Physics-based neural network as constitutive law for finite element analysis of sintering

Metal rubber (MR) is an entangled fibrous functional material, and its mechanical properties are crucial for its applications; however, numerical constitutive models of MR for prediction and calculation are currently undeveloped. In this work, we provide a numerical constitutive model to express the mechanics of MR materials and develop an efficient finite elements method (FEM) to calculate the performance of MR components. We analyze the nonlinearity and anisotropy characteristics of MR during the deformation process. The elasticity matrix is adopted to express the nonlinearity and anisotropy of MR. An artificial neural network (ANN) model is built, trained, and tested to output the current elastic moduli for the elasticity matrix. Then, we combine the constitutive ANN model with the finite element method simulation to calculate the mechanics of the MR component. Finally, we perform a series of static and shock experiments and finite element simulations of an MR isolator. The results demonstrate the feasibility and accuracy of the numerical constitutive MR model. This work provides an efficient and convenient method for the design and analysis of MR components.

Artificial neural network (ANN) models are used to learn the nonlinear constitutive laws based on indirectly measurable data. The real input and output of the ANN model are derived from indirect data using a mechanical system, which is composed of several subsystems including the ANN model. As the ANN model is coupled with other subsystems, the input of the ANN model needs to be determined during the training. This approach integrates measurable data, mechanics, and ANN models so that the ANN models can be trained without direct data which is usually not available from experiments. Two examples are provided as an illustration of the proposed approach. The first example uses two-dimensional (2D) finite element (FE) analysis to train an ANN model to learn the nonlinear in-plane shear constitutive law. The second example applies a continuum damage model to train an ANN model to learn the damage accumulation law. The results show that the trained ANN models achieve great accuracy based on the proposed approach.

Finite element forming simulation for non-crimp fabrics using a non-orthogonal constitutive equation

Intelligent finite element method: An evolutionary approach to constitutive modeling

This paper demonstrates a combined approach of numerical analysis and experimental investigations to study the mechanical reliability of flip chip solder joints. The effect of various design parameters like bump geometry, soft and hard underfill, and used solder mask on the thermal fatigue life of solder joints is discussed. Since special attention has been directed towards Flip Chip on Board (FCOB) assemblies, constitutive properties of polymeric and solder materials are discussed in detail. The solder is modeled using a nonlinear constitutive law with time dependent (creep) and time independent plastic strains. Furthermore, material testing shows that the underfill and solder mask materials might be considered as linear viscoelastic with temperature time shift properties. Thermal mismatch between the materials assembled is often the main reason for thermally induced stresses. Thermal cycling (125/spl deg/C...-55/spl deg/C...125/spl deg/C) is therefore the load generally used in the 3D non-linear finite element analysis. Calculation results of the solder bump deformation due to temperature changes are accompanied by experimental deformation analysis. The used MicroDAC method is based on algorithms of local object tracking in images obtained from electron scanning microscopy. The measured deformation fields were utilized for proper materials selection and processing, as well as for verification of finite element analysis.

Perhaps you have heard ofartificial intelligence (AI) or artificial neural networks (ANN) lately? An artificial neural network can be used to analyze all the simulated data from a digital twin and predict new outcomes. Sometimes they can respond faster than the digital twin itself. They can also be used to describe the complicated behavior of complex systems. We will revisit the topic of combining our digital twins with neural networks for control and automation. We will look at the rules used to define a simple example of a neural network and how it can be used as an alternative to the twin.

A data-driven, machine learning scheme used to predict the structural response of masonry arches

Fully coupled thermo-viscoplastic analysis of composite structures by means of multi-scale three-dimensional finite element computations

PurposeStress concentration factors (SCFs) are commonly used to assess the fatigue life of tubular T-joints in offshore structures. SCFs are usually estimated from parametric equations derived from experimental data and finite element analysis (FEA). However, these equations provide the SCF at the crown and saddle points of tubular T-joints only, while peak SCF might occur anywhere along the brace. Using the SCF at the crown and saddle can lead to inaccurate hotspot stress and fatigue life estimates. There are no equations available for calculating the SCF along the T-joint's brace axis under in-plane and out-of-plane bending moments.Design/methodology/approachIn this work, parametric equations for estimating SCFs are developed based on the training weights and biases of an artificial neural network (ANN), as ANNs are capable of representing complex correlations. 1,250 finite element simulations for tubular T-joints with varying dimensions subjected to in-plane bending moments and out-of-plane bending moments were conducted to obtain the corresponding SCFs for training the ANN.FindingsThe ANN was subsequently used to obtain equations to calculate the SCFs based on dimensionless parameters (α, β, γ and τ). The equations can predict the SCF around the T-joint's brace axis with an error of less than 8% and a root mean square error (RMSE) of less than 0.05.Originality/valueAccurate SCF estimation for determining the fatigue life of offshore structures reduces the risks associated with fatigue failure while ensuring their durability and dependability. The current study provides a systematic approach for calculating the stress distribution at the weld toe and SCF in T-joints using FEA and ANN, as ANNs are better at approximating complex phenomena than typical data fitting techniques. Having a database of parametric equations enables fast estimation of SCFs, as opposed to costly testing and time-consuming FEA.

Variability response functions for beams with nonlinear constitutive laws

Artificial neural networks and intelligent finite elements in non-linear structural mechanics

In this paper we present a thorough description of the digital twin development for a continuous pharmaceutical powder blending process in accordance with the Process Analytical Technologies (PAT) and Quality by Design (QbD) guidelines. A low-dosage system of caffeine active pharmaceutical ingredient (API) and dextrose excipient was examined via continuous blending experiments. Near infrared (NIR) spectroscopy–based process analytics were applied; quantitative evaluation of spectra was achieved using multivariate data analysis. The blending system was represented with mechanistic residence time distribution (RTD) models and two types of recurrent artificial neural networks (ANN), experimental datasets were used for model training or fitting and validation. Detailed comparison of the two modelling approaches, the optimization of the model-based digital twin, and efficiency of the soft sensor-based process monitoring is presented through several validating simulations. Both RTD models and nonlinear autoregressive neural networks demonstrated excellent predictive power for the low dosage blending process. RTD models can prove to be more advantageous in industrial development as they are less resource-intensive to develop and prediction accuracy on low concentration levels lacks dependency from the precision of chemometric calibration. Reduced material costs and limited development timeframe render the digital twin an efficient tool in technological development.

Environmental factors, such as climate change, have serious consequences for existing buildings, including increased resource consumption and footprint, adverse health effects, and reduced comfort for the occupants. To promote sustainability and address climate change, architecture must embrace digitalization. Buildings can be built digitally, analyzed in real time, optimized for energy consumption, and utilized to reduce carbon emissions and achieve zero energy consumption using digital twin technology. Currently, Lebanon’s residents are turning to solar power to generate renewable energy as a result of a lack of energy supplied by the government. In this study, a digital twin model was designed using an artificial neural network (ANN) to investigate the energy consumption of residential buildings. The main idea was to assist architects and engineers in forecasting energy consumption for different design materials by selecting the most effective alternate design for materials with building envelope characteristics, such as exterior walls, roof insulation, and windows, to minimize the consumption of energy in a residential building, hence resulting in a green building. The data simulations used in the digital twin model were carried out using Quick Energy Simulation Tool (eQuest) software; 1540 simulation results were used for different thicknesses of insulation material, values of conductivity, and window types. The digital twins were designed using an artificial neural network model. The results of the investigation and the accompanying eQuest output results were found to be precise and very similar.

The famous bifurcation analysis performed by Flügge on compressed thin-walled cylinders is based on a series of simplifying assumptions, which allow to obtain the bifurcation landscape, together with explicit expressions for limit behaviours: surface instability, wrinkling, and Euler rod buckling. The most severe assumption introduced by Flügge is the use of an incremental constitutive equation, which does not follow from any nonlinear hyperelastic constitutive law. This is a strong limitation for the applicability of the theory, which becomes questionable when is utilized for a material characterized by a different constitutive equation, such as for instance a Mooney-Rivlin material. We re-derive the entire Flügge's formulation, thus obtaining a framework where any constitutive equation fits. The use of two different nonlinear hyperelastic constitutive equations, referred to compressible materials, leads to incremental equations, which reduce to those derived by Flügge under suitable simplifications. His results are confirmed, together with all the limit equations, now rigorously obtained, and his theory is extended. This extension of the theory of buckling of thin shells allows for computationally efficient determination of bifurcation landscapes for nonlinear constitutive laws, which may for instance be used to model biomechanics of arteries, or soft pneumatic robot arms.

Parametric variational principle and quadratic programming method for van der Waals force simulation of parallel and cross nanotubes