Akshansh Mishra

Akshansh Mishra

Additive friction stir deposition (AFSD) is a novel solid-state additive manufacturing technique that circumvents issues of porosity, cracking, and properties anisotropy that plague traditional powder bed fusion and directed energy deposition approaches. However, correlations between process parameters, thermal profiles, and resulting microstructure in AFSD remain poorly understood. This hinders process optimization for properties. This work employs a framework combining supervised machine learning (SML) and physics-informed neural networks (PINNs) to predict peak temperature distribution in AFSD from process parameters. Eight regression algorithms were implemented for SML modeling, while four PINNs leveraged governing equations for transport, wave propagation, heat transfer, and quantum mechanics. Across multiple statistical measures, ensemble techniques like gradient boosting proved superior for SML, with lowest MSE of 165.78. The integrated ML approach was also applied to classify deposition quality from process factors, with logistic regression delivering robust accuracy. By fusing data-driven learning and fundamental physics, this dual methodology provides comprehensive insights into tailoring microstructure through thermal management in AFSD. The work demonstrates the power of bridging statistical and physics-based modeling for elucidating AM process-property relationships.

Akshansh Mishra, Asmita Suman, Devarrishi Dixit

Friction Stir Welding is a robust joining process, and numerous AI-based algorithms are being developed in this field to enhance mechanical and microstructure properties. Convolutional Neural Networks (CNNs) are Artificial Neural Networks that use image data as input. Identical to Artificial Neural Networks, they are composed of weights that are determined throughout learning, neurons (activated functions), and a goal (loss function). CNN is utilized in a variety of applications, including image recognition, semantic segmentation, image recognition, and localization. Utilizing training on 3000 microstructure pictures and new tests on 300 microstructure photographs, the current work investigates the predictions of Friction Stir Welded joint effectiveness using microstructure images.

Akshansh Mishra, Vijaykumar S Jatti, Vaishnavi More et al.

The ability to interpret spoken language is connected to natural language processing. It involves teaching the AI how words relate to one another, how they are meant to be used, and in what settings. The goal of natural language processing (NLP) is to get a machine intelligence to process words the same way a human brain does. This enables machine intelligence to interpret, arrange, and comprehend textual data by processing the natural language. The technology can comprehend what is communicated, whether it be through speech or writing because AI pro-cesses language more quickly than humans can. In the present study, five NLP algorithms, namely, Geneism, Sumy, Luhn, Latent Semantic Analysis (LSA), and Kull-back-Liebler (KL) al-gorithm, are implemented for the first time for the knowledge summarization purpose of the High Entropy Alloys (HEAs). The performance prediction of these algorithms is made by using the BLEU score and ROUGE score. The results showed that the Luhn algorithm has the highest accuracy score for the knowledge summarization tasks compared to the other used algorithms.

Akshansh Mishra, Vijaykumar S Jatti

In this study, we investigate the application of supervised machine learning algorithms for estimating the Ultimate Tensile Strength (UTS) of Polylactic Acid (PLA) specimens fabricated using the Fused Deposition Modeling (FDM) process. A total of 31 PLA specimens were prepared, with Infill Percentage, Layer Height, Print Speed, and Extrusion Temperature serving as input parameters. The primary objective was to assess the accuracy and effectiveness of four distinct supervised classification algorithms, namely Logistic Classification, Gradient Boosting Classification, Decision Tree, and K-Nearest Neighbor, in predicting the UTS of the specimens. The results revealed that while the Decision Tree and K-Nearest Neighbor algorithms both achieved an F1 score of 0.71, the KNN algorithm exhibited a higher Area Under the Curve (AUC) score of 0.79, outperforming the other algorithms. This demonstrates the superior ability of the KNN algorithm in differentiating between the two classes of ultimate tensile strength within the dataset, rendering it the most favorable choice for classification in the context of this research. This study represents the first attempt to estimate the UTS of PLA specimens using machine learning-based classification algorithms, and the findings offer valuable insights into the potential of these techniques in improving the performance and accuracy of predictive models in the domain of additive manufacturing.

Akshansh Mishra, Vijaykumar S. Jatti

Surface roughness is a crucial factor influencing the performance and functionality of additive manufactured components. Accurate prediction of surface roughness is vital for optimizing manufacturing processes and ensuring the quality of the final product. Quantum computing has recently gained attention as a potential solution for tackling complex problems and creating precise predictive models. In this research paper, we conduct an in-depth comparison of three quantum algorithms i.e. the Quantum Neural Network (QNN), Quantum Forest (Q-Forest), and Variational Quantum Classifier (VQC) adapted for regression for predicting surface roughness in additive manufactured specimens for the first time. We assess the algorithms performance using Mean Squared Error (MSE), Mean Absolute Error (MAE), and Explained Variance Score (EVS) as evaluation metrics. Our findings show that the Q-Forest algorithm surpasses the other algorithms, achieving an MSE of 56.905, MAE of 7.479, and an EVS of 0.2957. In contrast, the QNN algorithm displays a higher MSE of 60.840 and MAE of 7.671, coupled with a negative EVS of -0.444, indicating that it may not be appropriate for predicting surface roughness in this application. The VQC adapted for regression exhibits an MSE of 59.121, MAE of 7.597, and an EVS of -0.0106, suggesting its performance is also inferior to the Q-Forest algorithm.

Akshansh Mishra, Anish Dasgupta

The subject area known as computational neuroscience involves the investigation of brain function using mathematical techniques and theories. In order to comprehend how the brain processes information, it can also include various methods from signal processing, computer science, and physics. In the present work, for the first time a neurobiological based unsupervised machine learning algorithm i.e., Self-Organizing Map Neural Network is implemented for determining the fracture location in dissimilar friction stir welded AA5754-C11000 alloys. Too Shoulder Diameter (mm), Tool Rotational Speed (RPM), and Tool Traverse Speed (mm/min) are input parameters while the Fracture location i.e. whether the specimen fracture at Thermo-Mechanically Affected Zone (TMAZ) of copper or it fractures at TMAZ of Aluminium. The results showed that the implemented algorithm is able to predict the fracture location with 96.92% accuracy.

Akshansh Mishra, Rakesh Morisetty, Rajat Sarawagi

Oil production forecasting is an important step in controlling the cost-effect and monitoring the functioning of petroleum reservoirs. As a result, oil production forecasting makes it easier for reservoir engineers to develop feasible projects, which helps to avoid risky investments and achieve long-term growth. As a result, reliable petroleum reservoir forecasting is critical for controlling and managing the effective cost of oil reservoirs. Oil production is influenced by reservoir qualities such as porosity, permeability, compressibility, fluid saturation, and other well operational parameters. Three-time series algorithms i.e., Seasonal Naive method, Exponential Smoothening and ARIMA to forecast the Distillate Fuel Oil Refinery and Propane Blender net production for the next two years.

Akshansh Mishra

Text summarization is a technique for condensing a big piece of text into a few key elements that give a general impression of the content. When someone requires a quick and precise summary of a large amount of information, it becomes vital. If done manually, summarizing text can be costly and time-consuming. Natural Language Processing (NLP) is the sub-division of Artificial Intelligence that narrows down the gap between technology and human cognition by extracting the relevant information from the pile of data. In the present work, scientific information regarding the Friction Stir Welding of Aluminum alloys was collected from the abstract of scholarly research papers. For extracting the relevant information from these research abstracts four Natural Language Processing based algorithms i.e. Latent Semantic Analysis (LSA), Luhn Algorithm, Lex Rank Algorithm, and KL-Algorithm were used. In order to evaluate the accuracy score of these algorithms, Recall-Oriented Understudy for Gisting Evaluation (ROUGE) was used. The results showed that the Luhn Algorithm resulted in the highest f1-Score of 0.413 in comparison to other algorithms.

Akshansh Mishra, Eyob Messele Sefene, Gopikrishna Nidigonda et al.

Nowadays, industry 4.0 plays a tremendous role in the manufacturing industries for increasing the amount of data and accuracy in modern manufacturing systems. Thanks to artificial intelligence, particularly machine learning, big data analytics have dramatically amended, and manufacturers easily exploit organized and unorganized data. This study utilized hybrid optimization algorithms to find friction stir welding and optimal hardness value at the nugget zone. A similar AA 6262 material was used and welded in a butt joint configuration. Tool rotational speed (RPM), tool traverse speed (mm/min), and the plane depth (mm) are used as controllable parameters and optimized using Taguchi L9, Random Forest, and XG Boost machine learning tools. Analysis of variance was also conducted at a 95% confidence interval for identifying the significant parameters. The result indicated that the coefficient of determination from Taguchi L9 orthogonal array is 0.91 obtained while Random Forest and XG Boost algorithm imparted 0.62 and 0.65, respectively.

Akshansh Mishra

This study presents a novel approach to predicting mechanical properties of Additive Friction Stir Deposited (AFSD) aluminum alloy walled structures using biomimetic machine learning. The research combines numerical modeling of the AFSD process with genetic algorithm-optimized machine learning models to predict von Mises stress and logarithmic strain. Finite element analysis was employed to simulate the AFSD process for five aluminum alloys: AA2024, AA5083, AA5086, AA7075, and AA6061, capturing complex thermal and mechanical interactions. A dataset of 200 samples was generated from these simulations. Subsequently, Decision Tree (DT) and Random Forest (RF) regression models, optimized using genetic algorithms, were developed to predict key mechanical properties. The GA-RF model demonstrated superior performance in predicting both von Mises stress (R square = 0.9676) and logarithmic strain (R square = 0.7201). This innovative approach provides a powerful tool for understanding and optimizing the AFSD process across multiple aluminum alloys, offering insights into material behavior under various process parameters.

Akshansh Mishra

In this research, the application of the Physics-Informed Neural Network (PINN) model is explored to solve transport equation-based Partial Differential Equations (PDEs). The primary objective is to analyze the impact of different activation functions incorporated within the PINN model on its predictive performance, specifically assessing the Mean Squared Error (MSE) and Mean Absolute Error (MAE). The dataset used in the study consists of a varied set of input parameters related to strut diameter, unit cell size, and the corresponding yield stress values. Through this investigation the aim is to understand the effectiveness of the PINN model and the significance of choosing appropriate activation functions for solving complex PDEs in real-world applications. The outcomes suggest that the choice of activation function may have minimal influence on the model's predictive accuracy for this particular problem. The PINN model showcases exceptional generalization capabilities, indicating its capacity to avoid overfitting with the provided dataset. The research underscores the importance of striking a balance between performance and computational efficiency while selecting an activation function for specific real-world applications. These valuable findings contribute to advancing the understanding and potential adoption of PINN as an effective tool for solving challenging PDEs in diverse scientific and engineering domains.

Akshansh Mishra

Architected materials with their unique topology and geometry offer the potential to modify physical and mechanical properties. Machine learning can accelerate the design and optimization of these materials by identifying optimal designs and forecasting performance. This work presents LatticeML, a data-driven application for predicting the effective Young's Modulus of high-temperature graph-based architected materials. The study considers eleven graph-based lattice structures with two high-temperature alloys, Ti-6Al-4V and Inconel 625. Finite element simulations were used to compute the effective Young's Modulus of the 2x2x2 unit cell configurations. A machine learning framework was developed to predict Young's Modulus, involving data collection, preprocessing, implementation of regression models, and deployment of the best-performing model. Five supervised learning algorithms were evaluated, with the XGBoost Regressor achieving the highest accuracy (MSE = 2.7993, MAE = 1.1521, R-squared = 0.9875). The application uses the Streamlit framework to create an interactive web interface, allowing users to input material and geometric parameters and obtain predicted Young's Modulus values.

Akshansh Mishra

This study presents a geometric deep learning framework for predicting cold spray particle impact responses using finite element simulation data. A parametric dataset was generated through automated Abaqus simulations spanning a systematic range of particle velocity, particle temperature, and friction coefficient, yielding five output targets including maximum equivalent plastic strain, average contact plastic strain, maximum temperature, maximum von Mises stress, and deformation ratio. Four novel algorithms i.e. a GraphSAGE-style inductive graph neural network, a Chebyshev spectral graph convolution network, a topological data analysis augmented multilayer perceptron, and a geometric attention network were implemented and evaluated. Each input sample was treated as a node in a k-nearest-neighbour feature-space graph, enabling the models to exploit spatial similarity between process conditions during training. Three-dimensional feature space visualisations and two-dimensional contour projections confirmed the highly non-linear and velocity-dominated nature of the input-output relationships. Quantitative evaluation demonstrated that GraphSAGE and GAT consistently achieved R-square values exceeding 0.93 across most targets, with GAT attaining peak performance of R-square equal to 0.97 for maximum plastic strain. ChebSpectral and TDA-MLP performed considerably worse, yielding negative R-square values for several targets. These findings establish spatial graph-based neighbourhood aggregation as a robust and physically interpretable surrogate modelling strategy for cold spray process optimisation.

Akshansh Mishra

Accurate prediction of temperature evolution is essential for understanding thermomechanical behavior in friction stir welding. In this study, molecular dynamics simulations were performed using LAMMPS to model aluminum friction stir welding at the atomic scale, capturing material flow, plastic deformation, and heat generation during tool plunge, traverse, and retraction. Atomic positions and velocities were extracted from simulation trajectories and transformed into physics based two dimensional spatial grids. These grids represent local height variation, velocity components, velocity magnitude, and atomic density, preserving spatial correlations within the weld zone. A two-dimensional convolutional neural network was developed to predict temperature directly from the spatially resolved atomistic data. Hyperparameter optimization was carried out to determine an appropriate network configuration. The trained model demonstrates strong predictive capability, achieving a coefficient of determination R square of 0.9439, a root mean square error of 14.94 K, and a mean absolute error of 11.58 K on unseen test data. Class Activation Map analysis indicates that the model assigns higher importance to regions near the tool material interface, which are associated with intense deformation and heat generation in the molecular dynamics simulations. The results show that spatial learning from atomistic simulation data can accurately reproduce temperature trends in friction stir welding while remaining consistent with physical deformation and flow mechanisms observed at the atomic scale.

Akshansh Mishra, Rakesh Morisetty

Internal porosity remains a critical defect mode in additively manufactured components, compromising structural performance and limiting industrial adoption. Automated defect detection methods exist but lack interpretability, preventing engineers from understanding the physical basis of criticality predictions. This study presents an explainable computer vision framework for pore detection and criticality assessment in three-dimensional tomographic volumes. Sequential grayscale slices were reconstructed into volumetric datasets, and intensity-based thresholding with connected component analysis identified 500 individual pores. Each pore was characterized using geometric descriptors including size, aspect ratio, extent, and spatial position relative to the specimen boundary. A pore interaction network was constructed using percentile-based Euclidean distance criteria, yielding 24,950 inter-pore connections. Machine learning models predicted pore criticality scores from extracted features, and SHAP analysis quantified individual feature contributions. Results demonstrate that normalized surface distance dominates model predictions, contributing more than an order of magnitude greater importance than all other descriptors. Pore size provides minimal influence, while geometric parameters show negligible impact. The strong inverse relationship between surface proximity and criticality reveals boundary-driven failure mechanisms. This interpretable framework enables transparent defect assessment and provides actionable insights for process optimization and quality control in additive manufacturing.

Akshansh Mishra, Eyob Mesele Sefene, Shivraman Thapliyal

This work proposes an evolutionary computing-based image segmentation approach for analyzing soundness in Additive Friction Stir Deposition (AFSD) processes. Particle Swarm Optimization (PSO) was employed to determine optimal segmentation thresholds for detecting defects and features in multilayer AFSD builds. The methodology integrates gradient magnitude analysis with distance transforms to create novel attention-weighted visualizations that highlight critical interface regions. Five AFSD samples processed under different conditions were analyzed using multiple visualization techniques i.e. self-attention maps, and multi-channel visualization. These complementary approaches reveal subtle material transition zones and potential defect regions which were not readily observable through conventional imaging. The PSO algorithm automatically identified optimal threshold values (ranging from 156-173) for each sample, enabling precise segmentation of material interfaces. The multi-channel visualization technique effectively combines boundary information (red channel), spatial relationships (green channel), and material density data (blue channel) into cohesive representations that quantify interface quality. The results demonstrate that attention-based analysis successfully identifies regions of incomplete bonding and inhomogeneities in AFSD joints, providing quantitative metrics for process optimization and quality assessment of additively manufactured components.

Akshansh Mishra

This paper proposes an innovative method for predicting deformation in architected lattice structures that combines Physics-Informed Neural Networks (PINNs) with finite element analysis. A thorough study was carried out on FCC-based lattice beams utilizing five different materials (Structural Steel, AA6061, AA7075, Ti6Al4V, and Inconel 718) under varied edge loads (1000-10000 N). The PINN model blends data-driven learning with physics-based limitations via a proprietary loss function, resulting in much higher prediction accuracy than linear regression. PINN outperforms linear regression, achieving greater R-square (0.7923 vs 0.5686) and lower error metrics (MSE: 0.00017417 vs 0.00036187). Among the materials examined, AA6061 had the highest displacement sensitivity (0.1014 mm at maximum load), while Inconel718 had better structural stability.

Akshansh Mishra, Vijaykumar S Jatti

This research paper explores the impact of various input parameters, including Infill percentage, Layer Height, Extrusion Temperature, and Print Speed, on the resulting Tensile Strength in objects produced through additive manufacturing. The main objective of this study is to enhance our understanding of the correlation between the input parameters and Tensile Strength, as well as to identify the key factors influencing the performance of the additive manufacturing process. To achieve this objective, we introduced the utilization of Explainable Artificial Intelligence (XAI) techniques for the first time, which allowed us to analyze the data and gain valuable insights into the system's behavior. Specifically, we employed SHAP (SHapley Additive exPlanations), a widely adopted framework for interpreting machine learning model predictions, to provide explanations for the behavior of a machine learning model trained on the data. Our findings reveal that the Infill percentage and Extrusion Temperature have the most significant influence on Tensile Strength, while the impact of Layer Height and Print Speed is relatively minor. Furthermore, we discovered that the relationship between the input parameters and Tensile Strength is highly intricate and nonlinear, making it difficult to accurately describe using simple linear models.

Akshansh Mishra, Vijaykumar S Jatti

In this study, we introduce application of Neurosymbolic Artificial Intelligence (NSAI) for predicting the impact strength of additive manufactured polylactic acid (PLA) components, representing the first-ever use of NSAI in the domain of additive manufacturing. The NSAI model amalgamates the advantages of neural networks and symbolic AI, offering a more robust and accurate prediction than traditional machine learning techniques. Experimental data was collected and synthetically augmented to 1000 data points, enhancing the model's precision. The Neurosymbolic model was developed using a neural network architecture comprising input, two hidden layers, and an output layer, followed by a decision tree regressor representing the symbolic component. The model's performance was benchmarked against a Simple Artificial Neural Network (ANN) model by assessing mean squared error (MSE) and R-squared (R2) values for both training and validation datasets. The results reveal that the Neurosymbolic model surpasses the Simple ANN model, attaining lower MSE and higher R2 values for both training and validation sets. This innovative application of the Neurosymbolic approach in estimating the impact strength of additive manufactured PLA components underscores its potential for optimizing the additive manufacturing process. Future research could investigate further refinements to the Neurosymbolic model, extend its application to other materials and additive manufacturing processes, and incorporate real-time monitoring and control for enhanced process optimization.

Akshansh Mishra, Raheem Al-Sabur, Ahmad K. Jassim

Nowadays, manufacturing sectors harness the power of machine learning and data science algorithms to make predictions for the optimization of mechanical and microstructure properties of fabricated mechanical components. The application of these algorithms reduces the experimental cost beside leads to reduce the time of experiments. The present research work is based on the prediction of penetration depth using Supervised Machine Learning algorithms such as Support Vector Machines (SVM), Random Forest Algorithm, and Robust Regression algorithm. A Friction Stir Spot Welding (FSSW) was used to join two elements of AA1230 aluminum alloys. The dataset consists of three input parameters: Rotational Speed (rpm), Dwelling Time (seconds), and Axial Load (KN), on which the machine learning models were trained and tested. It observed that the Robust Regression machine learning algorithm outperformed the rest of the algorithms by resulting in the coefficient of determination of 0.96. The research work also highlights the application of image processing techniques to find the geometrical features of the weld formation.

Akshansh Mishra, Tarushi Pathak

Machine learning which is a sub-domain of an Artificial Intelligence which is finding various applications in manufacturing and material science sectors. In the present study, Deep Generative Modeling which a type of unsupervised machine learning technique has been adapted for the constructing the artificial microstructure of Aluminium-Silicon alloy. Deep Generative Adversarial Networks has been used for developing the artificial microstructure of the given microstructure image dataset. The results obtained showed that the developed models had learnt to replicate the lining near the certain images of the microstructures.

Akshansh Mishra

Image processing algorithms are finding various applications in manufacturing and materials industries such as identification of cracks in the fabricated samples, calculating the geometrical properties of the given microstructure, presence of surface defects, etc. The present work deals with the application of Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm for improving the quality of the microstructure images of the Friction Stir Welded joints. The obtained results showed that the obtained value of quantitative metric features such as Entropy value and RMS Contrast value were high which resulted in enhanced microstructure images.

Akshansh Mishra, Eyob Messele Sefene, Assefa Asmare Tsegaw

The highest strength-to-weight ratio criterion has fascinated curiosity increasingly in virtually all areas where heft reduction is indispensable. Lightweight materials and their joining processes are also a recent point of research demands in the manufacturing industries. Friction Stir Welding (FSW) is one of the recent advancements for joining materials without adding any third material (filler rod) and joining below the melting point of the parent material. The process is widely used for joining similar and dissimilar metals, especially lightweight non-ferrous materials like aluminum, copper, and magnesium alloys. This paper presents verdicts of optimum process parameters on attaining enhanced mechanical properties of the weld joint. The experiment was conducted on a 5 mm 6061 aluminum alloy sheet. Process parameters; tool material, rotational speed, traverse speed, and axial forces were utilized. Mechanical properties of the weld joint are examined employing a tensile test, and the maximum joint strength efficiency was reached 94.2%. Supervised Machine Learning based Regression algorithms such as Decision Trees, Random Forest, and Gradient Boosting Algorithm were used. The results showed that the Random Forest algorithm yielded highest coefficient of determination value of 0.926 which means it gives a best fit in comparison to other algorithms.

Akshansh Mishra, Devarrishi Dixit

Advent in machine learning is leaving a deep impact on various sectors including the material science domain. The present paper highlights the application of various supervised machine learning regression algorithms such as polynomial regression, decision tree regression algorithm, random forest algorithm, support vector regression algorithm, and artificial neural network algorithm to determine the thin film thickness of Polystyrene on the glass substrates. The results showed that the polynomial regression machine learning algorithm outperforms all other machine learning models by yielding the coefficient of determination of 0.96 approximately and mean square error of 0.04 respectively.