λ π
Research & Projects

Selected Work

JUN 2025 – PRESENT

PINN vs Meta-Heuristic Methods for Damage Detection in Trusses

Dr. Ravinder · IIT Indore

A Physics-Informed Neural Network for damage detection in truss structures from limited-sensor data, benchmarked against Modal Strain Energy and Flexibility Matrix methods paired with TLBO and Democratic Particle-Swarm Optimisation.

PINNDamage DetectionTLBODPSO
JUN 2025 – PRESENT

Physics-Informed Neural Network based Truss Optimization

Dr. Ravinder · IIT Indore

A PINN-based optimization method to minimize truss weight under constraints on displacement, stress, and cross-sectional areas — gradient-based and entirely data-free.

PINNOptimizationDifferentiable
MAR – APR 2025

Modal Behavior & Earthquake Simulation of a Truss Tower

Dr. Ravinder · IIT Indore

Simulated the dynamic response of a 3D truss tower in Python under El Centro ground motion, capturing modal behavior and seismic response.

PythonDynamicsSeismic
SEP – NOV 2024

Non-Destructive Damage Assessment in a Beam via ML

Dr. Ravinder · IIT Indore

Trained a Random Forest classifier on healthy and known-damage vibration datasets to detect damage in a beam from vibration data alone.

Random ForestVibrationSHM
JUL – NOV 2023

Dynamic Analysis With & Without Shear Walls

Dr. Sanjay Kumar · NIT Patna

Compared the seismic response of a building across different shear wall configurations to evaluate their effect on dynamic performance.

Shear WallsSeismic
JAN – APR 2024

Static vs Dynamic Seismic Design of a G+6 Building

Kamlesh Kumar · Ayesa India

Computed and compared storey shear, storey drift, and mode shapes for a G+6 building using two seismic design methods in Staad.Pro.

Staad.ProSeismic Design
Publication

Peer-Reviewed Research

● UNDER REVIEW

Physics-Informed Neural Networks based Truss Optimization

A physics-informed, differentiable framework for truss size optimization in which a neural network predicts member cross-sectional areas while enforcing structural constraints through a mechanics-based loss function — enabling efficient gradient-based optimization without any training data.