• 中文核心期刊
  • CSCD中国科学引文数据库来源期刊
  • 中国科技核心期刊
  • 中国机械工程学会材料分会会刊
Advanced Search
LIU Haomin, YANG Hongcai, LIU Zhan, LI Ziwei, SUN Junhua, ZHANG Yuanbin. Backpropagation Neural Network Prediction Model of Arc Additive Manufacturing Weld Size Base on Particle Swarm Optimization Algorithm[J]. Materials and Mechanical Engineering, 2024, 48(2): 97-102. DOI: 10.11973/jxgccl202402015
Citation: LIU Haomin, YANG Hongcai, LIU Zhan, LI Ziwei, SUN Junhua, ZHANG Yuanbin. Backpropagation Neural Network Prediction Model of Arc Additive Manufacturing Weld Size Base on Particle Swarm Optimization Algorithm[J]. Materials and Mechanical Engineering, 2024, 48(2): 97-102. DOI: 10.11973/jxgccl202402015

Backpropagation Neural Network Prediction Model of Arc Additive Manufacturing Weld Size Base on Particle Swarm Optimization Algorithm

More Information
  • Received Date: April 10, 2023
  • Revised Date: January 26, 2024
  • With welding current, wire feed speed, welding speed and substrate temperature as input variables, weld width and residual height as output variables, and the 4-12-2 structure particle swarm optimization backpropagation(PSO-BP)neural network model of melt intert-gas welding arc additive manufacturing 316L stainess steel was built with optimal particle inertia weight and learning factor in PSO algorithm. The results show that the root-mean-square error, maximum relative error and average relative error of predicted weld width obtained by PSO-BP neural network model and expected values were 0.386, 13.477% and 2.580%, and those of weld reinforcement were 0.152, 10.372% and 2.810%, respectively. Compared with BP neural network model, PSO-BP neural network model had higher prediction accuracy and stronger stability for the prediction of weld size.

  • [1]
    关桥. 焊接/连接与增材制造(3D打印)[J]. 焊接, 2014(5): 1-8.

    GUAN Q. Welding/joining technologies and additive manufacturing (3D pinting)[J]. Welding & Joining, 2014(5): 1-8.
    [2]
    林泓延, 姚屏, 李道良, 等. 机器人电弧增材制造技术研究现状与趋势[J]. 自动化与信息工程, 2019, 40(6): 8-19.

    LIN H Y, YAO P, LI D L, et al. Research status and trend of arc additive manufacturing technology for robot[J]. Automation & Information Engineering, 2019, 40(6): 8-19.
    [3]
    姜淑馨, 李峰光. 丝材电弧增材制造技术的研究与应用[J]. 铸造技术, 2022, 43(5): 369-374.

    JIANG S X, LI F G. Research and application of wire and arc additive manufacturing technology[J]. Foundry Technology, 2022, 43(5): 369-374.
    [4]
    KARUNAKARAN K P, SURYAKUMAR S, PUSHPA V, et al. Low cost integration of additive and subtractive processes for hybrid layered manufacturing[J]. Robotics and Computer-Integrated Manufacturing, 2010, 26(5): 490-499.
    [5]
    田彩兰, 陈济轮, 董鹏, 等. 国外电弧增材制造技术的研究现状及展望[J]. 航天制造技术, 2015(2): 57-60.

    TIAN C L, CHEN J L, DONG P, et al. Current state and future development of the wire arc additive manufacture technology abroad[J]. Aerospace Manufacturing Technology, 2015(2): 57-60.
    [6]
    田根, 王文宇, 常青, 等. 电弧增材制造技术研究现状及展望[J]. 材料导报, 2021, 35(23): 23131-23141.

    TIAN G, WANG W Y, CHANG Q, et al. Research progress and prospect of wire and arc additive manufacture[J]. Materials Reports, 2021, 35(23): 23131-23141.
    [7]
    NIKAM S H, JAIN N K. 3D-finite element simulation and image processing based prediction of width and height of single-layer deposition by micro-plasma-transferred arc process[J]. The International Journal of Advanced Manufacturing Technology, 2018, 95(9): 3679-3691.
    [8]
    CHEN K, CHEN H B, LIU L, et al. Prediction of weld bead geometry of MAG welding based on XGBoost algorithm[J]. The International Journal of Advanced Manufacturing Technology, 2019, 101(9): 2283-2295.
    [9]
    胡建文GMAW快速成形熔敷焊道尺寸神经网络建模和参数预测哈尔滨哈尔滨工业大学2012胡建文. GMAW快速成形熔敷焊道尺寸神经网络建模和参数预测[D]. 哈尔滨: 哈尔滨工业大学, 2012.

    HU J WWeld bead size modeling and parameter prediction for gmaw-based rapid manufacturing through a neural networkHarbinHarbin Institute of Technology2012HU J W. Weld bead size modeling and parameter prediction for gmaw-based rapid manufacturing through a neural network[D]. Harbin: Harbin Institute of Technology, 2012.
    [10]
    黄无云, 刘益剑, 刘宗熙, 等. 焊道形貌特征的BP神经网络建模与预测[J]. 南京师范大学学报(工程技术版), 2021, 21(1): 1-7.

    HUANG W Y, LIU Y J, LIU Z X, et al. Welded surface morphology modeling and prediction based on BP neural network[J]. Journal of Nanjing Normal University (Engineering and Technology Edition), 2021, 21(1): 1-7.
    [11]
    王晓光, 刘奋成, 方平, 等. CMT电弧增材制造316L不锈钢成形精度与组织性能分析[J]. 焊接学报, 2019, 40(5): 100-106.

    WANG X G, LIU F C, FANG P, et al. Forming accuracy and properties of wire arc additive manufacturing of 316L components using CMT process[J]. Transactions of the China Welding Institution, 2019, 40(5): 100-106.
    [12]
    CHUAIPHAN W, SRIJAROENPRAMONG L. Optimization of gas tungsten arc welding parameters for the dissimilar welding between AISI 304 and AISI 201 stainless steels[J]. Defence technology, 2019, 15(2): 170-178.
    [13]
    SADA S O O, ACHEBO J. Optimisation and prediction of the weld bead geometry of a mild steel metal inert gas weld[J]. Advances in Materials and Processing Technologies, 2022, 8(2): 1625-1634.
    [14]
    SAFARI S, HAJILOUNEZHAD T, ALI EHYAEI M. Multi-objective optimization of solid oxide fuel cell/gas turbine combined heat and power system: A comparison between particle swarm and genetic algorithms[J]. International Journal of Energy Research, 2020, 44(11): 9001-9020.
    [15]
    AMER M, MAUL T. A review of modularization techniques in artificial neural networks[J]. Artificial Intelligence Review, 2019, 52(1): 527-561.
    [16]
    万海超, 何勇. 基于改进PSO-BP神经网络的电锭细纱机的PID控制[J]. 制造业自动化, 2023, 45(2): 159-163.

    WAN H C, HE Y. PID control of spinning frame based on improved PSO-BP neural network[J]. Manufacturing Automation, 2023, 45(2): 159-163.

Catalog

    Article views (12) PDF downloads (5) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return