基于GA-GRNN的AWJ强化3D打印AlSi10Mg表面性能实验研究*

doi:10.16731/j.cnki.1671-3133.2024.07.005

现代制造工程 ›› 2024, Vol. 526 ›› Issue (7): 35-41.doi: 10.16731/j.cnki.1671-3133.2024.07.005

基于GA-GRNN的AWJ强化3D打印AlSi10Mg表面性能实验研究^*

张苗苗¹, 侯荣国^1,2, 吕哲¹, 王龙庆¹, 石广行¹, 王中庆¹

1 山东理工大学机械工程学院,淄博 255000;
2 山东省精密制造与特种加工重点实验室,淄博 255000

收稿日期:2023-10-20 出版日期:2024-07-18 发布日期:2024-07-30
通讯作者: 侯荣国,博士,教授,主要研究方向为超声辅助磨料水射流切割。E-mail:hourongguo212@163.com
作者简介:张苗苗,硕士研究生,主要研究方向为磨料水射流强化。E-mail:2507292688@qq.com
基金资助:
*山东省自然科学基金项目(ZR2020ME154)

Experimental study on the surface properties of AWJ surface strengthening 3D printed AlSi10Mg based on GA-GRNN

ZHANG Miaomiao¹, HOU Rongguo^1,2, LÜ Zhe¹, WANG Longqing¹, SHI Guangxing¹, WANG Zhongqing¹

1 School of Mechanical Engineering,Shandong University of Technology,Zibo 255000,China;
2 Shandong Provincial Key Laboratory of Precision Manufacturing and No-traditional Machining, Zibo 255000,China

Received:2023-10-20 Online:2024-07-18 Published:2024-07-30

摘要/Abstract

摘要： 为提高磨料水射流(Abrasive Water Jet,AWJ)强化工艺对3D打印AlSi10Mg表面性能的强化效果预测的准确性及高效性,首先开展磨料水射流强化AlSi10Mg表面强化实验;然后分别以表面硬度和表面残余应力作为目标,基于遗传算法-广义回归神经网络(Genetic Algorithm-Generalized Ragression Neural Network,GA-GRNN)对实验数据样本进行训练,建立3D打印AlSi10Mg表面性能预测模型;最后,利用遗传算法对建立的神经网络预测模型中的AWJ强化主要参数进行优化。研究结果表明,经过磨料水射流强化后的AlSi10Mg表面硬度与表面残余应力均得到有效提高;建立的GA-GRNN预测模型与校验值误差在2.3 %以内,具有较高的准确性;经遗传算法优化后,得到表面硬度最佳参数组合:射流压力为33 MPa,磨料粒径为0.15 mm,靶距为12.4 mm,此时表面硬度为159.25HV;表面残余应力最佳参数组合:射流压力为40 MPa,磨料粒径为0.13 mm,靶距为15 mm,此时表面残余应力为-137.4 MPa。为后续磨料水射流强化零件表面的参数选择提供数据支撑。

关键词: 磨料水射流, 3D打印的AlSi10Mg, 表面强化, GA-GRNN神经网络, 遗传算法

Abstract: Order to improve the accuracy and efficiency of the prediction of the strengthening effect of Abrasive Water Jet (AWJ) strengthening process on the surface properties of 3D printed AlSi10Mg materials, firstly,the surface strengthening experiment of AlSi10Mg material strengthened by abrasive water jet was carried out.Then,based on the GA-GRNN neural network,the experimental data samples were trained with the surface hardness and surface residual stress as the target respectively,and the surface performance prediction model of 3D printed AlSi10Mg was established.Finally,the main parameters of AWJ strengthening in the established neural network model were optimized by genetic algorithm.The results show that the surface hardness and surface residual stress of AlSi10Mg material are effectively improved after abrasive water jet strengthening.The error of the established GA-GRNN prediction model is within 2.3 %,which has high accuracy.After optimization by genetic algorithm,the best parameter combination of surface hardness is obtained jet pressure 33 MPa,abrasive particle size 0.15 mm,target distance 12.4 mm,and the surface hardness is 159.25HV. The optimal parameter combination of surface residual stress is jet pressure 40 MPa,abrasive particle size 0.13 mm,target distance 15 mm,and the surface residual stress is -137.4 MPa. It provides data support for the parameter selection of the surface of the subsequent abrasive water jet strengthening parts.

Key words: Abrasive Water Jet (AWJ), 3D printed AlSi10Mg, surface strengthen, GA-GRNN neural network, genetic algorithm

中图分类号:

TG73
TH142.2

张苗苗, 侯荣国, 吕哲, 王龙庆, 石广行, 王中庆. 基于GA-GRNN的AWJ强化3D打印AlSi10Mg表面性能实验研究^*[J]. 现代制造工程, 2024, 526(7): 35-41.

ZHANG Miaomiao, HOU Rongguo, LÜ Zhe, WANG Longqing, SHI Guangxing, WANG Zhongqing. Experimental study on the surface properties of AWJ surface strengthening 3D printed AlSi10Mg based on GA-GRNN[J]. Modern Manufacturing Engineering, 2024, 526(7): 35-41.

参考文献

[1] RAO B S,RAO T B.Mechanical and tribological properties of 3D printed Al-Si alloys and composites:a review[J].Silicon,2022,14(11):5751-5782.
[2] MAAMOUN A H,ELBESTAWI M,DOSBAEVA G K,et al.Thermal post-processing of AlSi10Mg parts produced by selective laser melting using recycled powder[J].Additive Manufacturing,2018,21:234-247.
[3] MANEIAH D,SHUNMUGASUNDARAM M,REDDY A R,et al.Optimization of machining parameters for surface roughness during abrasive water jet machining of aluminium/magnesium hybrid metal matrix composites[J].Materials Today:Proceedings,2020,27:1293-1298.
[4] 石明,汪舟,甘进,等.基于GA-BP神经网络的喷丸样品表层硬度预测模型[J].表面技术,2022,51(1):332-338,357.
[5] BALAJI D S,JEYAPOOVAN T.Multi-objective optimization in abrasive water jet peening on AA6063 alloy[J].Materials Today:Proceedings,2021,45:1928-1933.
[6] 吴少杰,刘怀举,张仁华,等.基于正交实验和数据驱动的喷丸表面完整性参数预测[J].表面技术,2021,50(4):86-95.
[7] MANOJ M,JINU G R,KUMAR J S.Process Optimization of Abrasive Water Jet Machining of Aluminum Hybrid Composite Using Taguchi DEAR Methodology[J].International Journal of Metalcasting,2024,18(2):933-943.
[8] 刘新,尹康达,寇海川.基于GA-GRNN的地震震级预测模型[J].华北地震科学,2023,41(2):37-42.
[9] 徐智超,杜茂华,栾建举,等.基于广义神经网络多目标铣削参数自适应研究[J].工具技术,2021,55(4):13-17.
[10] WANG Z,MULYANTO J A,ZHENG C,et al.Research on a surrogate model updating-based efficient multi-objective optimization framework for supertall buildings[J].Journal of Building Engineering,2023,72:106702.
[11] ZHONG L,LIU R,MIAO X,et al.Compressor Performance Prediction based on the Interpolation Method and Support Vector Machine[J].Aerospace,2023,10(6):558.
[12] 李全来,李长林,陶春生.微磨料气射流成形加工表面波纹度研究[J].现代制造工程,2017(6):114-120.
[13] BENDU H,DEEPAK B,MURUGAN S.Application of GRNN for the prediction of performance and exhaust emissions in HCCI engine using ethanol[J].Energy conversion and management,2016,122:165-173.
[14] 董慧芬,代玉行,王渗.基于GA-GRNN-GA的飞机发动机风扇叶片清洗参数优化[J].计算机应用与软件,2020,37(1):87-92,127.

[1]	廖雪超, 向桂宏, 阮兵, 田芮利, 钟实. 带AGV数量约束的柔性作业车间调度问题研究^*[J]. 现代制造工程, 2025, 537(6): 11-21.
[2]	李建儒, 龚堰珏, 赵罘. 基于混合遗传粒子群算法的机器人关节空间轨迹规划^*[J]. 现代制造工程, 2025, 537(6): 84-91.
[3]	陈德海, 田森焱, 李志军, 王海峰. 基于解析计算与遗传算法的永磁同步电机偏心磁极优化设计^*[J]. 现代制造工程, 2025, 536(5): 153-160.
[4]	刘晋飞, 刘乙涵, 陈明, 黄华. 基于改进IGA的多品种变批量智能车间调度^*[J]. 现代制造工程, 2025, 535(4): 1-10.
[5]	王春, 张朝阳, 吉卫喜, 卢璟钰. 考虑设备退化的离散车间生产排程优化研究^*[J]. 现代制造工程, 2025, 534(3): 31-40.
[6]	黄开启, 胡智强. 矿用自卸车互联油气悬架参数多目标优化[J]. 现代制造工程, 2025, 534(3): 124-131.
[7]	李俊聪, 黄翔, 曾京, 汪群生. 高速列车蛇行稳定性自适应控制策略研究^*[J]. 现代制造工程, 2025, 533(2): 61-68.
[8]	霍俊杰, 王志坚. 采用新编码GA的工艺规划与车间调度集成优化^*[J]. 现代制造工程, 2024, 528(9): 25-33.
[9]	杨兴臣, 苌道方. 有限缓冲区下多汽车工厂协同混流排产研究[J]. 现代制造工程, 2024, 527(8): 9-18.
[10]	裴红蕾. 具有串并行异类工序约束的多柔性车间联合调度^*[J]. 现代制造工程, 2024, 525(6): 15-21.
[11]	袁东维, 凤飞龙. 工业互联网环境下基于协作度的制造服务组合推荐方法^*[J]. 现代制造工程, 2024, 525(6): 69-74.
[12]	张殷晨, 左鹏奇, 王逸飞, 林楠, 谢润, 金立军. 基于遗传算法的家电智能生产线分布式资源调度算法设计^*[J]. 现代制造工程, 2024, 524(5): 31-38.
[13]	周兴明, 周井玲. 复合载荷作用下H型垂直轴风力机叶片结构多目标优化^*[J]. 现代制造工程, 2024, 523(4): 153-159.
[14]	景湉佳, 贾世会, 迟晓妮, 唐秋华. 基于线性加权和法的装配线平衡问题求解^*[J]. 现代制造工程, 2024, 522(3): 8-14.
[15]	张国顺, 罗建国, 张建, 傅爱军, 杨晋博. 某车型排气系统隔振性能及优化研究^*[J]. 现代制造工程, 2024, 522(3): 62-69.

基于GA-GRNN的AWJ强化3D打印AlSi10Mg表面性能实验研究^*

Experimental study on the surface properties of AWJ surface strengthening 3D printed AlSi10Mg based on GA-GRNN

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics