We have built an open source web application VOXELIZE using Streamlit that converts STL files into interactive voxel visualizations. We have further attached the app link and GitHub Repo.

Our application features drag-and-drop STL file processing, 32 scientific and artistic colormaps, interactive 3D scatter plots with customizable parameters, 2D slice analysis for internal structure examination, and comprehensive export capabilities including NumPy arrays and CSV coordinates.

We designed this tool specifically for materials scientists analyzing crystal structures and defects, engineers inspecting 3D printed parts for quality control, researchers preparing data for computational modeling, and anyone working with complex 3D geometries. We built it using Python, Streamlit, Trimesh, and Plotly to make advanced 3D analysis accessible through a simple web interface without requiring complex software installations. 

App Link: https://voxelize.streamlit.app/  

GitHub Repo: https://github.com/akshansh11/Voxelize

We have developed EDMLearner, an intelligent web application that combines advanced manufacturing with machine learning for optimizing Electrical Discharge Machining (EDM) processes in orthopedic implant production. Built using Streamlit, the platform converts complex experimental data from Ti-13Zr-13Nb titanium alloy machining into actionable insights through interactive visualizations and predictive modeling.

The application implements both empirical models validated through Response Surface Methodology and modern machine learning algorithms including Random Forest and Gradient Boosting regressors. Users can explore multi-objective optimization scenarios, balancing material removal rate, electrode wear, and surface roughness through real-time parameter adjustment and 3D response surface analysis. The digital twin simulator provides live process monitoring with automated recommendations, enabling manufacturers to optimize machining parameters before actual production runs.

EDMLearner addresses critical challenges in medical device manufacturing where precision titanium alloy machining directly impacts implant biocompatibility and patient outcomes. The platform's ability to predict optimal EDM parameters reduces experimental costs, minimizes material waste, and accelerates the development of high-quality orthopedic implants. Through interactive contour mapping and Pareto frontier analysis, engineers can identify parameter combinations that achieve superior performance across multiple objectives simultaneously.

The application demonstrates how data-driven approaches can transform traditional manufacturing processes, making advanced optimization techniques accessible through intuitive web interfaces. 

App Link: https://edmlearner.streamlit.app/

GitHub Repo: https://github.com/akshansh11/EDMLearner