Skip to content

dadhichmohak/syncoat-squad

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Smart Coatings Optimization using Genetic Algorithms

Overview

This project explores the formulation of smart coatings - advanced paints with enhanced functionalities such as self-healing, UV resistance, corrosion protection, antimicrobial action, and thermochromism- using a Genetic Algorithm (GA)-based computational approach.

Our Python model simulates the optimization of coating formulations by balancing performance and cost. This in-silico approach drastically reduces R&D time and expenses, unlocking rapid innovation for the paints and coatings industry.


Key Features

  • AI-Driven Optimization of coating properties:

    • Durability
    • Self-Healing
    • UV Resistance
    • Corrosion Resistance
    • Miscibility
    • Cost
  • Customizable Fitness Function to prioritize specific industrial needs

  • Evolutionary Techniques: Selection, Crossover, Mutation

  • Early Stopping Mechanism for efficient convergence


Methodology

  1. Material Database: A dictionary containing multiple base materials and their normalized properties across 9+ parameters.

  2. Fitness Function: Weighted scoring system based on desirable traits and cost penalties.

  3. Genetic Algorithm Process:

    • Initialize random population of formulations
    • Evaluate fitness of each formulation
    • Select top-performing "parents"
    • Apply crossover and mutation
    • Iterate for multiple generations
    • Return the optimal formulation

Important Links


References


Key Learnings

  • Interdisciplinary Insight: Blending polymer chemistry with computational algorithms creates impactful industry solutions.
  • Research Depth: Gained strong grounding in literature related to self-healing, thermochromic, antimicrobial, and photocatalytic coatings.
  • GA Implementation: Hands-on application of genetic algorithms helped deepen understanding of evolutionary computation and real-world constraints.
  • Property Trade-offs: Optimizing for cost often compromises performance—a key industrial design insight.
  • Sustainability Emphasis: Exposure to eco-conscious formulation practices shaped our vision for future material design.

Future Scope

  • Integrate ML-based property prediction models for faster optimization
  • Expand the material database to include bio-based or green alternatives
  • Validate computational results via pilot-scale formulation and testing
  • Apply similar modeling to smart textiles, wearables, and biosensors
  • Collaborate with industry partners for real-world deployment

Team Members

  • Aarav Gupta (230008001)
  • Mohak Dadhich (230008023)
  • Prakrut Moon (230008024)
  • Priyanshu Patel (230008026)

This might find funny but we made a logo for our project too

About

Optimize smart coating formulations using genetic algorithms - AI meets materials science for better performance and lower cost.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors