A curated list of 100+ AI-ready tools for Computer-Aided Engineering, ranked by an AI-Readiness Score (agent-callability: MCP, Python API, CLI, pip). CFD, FEA, SPH, DEM, differentiable simulation, neural operators, PINNs, MCP servers.

[ESWA] NeuroXAI: Adaptive, Robust, Explainable Surrogate Framework for Determination of Channel Importance in EEG Application

An extension of Fourier Neural Operator to finite-dimensional input and/or output spaces.

A Keysight ADS/RFPro-based workflow for RFIC pixel-layout generation, EM simulation automation, HDF5 dataset creation, and CNN-based surrogate modeling.

WinDiNet: Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows

Signal Filtering and Generation of Synthetic Time-Series.

A core library for engineering surrogate modeling and operator learning

Source code for Surrogate Modeling of Melt Pool Temperature Field using Deep Learning

Claude Code agent skills bridging Abaqus FEA and ML surrogates: LHS batch dataset generation + ODB to ML-ready grid CSVs.

An interactive Python dashboard for planning space missions. It features orbital maneuver calculations, animated 2D flight paths, and an AI model for predicting fuel needs, all wrapped in a clean, user-friendly interface.

Solving PDEs without pre-comuted data!

neural network surrogate for CFD simulations

This project builds a machine-learning surrogate model using data generated from a quasi-6-DoF physics simulator replacing numerical integration with a neural network that can predict full 3-D trajectories including altitude, downrange motion, and lateral deflection hundreds of times faster while maintaining meter-level accuracy.

Explainable AI for time series: gradient-based counterfactual generation for the non-differentiable Random Shapelet Forest, using PyTorch surrogate models (Feedforward, LSTM, CNN, Transformer) and a Streamlit UI. Research internship, DSV — Stockholm University.

Physics-informed neural-network surrogate for asset-integrity digital twin. ODE-constrained training with KKT enforcement.

Computational simulation of PLGA nanoparticle transport, drug release, and tumor response using finite difference methods in Python.

Streamlit app for surrogate-model validation on airfoil self-noise data

Explainable wearable gait analysis for high retrospective prodromal/non-motor burden phenotyping in established Parkinson’s disease.

Parameter-efficient autoregressive spectral U-Net for PDE surrogates: 0.0822 test L² on Navier–Stokes ν=1e-5 with 2.04M parameters (2.33× smaller than canonical FNO at ~20% lower error).

Privacy-preserving motion analytics for videos, RGB-D streams, and frame folders.