Optimization of Multi-objective Grinding Process Parameters to Suppress Chatter Marks [J]. China Mechanical Engineering, 2023, 34(09): 1086-1092. |
| [13] | . Analysis on Dynamic Characteristics of Compliant Foil Face Gas Seals with Three Degrees of Freedom Perturbation [J]. China Mechanical Engineering, 2022, 33(15): 1828-1840. |
| [14] | WANG Xianye, LIU Haitao, HUANG Tian. Dimensional Parameter Optimization of Planar Closed-loop Legged Mechanisms [J]. China Mechanical Engineering, 2022, 33(11): 1261-1268. |
| [15] | YI Qian, LI Congbo, PAN Jian, ZHANG You. Reliability Analysis of Machining Accuracy and Processing Parameter Optimization for Thin-plate Parts [J]. China Mechanical Engineering, 2022, 33(11): 1269-1277. |
| Viewed | ||||||
|
Full text |
|
|||||
|
Abstract |
|
|||||