Constitutive modeling is crucial for engineering design and simulations to accurately describe material behavior.However,traditional phenomenological models often struggle to capture the complexities of real materials...Constitutive modeling is crucial for engineering design and simulations to accurately describe material behavior.However,traditional phenomenological models often struggle to capture the complexities of real materials under varying stress conditions due to their fixed forms and limited parameters.While recent advances in deep learning have addressed some limitations of classical models,purely data-driven methods tend to require large data sets,lack interpretability,and struggle to generalize beyond their training data.To tackle these issues,we introduce“Fusion-based Constitutive model(FuCe):Toward model-data augmentation in constitutive modeling.”This approach combines established phenomenological models with an Input Convex Neural Network architecture,designed to train on the limited and noisy force-displacement data typically available in practical applications.The hybrid model inherently adheres to necessary constitutive conditions.During inference,Monte Carlo dropout is employed to generate Bayesian predictions,providing mean values and confidence intervals that quantify uncertainty.We demonstrate the model's effectiveness by learning two isotropic constitutive models and one anisotropic model with a single fiber direction,across six different stress states.The framework's applicability is also showcased in finite element simulations across three geometries of varying complexities.Our results highlight the framework's superior extrapolation capabilities,even when trained on limited and noisy data,delivering accurate and physically meaningful predictions across all numerical examples.展开更多
The present work reports the inclusion of different proportions of Mango/Sheesham/Mahogany/Babool dust to polypropylene for improving mechanical,wear behavior and biodegradability of wood-plastic composite(WPC).The wo...The present work reports the inclusion of different proportions of Mango/Sheesham/Mahogany/Babool dust to polypropylene for improving mechanical,wear behavior and biodegradability of wood-plastic composite(WPC).The wood dust(10%,15%,20%by weight)was mixed with polypropylene granules and WPCs were prepared using an injection molding technique.The mechanical,wear,and morphological characterizations of fabricated WPCs were carried out using standard ASTM methods,pin on disk apparatus,and scanning electron microscopy(SEM),respectively.Further,the biodegradability and resistance to natural weathering of WPCs were evaluated following ASTM D5338-11 and ASTM D1435-99,respectively.The WPCs consisting ofBabool and Sheesham dust were having superior mechanical properties whereas the WPCs consisting of Mango and Mahogany were more wear resistant.It was found that increasing wood powder proportion results in higher Young's modulus,lesser wear rate,and decreased stress at break.The WPCs made of Sheesham dust were least biodegradable.It was noticed that the biodegradability corresponds with resistance to natural weathering;more biodegradable WPCs were having the lesser resistance to natural weathering.展开更多
After publication of our article[1],the authors became aware that they had omitted to include the credit line for Fig.1[2].The corrected Fig.1 caption with the credit line is given below:“Fig.1(a)Photograph of wood-p...After publication of our article[1],the authors became aware that they had omitted to include the credit line for Fig.1[2].The corrected Fig.1 caption with the credit line is given below:“Fig.1(a)Photograph of wood-plastic composite samples;(b)photographs of experimental setups used 1)pin on disk,2)tensile testing,3)three-point bending,4)impact,5)injection molding,6)effect of weathering[12].Reprinted from Construction and Building Materials,172,Thanate Ratanawilai,Kampanart Taneerat,Alternative polymeric matrices for wood-plastic composites:Effects on mechanical properties and resistance to natural weathering,349–357,Copyright(2018),with permission from Elsevier.”展开更多
基金Anusandhan National Research Foundation(ANRF)via grant no.CRG/2023/007667 and from the Ministry of Port,Shipping,and Waterways via letter no.ST-14011/74/MT(356529).
文摘Constitutive modeling is crucial for engineering design and simulations to accurately describe material behavior.However,traditional phenomenological models often struggle to capture the complexities of real materials under varying stress conditions due to their fixed forms and limited parameters.While recent advances in deep learning have addressed some limitations of classical models,purely data-driven methods tend to require large data sets,lack interpretability,and struggle to generalize beyond their training data.To tackle these issues,we introduce“Fusion-based Constitutive model(FuCe):Toward model-data augmentation in constitutive modeling.”This approach combines established phenomenological models with an Input Convex Neural Network architecture,designed to train on the limited and noisy force-displacement data typically available in practical applications.The hybrid model inherently adheres to necessary constitutive conditions.During inference,Monte Carlo dropout is employed to generate Bayesian predictions,providing mean values and confidence intervals that quantify uncertainty.We demonstrate the model's effectiveness by learning two isotropic constitutive models and one anisotropic model with a single fiber direction,across six different stress states.The framework's applicability is also showcased in finite element simulations across three geometries of varying complexities.Our results highlight the framework's superior extrapolation capabilities,even when trained on limited and noisy data,delivering accurate and physically meaningful predictions across all numerical examples.
文摘The present work reports the inclusion of different proportions of Mango/Sheesham/Mahogany/Babool dust to polypropylene for improving mechanical,wear behavior and biodegradability of wood-plastic composite(WPC).The wood dust(10%,15%,20%by weight)was mixed with polypropylene granules and WPCs were prepared using an injection molding technique.The mechanical,wear,and morphological characterizations of fabricated WPCs were carried out using standard ASTM methods,pin on disk apparatus,and scanning electron microscopy(SEM),respectively.Further,the biodegradability and resistance to natural weathering of WPCs were evaluated following ASTM D5338-11 and ASTM D1435-99,respectively.The WPCs consisting ofBabool and Sheesham dust were having superior mechanical properties whereas the WPCs consisting of Mango and Mahogany were more wear resistant.It was found that increasing wood powder proportion results in higher Young's modulus,lesser wear rate,and decreased stress at break.The WPCs made of Sheesham dust were least biodegradable.It was noticed that the biodegradability corresponds with resistance to natural weathering;more biodegradable WPCs were having the lesser resistance to natural weathering.
文摘After publication of our article[1],the authors became aware that they had omitted to include the credit line for Fig.1[2].The corrected Fig.1 caption with the credit line is given below:“Fig.1(a)Photograph of wood-plastic composite samples;(b)photographs of experimental setups used 1)pin on disk,2)tensile testing,3)three-point bending,4)impact,5)injection molding,6)effect of weathering[12].Reprinted from Construction and Building Materials,172,Thanate Ratanawilai,Kampanart Taneerat,Alternative polymeric matrices for wood-plastic composites:Effects on mechanical properties and resistance to natural weathering,349–357,Copyright(2018),with permission from Elsevier.”
