arXiv subjects

Satyajit Mojumder

Publications and source records attributed to Satyajit Mojumder.

18 recordsLinked to original sources

arXiv2026

In-situ process monitoring for defect detection in wire-arc additive manufacturing: an agentic AI approach

AI agents are being increasingly deployed across a wide range of real-world applications. In this paper, we propose an agentic AI framework for in-situ process monitoring for defect detection in wire-arc additive manufacturing (WAAM). The autonomous agent leverages a WAAM process monitoring dataset and a trained classification tool to build AI agents and uses a large language model (LLM) for in-situ process monitoring decision-making for defect detection. A processing agent is developed based on welder process signals, such as current and voltage, and a monitoring agent is developed based on acoustic data collected during the process. Both agents are tasked with identifying porosity defects from processing and monitoring signals, respectively. Ground truth X-ray computed tomography (XCT) data are used to develop classification tools for both the processing and monitoring agents. Furthermore, a multi-agent framework is demonstrated in which the processing and monitoring agents are orchestrated together for parallel decision-making on the given task of defect classification. Evaluation metrics are proposed to determine the efficacy of both individual agents, the combined single-agent, and the coordinated multi-agent system. The multi-agent configuration outperforms all individual-agent counterparts, achieving a decision accuracy of 91.6% and an F1 score of 0.821 on decided runs, across 15 independent runs, and a reasoning quality score of 3.74 out of 5. These in-situ process monitoring agents hold significant potential for autonomous real-time process monitoring and control toward building qualified parts for WAAM and other additive manufacturing processes.

cs.AI↗

arXiv2025

Multimodal learning of melt pool dynamics in laser powder bed fusion

While multiple sensors are used for real-time monitoring in additive manufacturing, not all provide practical or reliable process insights. For example, high-speed X-ray imaging offers valuable spatial information about subsurface melt pool behavior but is costly and impractical for most industrial settings. In contrast, absorptivity data from low-cost photodiodes correlate with melt pool dynamics but is often too noisy for accurate prediction when used alone. In this paper, we propose a multimodal data fusion approach for predicting melt pool dynamics by combining high-fidelity X-ray data with low-fidelity absorptivity data in the Laser Powder Bed Fusion (LPBF) process. Our multimodal learning framework integrates convolutional neural networks (CNNs) for spatial feature extraction from X-ray data with recurrent neural networks (RNNs) for temporal feature extraction from absorptivity signals, using an early fusion strategy. The multimodal model is further used as a transfer learning model to fine-tune the RNN model that can predict melt pool dynamics only with absorptivity, with greater accuracy compared to the multimodal model. Results show that training with both modalities significantly improves prediction accuracy compared to using either modality alone. Furthermore, once trained, the model can infer melt pool characteristics using only absorptivity data, eliminating the need for expensive X-ray imaging. This multimodal fusion approach enables cost-effective, real-time monitoring and has broad applicability in additive manufacturing.

cs.LG↗

arXiv2025

Physics-guided denoiser network for enhanced additive manufacturing data quality

Modern engineering systems are increasingly equipped with sensors for real-time monitoring and decision-making. However, the data collected by these sensors is often noisy and difficult to interpret, limiting its utility for control and diagnostics. In this work, we propose a physics-informed denoising framework that integrates energy-based model and Fisher score regularization to jointly reduce data noise and enforce physical consistency with a physics-based model. The approach is first validated on benchmark problems, including the simple harmonic oscillator, Burgers' equation, and Laplace's equation, across varying noise levels. We then apply the denoising framework to real thermal emission data from laser powder bed fusion (LPBF) additive manufacturing experiments, using a trained Physics-Informed Neural Network (PINN) surrogate model of the LPBF process to guide denoising. Results show that the proposed method outperforms baseline neural network denoisers, effectively reducing noise under a range of LPBF processing conditions. This physics-guided denoising strategy enables robust, real-time interpretation of low-cost sensor data, facilitating predictive control and improved defect mitigation in additive manufacturing.

eess.SP↗

arXiv2024

Simulation-Free Determination of Microstructure Representative Volume Element Size via Fisher Scores

A representative volume element (RVE) is a reasonably small unit of microstructure that can be simulated to obtain the same effective properties as the entire microstructure sample. Finite element (FE) simulation of RVEs, as opposed to much larger samples, saves computational expense, especially in multiscale modeling. Therefore, it is desirable to have a framework that determines RVE size prior to FE simulations. Existing methods select the RVE size based on when the FE-simulated properties of samples of increasing size converge with insignificant statistical variations, with the drawback that many samples must be simulated. We propose a simulation-free alternative that determines RVE size based only on a micrograph. The approach utilizes a machine learning model trained to implicitly characterize the stochastic nature of the input micrograph. The underlying rationale is to view RVE size as the smallest moving window size for which the stochastic nature of the microstructure within the window is stationary as the window moves across a large micrograph. For this purpose, we adapt a recently developed Fisher score-based framework for microstructure nonstationarity monitoring. Because the resulting RVE size is based solely on the micrograph and does not involve any FE simulation of specific properties, it constitutes an RVE for any property of interest that solely depends on the microstructure characteristics. Through numerical experiments of simple and complex microstructures, we validate our approach and show that our selected RVE sizes are consistent with when the chosen FE-simulated properties converge.

cs.CE↗

arXiv2023

Statistical Parameterized Physics-Based Machine Learning Digital Twin Models for Laser Powder Bed Fusion Process

A digital twin (DT) is a virtual representation of physical process, products and/or systems that requires a high-fidelity computational model for continuous update through the integration of sensor data and user input. In the context of laser powder bed fusion (LPBF) additive manufacturing, a digital twin of the manufacturing process can offer predictions for the produced parts, diagnostics for manufacturing defects, as well as control capabilities. This paper introduces a parameterized physics-based digital twin (PPB-DT) for the statistical predictions of LPBF metal additive manufacturing process. We accomplish this by creating a high-fidelity computational model that accurately represents the melt pool phenomena and subsequently calibrating and validating it through controlled experiments. In PPB-DT, a mechanistic reduced-order method-driven stochastic calibration process is introduced, which enables the statistical predictions of the melt pool geometries and the identification of defects such as lack-of-fusion porosity and surface roughness, specifically for diagnostic applications. Leveraging data derived from this physics-based model and experiments, we have trained a machine learning-based digital twin (PPB-ML-DT) model for predicting, monitoring, and controlling melt pool geometries. These proposed digital twin models can be employed for predictions, control, optimization, and quality assurance within the LPBF process, ultimately expediting product development and certification in LPBF-based metal additive manufacturing.

cs.LG↗

arXiv2023

Extended tensor decomposition model reduction methods: training, prediction, and design under uncertainty

This paper introduces an extended tensor decomposition (XTD) method for model reduction. The proposed method is based on a sparse non-separated enrichment to the conventional tensor decomposition, which is expected to improve the approximation accuracy and the reducibility (compressibility) in highly nonlinear and singular cases. The proposed XTD method can be a powerful tool for solving nonlinear space-time parametric problems. The method has been successfully applied to parametric elastic-plastic problems and real time additive manufacturing residual stress predictions with uncertainty quantification. Furthermore, a combined XTD-SCA (self-consistent clustering analysis) strategy has been presented for multi-scale material modeling, which enables real time multi-scale multi-parametric simulations. The efficiency of the method is demonstrated with comparison to finite element analysis. The proposed method enables a novel framework for fast manufacturing and material design with uncertainties.

math.NA↗

arXiv2022

Multiscale reduced-order modeling of fused filament fabricated composites

Defects such as voids are observed at multiple length scales of an additively manufactured composite material. Modeling such defects and their multiscale interaction is crucial for the materials performance prediction. In this work, we study as-built defects in fused filament fabricated Polycarbonate/Short Carbon Fiber (PC/SCF) composite samples. The microscale and mesoscale voids along with the mesoscale layer orientations have been studied using a mechanistic reduced-order model. Our result indicates that the microscale intrabead voids interact with the mesoscale interbead voids and significantly degrade the mechanical response of the printed composites compared to the microscale microstructure without voids. The mesoscale layer orientations also influence the stress-strain response and show better performance when the load is applied to the bead direction. The efficient reduced-order modeling approach used in this work provides a way to evaluate multiscale design aspects of additively manufactured composite materials.

cond-mat.mtrl-sci↗

arXiv2021

Concurrent n-scale modeling for non-orthogonal woven composite

Concurrent analysis of composite materials can provide the interaction among scales for better composite design, analysis, and performance prediction. A data-driven concurrent n-scale modeling theory ($\textrm{FExSCA}^\textrm{n-1}$) is proposed in this paper utilizing a mechanistic reduced order model (ROM) called self-consistent clustering analysis (SCA). We demonstrated this theory with a $\textrm{FExSCA}^2$ approach to study the 3-scale woven carbon fiber reinforced polymer (CFRP) laminate structure. $\textrm{FExSCA}^2$ significantly reduced expensive 3D nested composite representative volume elements (RVEs) computation for woven and unidirectional (UD) composite structures by developing a material database. The modeling procedure is established by integrating the material database into a woven CFRP structural numerical model, formulating a concurrent 3-scale modeling framework. This framework provides an accurate prediction for the structural performance (e.g., nonlinear structural behavior under tensile load), as well as the woven and UD physics field evolution. The concurrent modeling results are validated against physical tests that link structural performance to the basic material microstructures. The proposed methodology provides a comprehensive predictive modeling procedure applicable to general composite materials aiming to reduce laborious experiments needed.

cond-mat.mtrl-sci↗

arXiv2021

Mechanistic Data Science for Modeling and Design of Aerospace Composite Materials

Polymer matrix composites exhibit remarkable lightweight and high strength properties that make them attractive for aerospace applications. Constituents' materials such as advanced polymers and fibers or fillers with their hierarchical structure embed these exceptional properties to the composite materials. This hierarchical structure in multiple length scales provides an opportunity for designing the composite materials for optimized properties. However, the high dimensional design space for the constituents' materials and architectures choice of the composites makes it a challenging design problem. To tackle this high dimensional design space, a systematic, efficient approach named mechanistic data science framework is proposed in this work to identify the governing mechanisms of materials systems from the limited available data and create a composite knowledge database. Our composite knowledge database comprises the knowledge of polymers at the nanoscale with nano reinforcement, the unidirectional structure at the microscale, and woven structure at mesoscale mechanisms that can be further used for the part scale composite design and analysis. The mechanistic data science framework presented in this work can be further extended to other materials systems that will provide the materials designer with the necessary tools to evaluate a new materials system design rapidly.

cond-mat.mtrl-sci↗

arXiv2021

Comparative study on Mechanical characteristics of Functionally graded and Coreshell nanospheres: An Atomistic approach

Functionally Graded Material (FGM) is a type of advanced material consisting of two (or more) distinct substances with a constantly changing composition profile. FGM technologies have moved from their traditional use to advanced micro and nanoscale electronics and energy conversion systems along with the advent of nanotechnology. MD simulations are used in this analysis to examine the effect of compressive load on Ag-Au FGM and Core-shell nanospheres. The plasticity process is often started by the nucleation of partial dislocations from the contact surfaces, and these dislocations spread towards the nanosphere's center. Also, we have found the formation of pyramidal-shaped partial dislocations on the pseudo-plastic regime. For a given wt% range of Ag in Au, Coreshell nanospheres have stronger mechanical strength than FGM nanospheres, and we have also observed two distinct patterns in ultimate stress variation for FGM and Coreshell nanospheres. The dislocation analysis suggests a correlation between this stress variation and the Shockley & Hirth partial dislocation density.

cond-mat.mtrl-sci↗

arXiv2020

Extraction of Material Properties through Multi-fidelity Deep Learning from Molecular Dynamics Simulation

Simulation of reasonable timescales for any long physical process using molecular dynamics (MD) is a major challenge in computational physics. In this study, we have implemented an approach based on multi-fidelity physics informed neural network (MPINN) to achieve long-range MD simulation results over a large sample space with significantly less computational cost. The fidelity of our present multi-fidelity study is based on the integration timestep size of MD simulations. While MD simulations with larger timestep produce results with lower level of accuracy, it can provide enough computationally cheap training data for MPINN to learn an accurate relationship between these low-fidelity results and high-fidelity MD results obtained using smaller simulation timestep. We have performed two benchmark studies, involving one and two component LJ systems, to determine the optimum percentage of high-fidelity training data required to achieve accurate results with high computational saving. The results show that important system properties such as system energy per atom, system pressure and diffusion coefficients can be determined with high accuracy while saving 68% computational costs. Finally, as a demonstration of the applicability of our present methodology in practical MD studies, we have studied the viscosity of argon-copper nanofluid and its variation with temperature and volume fraction by MD simulation using MPINN. Then we have compared them with numerous previous studies and theoretical models. Our results indicate that MPINN can predict accurate nanofluid viscosity at a wide range of sample space with significantly small number of MD simulations. Our present methodology is the first implementation of MPINN in conjunction with MD simulation for predicting nanoscale properties. This can pave pathways to investigate more complex engineering problems that demand long-range MD simulations.

physics.comp-ph↗

arXiv2020

Numerical Investigation of Mechanical Properties of Aluminum-Copper Alloys at Nanoscale

Nanoindentation is a powerful tool capable of providing fundamental insights of material elastic and plastic response at the nanoscale. Alloys at nanoscale are particularly interesting as the local heterogeneity and deformation mechanism revealed by atomistic study offers a better way to understand hardening mechanism to build a stronger material. In this work, nanoindentation in Al-Cu alloys are studied using atomistic simulations to investigate the effects of loading direction, alloying percentages of Cu via dislocation-driven mechanisms. Also, a low-fidelity finite element (FE) model has been developed for nanoindentation simulations where nanoscale materials properties are used from atomistic simulations. Material properties, such as hardness and reduced modulus, are computed from both the FE and MD simulations and then compared. Considering the fundamental difference between these two numerical approaches, the FE results obtained from the present study conform fairly with those from MD simulations. This paves a way into finding material properties of alloys with reduced simulation time and cost by using FE where high-fidelity results are not required. The results have been presented as load-displacement analysis, dislocation density, dislocation loops nucleation and propagation, von-Mises stress distribution and surface imprints. The techniques adopted in this paper to incorporate atomistic data into FE simulations can be further extended for finding other mechanical and fracture properties for complex alloy materials.

cond-mat.mtrl-sci↗

arXiv2020

Mechanical and Vibrational Characteristics of Functionally Graded Cu-Ni Nanowire: A Molecular Dynamics Study

Functionally graded material (FGM) is a class of advanced materials, consisting of two (or more) different constituents, that possesses a continuously varying composition profile. With the advancement of nanotechnology, applications of FGMs have shifted from their conventional usage towards sophisticated micro and nanoscale electronics and energy conversion devices. Therefore, the study of mechanical and vibrational properties of different FGM nanostructures is crucial in exploring their feasibility for different applications. In this study, for the first time, we employed molecular dynamics (MD) simulations to investigate the mechanical and vibrational properties of radially graded Cu-Ni FGM nanowires (NW). Distribution of Cu and Ni along the radial direction follows power-law, exponential and sigmoid functions for FGM NWs under consideration. Our results demonstrate that, distribution function parameters play an important role in modulating the mechanical (elastic modulus and ultimate tensile strength) and vibrational (natural frequency and quality factor) properties of FGM NWs. The study also suggests that, elastic moduli of FGM NWs can be predicted with relatively good accuracy using Tamura and Reuss micromechanical models, regardless of NW diameter. We found that, Euler-Bernoulli beam theory under-predicts the natural frequencies of FGM NWs, whereas He-Lilley model closely approximates the MD results. Interestingly, FGM NWs are always found to exhibit beat vibration because of their asymmetrical cross sections. Finally, this is the first atomistic scale study of FGMs that directly compares MD simulations with continuum theories and micromechanical models to understand the underlying mechanisms that govern the mechanical and vibrational properties of FGM NWs in nanoscale.

cond-mat.mtrl-sci↗

arXiv2017

Atomistic study of hardening mechanism in Al-Cu nanostructure

Nanostructures have the immense potential to supplant the traditional metallic structure as they show enhanced mechanical properties through strain hardening. In this paper, the effect of grain size on the hardening mechanism of Al-Cu nanostructure is elucidated by molecular dynamics simulation. Al-Cu (50-54% Cu by weight) nanostructure having an average grain size of 4.57 to 7.26 nm are investigated for tensile simulation at different strain rate using embedded atom method (EAM) potential at a temperature of 50~500K. It is found that the failure mechanism of the nanostructure is governed by the temperature, grain size as well as strain rate effect. At the high temperature of 300-500K, the failure strength of Al-Cu nanostructure increases with the decrease of average grain size following Hall-Petch relation. Dislocation motions are hindered significantly when the grain size is decreased which play a vital role on the hardening of the nanostructure. The failure is always found to initiate at a particular Al grain due to its weak link and propagates through grain boundary (GB) sliding, diffusion, dislocation nucleation and propagation. We also visualize the dislocation density at different grain size to show how the dislocation affects the material properties at the nanoscale. These results will further aid investigation on the deformation mechanism of nanostructure.

cond-mat.mtrl-sci↗

arXiv2017

Molecular dynamics study of plasticity in Al-Cu alloy nanopillar due to compressive loading

In this paper, compressive loading effects on the plasticity of Al-Cu alloy varying the crystal orientation of Al and alloying element (Cu) percentage are investigated using molecular dynamics approach. The alloying percentage of Cu are varied up to 10% in <001>, <110> and <111> crystal loading direction of Al. Our results indicate that the alloy nanopillar has highest first yielding strength and strain along <110> and <001> direction, respectively. Further, the dislocation density and dislocation interaction are studied to explain the compressive stress strain behavior of the alloy nanopillar.

cond-mat.mtrl-sci↗

arXiv2017

Study of Uniaxial Tensile Properties of Hexagonal Boron Nitride Nanoribbons

Uniaxial tensile properties of hexagonal boron nitride nanoribbons and dependence of these properties on temperature, strain rate, and the inclusion of vacancy defects have been explored with molecular dynamics simulations using Tersoff potential. The ultimate tensile strength of pristine hexagonal boron nitride nanoribbon of 26 nm x 5 nm with armchair chirality is found to be 100.5 GPa. The ultimate tensile strength and strain have been found decreasing with increasing the temperature while an opposite trend has been observed for increasing the strain rate. Furthermore, the vacancy defects reduce ultimate tensile strength and strain where the effect of bi-vacancy is clearly dominating over point vacancy.

cond-mat.mtrl-sci↗

arXiv2017

Atomistic Representation of Anomalies in the Failure Behaviour of Nanocrystalline Silicene

Silicene, a 2D analogue of graphene, has spurred a tremendous research interest in the scientific community for its unique properties essential for next generation electronic devices. In this work, for the first time, we present a molecular dynamics (MD) investigation to determine the fracture strength and toughness of nanocrystalline silicene (nc silicene) sheet of varied grain size and pre existing crack length at room temperature. Our results suggest that the transition from an inverse pseudo Hall Petch to a pseudo Hall Petch behavior in nc silicene occurs at a critical grain size of 17.32 nm. This phenomenon is also prevalent in nanocrystalline graphene. However, nc silicene with pre existing cracks exhibits anomalous crack propagation and fracture toughness behaviour. We have observed two distinct types of failure mechanisms (crack sensitive and insensitive failure) and devised the mechanophysical conditions under which they occur. Fracture toughness calculated from both Griffiths theory and MD simulations indicate that the former overpredicts the fracture toughness of nc silicene. The most striking outcome, however, is that despite the presence of a pre existing crack, the crack sensitivity of nc silicene is found to be dependent on the grain size and their orientations. This study is the first direct comparison of atomistic simulations to the continuum theories to predict the anomalous behaviour in deformation and failure mechanisms of nc silicene.

cond-mat.mtrl-sci↗

arXiv2017

Graphene and its elemental analogue: A molecular dynamics view of fracture phenomenon

Graphene and some graphene like two dimensional materials; hexagonal boron nitride (hBN) and silicene have unique mechanical properties which severely limit the suitability of conventional theories used for common brittle and ductile materials to predict the fracture response of these materials. This study revealed the fracture response of graphene, hBN and silicene nanosheets under different tiny crack lengths by molecular dynamics (MD) simulations using LAMMPS. The useful strength of these large area two dimensional materials are determined by their fracture toughness. Our study shows a comparative analysis of mechanical properties among the elemental analogues of graphene and suggested that hBN can be a good substitute for graphene in terms of mechanical properties. We have also found that the pre-cracked sheets fail in brittle manner and their failure is governed by the strength of the atomic bonds at the crack tip. The MD prediction of fracture toughness shows significant difference with the fracture toughness determined by Griffth's theory of brittle failure which restricts the applicability of Griffith's criterion for these materials in case of nano-cracks. Moreover, the strengths measured in armchair and zigzag directions of nanosheets of these materials implied that the bonds in armchair direction has the stronger capability to resist crack propagation compared to zigzag direction.

cond-mat.mtrl-sci↗