Studies on ballistic penetration to laminates is complicated,but important for design effective protection of structures.Experimental means of study is expensive and can often be dangerous.Numerical simulation has bee...Studies on ballistic penetration to laminates is complicated,but important for design effective protection of structures.Experimental means of study is expensive and can often be dangerous.Numerical simulation has been an excellent supplement,but the computation is time-consuming.Main aim of this thesis was to develop and test an effective tool for real-time prediction of projectile penetrations to laminates by training a neural network and a decision tree regression model.A large number of finite element models were developed;the residual velocities of projectiles from finite element simulations were used as the target data and processed to produce sufficient number of training samples.Study focused on steel 4340tpolyurea laminates with various configurations.Four different 3D shapes of the projectiles were modeled and used in the training.The trained neural network and decision tree model was tested using independently generated test samples using finite element models.The predicted projectile velocity values using the trained machine learning models are then compared with the finite element simulation to verify the effectiveness of the models.Additionally,both models were trained using a published experimental data of projectile impacts to predict residual velocity of projectiles for the unseen samples.Performance of both the models was evaluated and compared.Models trained with Finite element simulation data samples were found capable to give more accurate predication,compared to the models trained with experimental data,because finite element modeling can generate much larger training set,and thus finite element solvers can serve as an excellent teacher.This study also showed that neural network model performs better with small experimental dataset compared to decision tree regression model.展开更多
We propose a large combined moving component composed of carbon fiber reinforced polymer(CFRP)laminates for making lightweight machine tools with high dynamic performance.The accurate dynamic prediction of composite m...We propose a large combined moving component composed of carbon fiber reinforced polymer(CFRP)laminates for making lightweight machine tools with high dynamic performance.The accurate dynamic prediction of composite machine tools is essential for the new generation machine tool.This paper aims to address two challenges in numerical dynamic modeling and the design of composite machine tools to enhance development efficiency.(1)Anisotropic composite laminates,which form the composite machine tool,exhibit coupling in various directions.We propose the generalized continuity condition of the boundary to tackle this dynamic modeling challenge.(2)Composite machine tools feature numerous composite-metal coupled structures.The mechanical model correction of isotropic metals is performed to address their dynamics.We take the example of a five-axis gantry machine tool with composite moving parts,establish a dynamic model for efficient prediction,and verify it through simulation and experimentation.The proposed method yields remarkable results,with an average relative error of only 3.85%in modal frequency prediction and a staggering 99.7%reduction in solution time compared to finite element analysis.We further discuss the dynamic performance of the machine tool under varied stacking angles and layer numbers of the composite machine tool.We propose general design criteria for composite machine tools to consider the modal frequency and manufacturing cost of machine tools.展开更多
文摘Studies on ballistic penetration to laminates is complicated,but important for design effective protection of structures.Experimental means of study is expensive and can often be dangerous.Numerical simulation has been an excellent supplement,but the computation is time-consuming.Main aim of this thesis was to develop and test an effective tool for real-time prediction of projectile penetrations to laminates by training a neural network and a decision tree regression model.A large number of finite element models were developed;the residual velocities of projectiles from finite element simulations were used as the target data and processed to produce sufficient number of training samples.Study focused on steel 4340tpolyurea laminates with various configurations.Four different 3D shapes of the projectiles were modeled and used in the training.The trained neural network and decision tree model was tested using independently generated test samples using finite element models.The predicted projectile velocity values using the trained machine learning models are then compared with the finite element simulation to verify the effectiveness of the models.Additionally,both models were trained using a published experimental data of projectile impacts to predict residual velocity of projectiles for the unseen samples.Performance of both the models was evaluated and compared.Models trained with Finite element simulation data samples were found capable to give more accurate predication,compared to the models trained with experimental data,because finite element modeling can generate much larger training set,and thus finite element solvers can serve as an excellent teacher.This study also showed that neural network model performs better with small experimental dataset compared to decision tree regression model.
基金supported by the National Natural Science Foundation of China(Grant No.U21B2081)。
文摘We propose a large combined moving component composed of carbon fiber reinforced polymer(CFRP)laminates for making lightweight machine tools with high dynamic performance.The accurate dynamic prediction of composite machine tools is essential for the new generation machine tool.This paper aims to address two challenges in numerical dynamic modeling and the design of composite machine tools to enhance development efficiency.(1)Anisotropic composite laminates,which form the composite machine tool,exhibit coupling in various directions.We propose the generalized continuity condition of the boundary to tackle this dynamic modeling challenge.(2)Composite machine tools feature numerous composite-metal coupled structures.The mechanical model correction of isotropic metals is performed to address their dynamics.We take the example of a five-axis gantry machine tool with composite moving parts,establish a dynamic model for efficient prediction,and verify it through simulation and experimentation.The proposed method yields remarkable results,with an average relative error of only 3.85%in modal frequency prediction and a staggering 99.7%reduction in solution time compared to finite element analysis.We further discuss the dynamic performance of the machine tool under varied stacking angles and layer numbers of the composite machine tool.We propose general design criteria for composite machine tools to consider the modal frequency and manufacturing cost of machine tools.
