基于神经网络的宽带激光熔覆熔池特征参数预测
|
摘要
为了实现宽带激光熔覆熔池特征的准确预测,从而对激光熔覆工艺过程进行实时监测、评价及反馈控制。通过宽带激光熔覆全因素工艺试验采集熔池特征参数样本数据,采用遗传算法优化BP神经网络的初始权值和初始阈值,建立激光熔覆工艺参数(激光功率、粉末厚度、扫描速度)与熔池特征参数之间的BP神经网络预测模型。利用训练集数据对所建立的神经网络进行训练,形成输入与输出之间的映射关系,并利用测试集数据对网络进行测试。试验结果表明,宽带激光熔覆熔池特征参数神经网络预测模型具有很高的精度。该神经网络预测模型对激光熔覆过程监测及熔覆层质量控制具有重要意义。
In order to realize the accurate prediction on characteristics of molten pool in wide-band laser cladding,and achieve the real-time detection,evaluation and closed-loop control of laser cladding,a full factorial design method is used to conduct the experiments,and the experimental results are chosen randomly as sample data for neural network.Genetic algorithm is utilized to optimize the initial weights and thresholds of back propagation(BP)neural network.The BP neural network prediction model is developed to express the relationship between the process parameters(laser power,powder thickness,scanning speed)and the characteristics of molten pool.The training set of data obtained in experiments is used to train the neural network to establish the perfect mapping relation between input and output of network.The testing set of data is used to verify the performance of the trained network.Simulation results indicate that the prediction model of characteristic parameters of molten pool in wide-band laser cladding has sufficient accuracy.The neural network prediction model is of great significance for the realtime monitoring of laser cladding process and the quality control of cladding layers.
In order to realize the accurate prediction on characteristics of molten pool in wide-band laser cladding,and achieve the real-time detection,evaluation and closed-loop control of laser cladding,a full factorial design method is used to conduct the experiments,and the experimental results are chosen randomly as sample data for neural network.Genetic algorithm is utilized to optimize the initial weights and thresholds of back propagation(BP)neural network.The BP neural network prediction model is developed to express the relationship between the process parameters(laser power,powder thickness,scanning speed)and the characteristics of molten pool.The training set of data obtained in experiments is used to train the neural network to establish the perfect mapping relation between input and output of network.The testing set of data is used to verify the performance of the trained network.Simulation results indicate that the prediction model of characteristic parameters of molten pool in wide-band laser cladding has sufficient accuracy.The neural network prediction model is of great significance for the realtime monitoring of laser cladding process and the quality control of cladding layers.
引文
[1] Yang J,Han J,Yu H,et al.Role of molten pool mode on formability,microstructure and mechanical properties of selective laser melted Ti-6Al-4V alloy[J].Materials&Design,2016,110:558-570.
[2] Liu J,Yu H,Chen C,et al.Research and development status of laser cladding on magnesium alloys:A review[J].Optics and Lasers in Engineering,2017,93:195-210.
[3] Riveiro A,Mejías A,Lusqui珘nos F,et al.Laser cladding of aluminium on AISI 304 stainless steel with high-power diode lasers[J].Surface and Coatings Technology,2014,253:214-220.
[4] Liu W,Tang Z,Liu X,et al.A review on in-situ monitoring and adaptive control technology for laser cladding remanufacturing[J].Procedia CIRP,2017,61:235-240.
[5] Heeling T,Cloots M,Wegener K.Melt pool simulation for the evaluation of process parameters in selective laser melting[J].Additive Manufacturing,2017,14:116-125.
[6] Lei K,Qin X,Liu H,et al.Analysis and modeling of melt pool morphology for high power diode laser cladding with a rectangle beam spot[J].Optics and Lasers in Engineering,2018,110(11):89-99.
[7] Liu H,Qin X,Huang S,et al.Geometry modeling of single track cladding deposited by high power diode laser with rectangular beam spot[J].Optics and Lasers in Engineering,2018,100:38-46.
[8] Akbari M,Saedodin S,Panjehpour A,et al.Numerical simulation and designing artificial neural network for estimating melt pool geometry and temperature distribution in laser welding of Ti6Al4V alloy[J].Optik-International Journal for Light and Electron Optics,2016,127(23):11161-11172.
[9] Li K,Yan S,Pan W,et al.Warpage optimization of fiberreinforced composite injection molding by combining back propagation neural network and genetic algorithm[J].The International Journal of Advanced Manufacturing Technology,2017,90(1-4):963-970.
[10]Mondal S,Bandyopadhyay A,Pal P K.Application of artificial neural network for the prediction of laser cladding process characteristics at Taguchi-based optimized condition[J].The International Journal of Advanced Manufacturing Technology,2014,70(9-12):2151-2158.
[11]Ni Li-bin,Liu Ji-chang,Wu Yao-ting,et al.Optimization of laser cladding process variables based on neural network and particle swarm optimization algorithms[J].Chinese journal of lasers,2011,(2):99-104.
[12]Sathiya P,Panneerselvam K,Soundararajan R.Optimal design for laser beam butt welding process parameter using artificial neural networks and genetic algorithm for super austenitic stainless steel[J].Optics&Laser Technology,2012,44(6):1905-1914.
[13]Sathiya P,Panneerselvam K,Abdul Jaleel M Y.Optimization of laser welding process parameters for super austenitic stainless steel using artificial neural networks and genetic algorithm[J].Materials&Design(1980-2015),2012,36:490-498.
[14]Yin F,Mao H,Hua L.A hybrid of back propagation neural network and genetic algorithm for optimization of injection molding process parameters[J].Materials&Design,2011,32(6):3457-3464.
[15]Yin F,Mao H,Hua L,et al.Back Propagation neural network modeling for warpage prediction and optimization of plastic products during injection molding[J].Materials&Design,2011,32(4):1844-1850.
[16]Yang J,Han J,Yu H,et al.Role of molten pool mode on formability,microstructure and mechanical properties of selective laser melted Ti-6Al-4V alloy[J].Materials&Design.2016,110:558-570.
[17]LEI Kai-yun,QIN Xun-peng,LIU Hua-ming,et al.Weld pool edge extraction in wide-band laser cladding based on local region active contour model[J].Journal of Optoelectronics·Laser,2018,29(5):516-522.雷凯文,秦训鹏,刘华明,等.基于局部主动轮廓模型的宽带激光熔覆熔池边缘提取[J].光电子·激光,2018,29(5):516-522.
[18]ZHENG Qiang,DONG En-qing.Narrow band active contour model for local segmentation of medical and texture images[J].Acta automatica sinica,2013,39(1):21-30.
[19]Criales L E,Ar1soy Y M,Lane B,et al.Laser powder bed fusion of nickel alloy 625:Experimental investigations of effects of process parameters on melt pool size and shape with spatter analysis[J].International Journal of Machine Tools and Manufacture,2017,121:22-36.
[20]Yong Y,Fu W,Deng Q,et al.A comparative study of vision detection and numerical simulation for laser cladding of nickel-based alloy[J].Journal of Manufacturing Processes,2017,28:364-372.
[21]Liu H,Qin X,Huang S,et al.Geometry characteristics prediction of single track cladding deposited by high power diode laser based on genetic algorithm and neural network[J].International Journal of Precision Engineering&Manufacturing,2018,19(7):1061-1070.
[2] Liu J,Yu H,Chen C,et al.Research and development status of laser cladding on magnesium alloys:A review[J].Optics and Lasers in Engineering,2017,93:195-210.
[3] Riveiro A,Mejías A,Lusqui珘nos F,et al.Laser cladding of aluminium on AISI 304 stainless steel with high-power diode lasers[J].Surface and Coatings Technology,2014,253:214-220.
[4] Liu W,Tang Z,Liu X,et al.A review on in-situ monitoring and adaptive control technology for laser cladding remanufacturing[J].Procedia CIRP,2017,61:235-240.
[5] Heeling T,Cloots M,Wegener K.Melt pool simulation for the evaluation of process parameters in selective laser melting[J].Additive Manufacturing,2017,14:116-125.
[6] Lei K,Qin X,Liu H,et al.Analysis and modeling of melt pool morphology for high power diode laser cladding with a rectangle beam spot[J].Optics and Lasers in Engineering,2018,110(11):89-99.
[7] Liu H,Qin X,Huang S,et al.Geometry modeling of single track cladding deposited by high power diode laser with rectangular beam spot[J].Optics and Lasers in Engineering,2018,100:38-46.
[8] Akbari M,Saedodin S,Panjehpour A,et al.Numerical simulation and designing artificial neural network for estimating melt pool geometry and temperature distribution in laser welding of Ti6Al4V alloy[J].Optik-International Journal for Light and Electron Optics,2016,127(23):11161-11172.
[9] Li K,Yan S,Pan W,et al.Warpage optimization of fiberreinforced composite injection molding by combining back propagation neural network and genetic algorithm[J].The International Journal of Advanced Manufacturing Technology,2017,90(1-4):963-970.
[10]Mondal S,Bandyopadhyay A,Pal P K.Application of artificial neural network for the prediction of laser cladding process characteristics at Taguchi-based optimized condition[J].The International Journal of Advanced Manufacturing Technology,2014,70(9-12):2151-2158.
[11]Ni Li-bin,Liu Ji-chang,Wu Yao-ting,et al.Optimization of laser cladding process variables based on neural network and particle swarm optimization algorithms[J].Chinese journal of lasers,2011,(2):99-104.
[12]Sathiya P,Panneerselvam K,Soundararajan R.Optimal design for laser beam butt welding process parameter using artificial neural networks and genetic algorithm for super austenitic stainless steel[J].Optics&Laser Technology,2012,44(6):1905-1914.
[13]Sathiya P,Panneerselvam K,Abdul Jaleel M Y.Optimization of laser welding process parameters for super austenitic stainless steel using artificial neural networks and genetic algorithm[J].Materials&Design(1980-2015),2012,36:490-498.
[14]Yin F,Mao H,Hua L.A hybrid of back propagation neural network and genetic algorithm for optimization of injection molding process parameters[J].Materials&Design,2011,32(6):3457-3464.
[15]Yin F,Mao H,Hua L,et al.Back Propagation neural network modeling for warpage prediction and optimization of plastic products during injection molding[J].Materials&Design,2011,32(4):1844-1850.
[16]Yang J,Han J,Yu H,et al.Role of molten pool mode on formability,microstructure and mechanical properties of selective laser melted Ti-6Al-4V alloy[J].Materials&Design.2016,110:558-570.
[17]LEI Kai-yun,QIN Xun-peng,LIU Hua-ming,et al.Weld pool edge extraction in wide-band laser cladding based on local region active contour model[J].Journal of Optoelectronics·Laser,2018,29(5):516-522.雷凯文,秦训鹏,刘华明,等.基于局部主动轮廓模型的宽带激光熔覆熔池边缘提取[J].光电子·激光,2018,29(5):516-522.
[18]ZHENG Qiang,DONG En-qing.Narrow band active contour model for local segmentation of medical and texture images[J].Acta automatica sinica,2013,39(1):21-30.
[19]Criales L E,Ar1soy Y M,Lane B,et al.Laser powder bed fusion of nickel alloy 625:Experimental investigations of effects of process parameters on melt pool size and shape with spatter analysis[J].International Journal of Machine Tools and Manufacture,2017,121:22-36.
[20]Yong Y,Fu W,Deng Q,et al.A comparative study of vision detection and numerical simulation for laser cladding of nickel-based alloy[J].Journal of Manufacturing Processes,2017,28:364-372.
[21]Liu H,Qin X,Huang S,et al.Geometry characteristics prediction of single track cladding deposited by high power diode laser based on genetic algorithm and neural network[J].International Journal of Precision Engineering&Manufacturing,2018,19(7):1061-1070.