This study presents a multi-scale deep-learning framework that integrates several advanced neural models to optimize hybrid three dimensional(3D)printed self-sensing nano-carbon cementitious composites.The first step ...This study presents a multi-scale deep-learning framework that integrates several advanced neural models to optimize hybrid three dimensional(3D)printed self-sensing nano-carbon cementitious composites.The first step was undertaken by Multi-Scale Graph Neural Network,where special conductive pathways were taught ensuring the uniform work on nano-carbon learning patterns,improving electrical conductivity by 25%–35%.four-dimensional Spatiotemporal Transformer Network decoded printing parameters achievements with an interlayer conductivity improvement of 40%–50%,avoiding anisotropic print by aiming for defects prediction on print Induced anisotropic behavior.High-fidelity artificial microstructures have been generated with Physics Informed Generative Adversarial Networks;these synthetic methods realize an experimental cost-cutting of about 50%while conserving about 98%fidelity to the characteristics of real microstructures.Fifth,Self-Supervised Contrastive Learning automatically classifies small macro and microdefects with over 95%detection reliability.There has been reduction of as much as 35%in the number of false positives.Predicted kinetics of hydration and long-term electrical stability can now be predicted with speed improvements of 15%and resistance drift reduction by 20%over six months.This approach for the first time combines different hybrid models of deep learning for the self-sensing cementitious composites,thus significantly increasing percolation of electrical networks,accuracy in crack detection,and predictions on long-term durability.The developed framework creates a new paradigm in the real-time structural health monitoring world,providing enhanced reliability in structures while also reducing costs at a level for the next generation of smart infrastructure sets.展开更多
The interest in nano-engineered cements basically brought by the demands on increasing the performance of concrete structures in challenging applications,such as extreme thermal,electrical,and electromagnetic environm...The interest in nano-engineered cements basically brought by the demands on increasing the performance of concrete structures in challenging applications,such as extreme thermal,electrical,and electromagnetic environments.Traditional cementitious materials lack technological capabilities regarding thermal conductivity,electrical resistivity,mechanical strength,and electromagnetic shielding.Such limitations prevent their application in highperformance and multifunctional concrete structures,which are increasingly required in modern construction.The highdimensional complexity of multivariable optimization of multiple properties makes most of the current approaches unsuitable,and so requires new ways to predict,model,and optimize the performance of such advanced materials.In the present contribution,we introduce a holistic approach to the optimization of nano-engineered cements composites incorporating epoxy resin,nano titanium dioxide,carbon nanotubes,and portland cement.Advanced techniques of machine learning used include random forest regressor for multi-output property prediction and eXtreme gradient boosting,an implementation of the gradient-boosting algorithm that proved particularly useful in multi-objective optimization,for electrical codes’thermal and mechanical properties.Bayesian optimization is also employed to decrease the experimental trials and fine-tune the processing parameters;high-dimensional input space is reduced using principal component analysis to attain optimal model performance.Graph neural networks are utilized for modeling structureproperty relations,and Gaussian processes serve as a surrogate model mimicking the outcome of finite element analysis simulation effectively reducing delays at the computational level.The model yields noteworthy improvements:resistivity decreases by 30%–40%,thermal conductivity increases by 25%–30%,and tensile strength increases by 15%–20%.These enhancements make nano-engineered cements composites highly promising for multifunctional applications such as vibration absorption and electromagnetic shielding,which presents the need for smart,high-performance concrete structures for advanced applications in construction.展开更多
文摘This study presents a multi-scale deep-learning framework that integrates several advanced neural models to optimize hybrid three dimensional(3D)printed self-sensing nano-carbon cementitious composites.The first step was undertaken by Multi-Scale Graph Neural Network,where special conductive pathways were taught ensuring the uniform work on nano-carbon learning patterns,improving electrical conductivity by 25%–35%.four-dimensional Spatiotemporal Transformer Network decoded printing parameters achievements with an interlayer conductivity improvement of 40%–50%,avoiding anisotropic print by aiming for defects prediction on print Induced anisotropic behavior.High-fidelity artificial microstructures have been generated with Physics Informed Generative Adversarial Networks;these synthetic methods realize an experimental cost-cutting of about 50%while conserving about 98%fidelity to the characteristics of real microstructures.Fifth,Self-Supervised Contrastive Learning automatically classifies small macro and microdefects with over 95%detection reliability.There has been reduction of as much as 35%in the number of false positives.Predicted kinetics of hydration and long-term electrical stability can now be predicted with speed improvements of 15%and resistance drift reduction by 20%over six months.This approach for the first time combines different hybrid models of deep learning for the self-sensing cementitious composites,thus significantly increasing percolation of electrical networks,accuracy in crack detection,and predictions on long-term durability.The developed framework creates a new paradigm in the real-time structural health monitoring world,providing enhanced reliability in structures while also reducing costs at a level for the next generation of smart infrastructure sets.
文摘The interest in nano-engineered cements basically brought by the demands on increasing the performance of concrete structures in challenging applications,such as extreme thermal,electrical,and electromagnetic environments.Traditional cementitious materials lack technological capabilities regarding thermal conductivity,electrical resistivity,mechanical strength,and electromagnetic shielding.Such limitations prevent their application in highperformance and multifunctional concrete structures,which are increasingly required in modern construction.The highdimensional complexity of multivariable optimization of multiple properties makes most of the current approaches unsuitable,and so requires new ways to predict,model,and optimize the performance of such advanced materials.In the present contribution,we introduce a holistic approach to the optimization of nano-engineered cements composites incorporating epoxy resin,nano titanium dioxide,carbon nanotubes,and portland cement.Advanced techniques of machine learning used include random forest regressor for multi-output property prediction and eXtreme gradient boosting,an implementation of the gradient-boosting algorithm that proved particularly useful in multi-objective optimization,for electrical codes’thermal and mechanical properties.Bayesian optimization is also employed to decrease the experimental trials and fine-tune the processing parameters;high-dimensional input space is reduced using principal component analysis to attain optimal model performance.Graph neural networks are utilized for modeling structureproperty relations,and Gaussian processes serve as a surrogate model mimicking the outcome of finite element analysis simulation effectively reducing delays at the computational level.The model yields noteworthy improvements:resistivity decreases by 30%–40%,thermal conductivity increases by 25%–30%,and tensile strength increases by 15%–20%.These enhancements make nano-engineered cements composites highly promising for multifunctional applications such as vibration absorption and electromagnetic shielding,which presents the need for smart,high-performance concrete structures for advanced applications in construction.
