The model of heat source(MHS) which reflects the thermal interaction between materials and laser during processing determines the accuracy of simulation results. To acquire desirable simulations results, although vari...The model of heat source(MHS) which reflects the thermal interaction between materials and laser during processing determines the accuracy of simulation results. To acquire desirable simulations results, although various modifications of heat sources in the aspect of absorption process of laser by materials have been purposed, the distribution of laser power density(DLPD) in MHS is still modeled theoretically. However, in the actual situations of laser processing, the DLPD is definitely different from the ideal models. So, it is indispensable to build MHS using actual DLPD to improve the accuracy of simulation results. Besides, an automatic modeling method will be benefit to simplify the tedious pre-processing of simulations. This paper presents a modeling method and corresponding algorithm to model heat source using measured DLPD. This algorithm automatically processes original data to get modeling parameters and provides a step MHS combining with absorption models. Simulations and experiments of heat transfer in steel plates irradiated by laser prove the mothed and the step MHS. Moreover, the investigations of laser induced thermal-crack propagation in glass highlight the signification of modeling heat source based on actual DLPD and demonstrate the enormous application of this method in the simulation of laser processing.展开更多
In this work,the nickel-based powder metallurgy superalloy FGH95 was selected as experimental material,and the experimental parameters in multiple overlap laser shock processing(LSP)treatment were selected based on or...In this work,the nickel-based powder metallurgy superalloy FGH95 was selected as experimental material,and the experimental parameters in multiple overlap laser shock processing(LSP)treatment were selected based on orthogonal experimental design.The experimental data of residual stress and microhardness were measured in the same depth.The residual stress and microhardness laws were investigated and analyzed.Artificial neural network(ANN)with four layers(4-N-(N-1)-2)was applied to predict the residual stress and microhardness of FGH95 subjected to multiple overlap LSP.The experimental data were divided as training-testing sets in pairs.Laser energy,overlap rate,shocked times and depth were set as inputs,while residual stress and microhardness were set as outputs.The prediction performances with different network configuration of developed ANN models were compared and analyzed.The developed ANN model with network configuration of 4-7-6-2 showed the best predict performance.The predicted values showed a good agreement with the experimental values.In addition,the correlation coefficients among all the parameters and the effect of LSP parameters on materials response were studied.It can be concluded that ANN is a useful method to predict residual stress and microhardness of material subjected to LSP when with limited experimental data.展开更多
Surface microstructure and mechanical properties of pearlitic Fe–0.8%C(mass fraction) steel after laser shock processing(LSP) with different laser pulse energies were investigated by scanning electron microscopy(SEM)...Surface microstructure and mechanical properties of pearlitic Fe–0.8%C(mass fraction) steel after laser shock processing(LSP) with different laser pulse energies were investigated by scanning electron microscopy(SEM),transmission electron microscopy(TEM),X-ray diffraction(XRD) and microhardness measurements.After LSP,the cementite lamellae were bent,kinked and broken into particles.Fragmentation and dissolution of the cementite lamellae were enhanced by increasing the laser pulse energy.Due to the dissolution of carbon atoms in the ferritic matrix,the lattice parameter of α-Fe increased.The grain size of the surface ferrite was refined,and the microstructure changed from lamellae to ultrafine micro-duplex structure(ferrite(α)+cementite(θ)) with higher laser pulse energy,accompanied by the residual stress and microhardness increase.展开更多
Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification...Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.展开更多
基金Project(2021YFF0500200) supported by the National Key R&D Program of ChinaProject(52105437) supported by the National Natural Science Foundation of China+1 种基金Project(202006120184) supported by the Heilongjiang Provincial Postdoctoral Science Foundation,ChinaProject(LBH-Z20054) supported by the China Scholarship Council。
文摘The model of heat source(MHS) which reflects the thermal interaction between materials and laser during processing determines the accuracy of simulation results. To acquire desirable simulations results, although various modifications of heat sources in the aspect of absorption process of laser by materials have been purposed, the distribution of laser power density(DLPD) in MHS is still modeled theoretically. However, in the actual situations of laser processing, the DLPD is definitely different from the ideal models. So, it is indispensable to build MHS using actual DLPD to improve the accuracy of simulation results. Besides, an automatic modeling method will be benefit to simplify the tedious pre-processing of simulations. This paper presents a modeling method and corresponding algorithm to model heat source using measured DLPD. This algorithm automatically processes original data to get modeling parameters and provides a step MHS combining with absorption models. Simulations and experiments of heat transfer in steel plates irradiated by laser prove the mothed and the step MHS. Moreover, the investigations of laser induced thermal-crack propagation in glass highlight the signification of modeling heat source based on actual DLPD and demonstrate the enormous application of this method in the simulation of laser processing.
基金Projects(51875558,51471176)supported by the National Natural Science Foundation of ChinaProject(2017YFB1302802)supported by the National Key R&D Program of China。
文摘In this work,the nickel-based powder metallurgy superalloy FGH95 was selected as experimental material,and the experimental parameters in multiple overlap laser shock processing(LSP)treatment were selected based on orthogonal experimental design.The experimental data of residual stress and microhardness were measured in the same depth.The residual stress and microhardness laws were investigated and analyzed.Artificial neural network(ANN)with four layers(4-N-(N-1)-2)was applied to predict the residual stress and microhardness of FGH95 subjected to multiple overlap LSP.The experimental data were divided as training-testing sets in pairs.Laser energy,overlap rate,shocked times and depth were set as inputs,while residual stress and microhardness were set as outputs.The prediction performances with different network configuration of developed ANN models were compared and analyzed.The developed ANN model with network configuration of 4-7-6-2 showed the best predict performance.The predicted values showed a good agreement with the experimental values.In addition,the correlation coefficients among all the parameters and the effect of LSP parameters on materials response were studied.It can be concluded that ANN is a useful method to predict residual stress and microhardness of material subjected to LSP when with limited experimental data.
基金Projects(50801021,51201061)supported by the National Natural Science Foundation of ChinaProject(144200510009)supported by the Henan Province Program for Science and Technology Innovation Excellent Talents,China+1 种基金Project(152102210077)supported by the Science and Technology Project of Henan Province,ChinaProject(2015XTD006)supported by the Science and Technology Innovation Team of Henan University of Science and Technology,China
文摘Surface microstructure and mechanical properties of pearlitic Fe–0.8%C(mass fraction) steel after laser shock processing(LSP) with different laser pulse energies were investigated by scanning electron microscopy(SEM),transmission electron microscopy(TEM),X-ray diffraction(XRD) and microhardness measurements.After LSP,the cementite lamellae were bent,kinked and broken into particles.Fragmentation and dissolution of the cementite lamellae were enhanced by increasing the laser pulse energy.Due to the dissolution of carbon atoms in the ferritic matrix,the lattice parameter of α-Fe increased.The grain size of the surface ferrite was refined,and the microstructure changed from lamellae to ultrafine micro-duplex structure(ferrite(α)+cementite(θ)) with higher laser pulse energy,accompanied by the residual stress and microhardness increase.
文摘Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.
