Skip to content

This project detects failure of machine. It also detects the type of failure and gives instructions to machine operator in simple language using report.

Notifications You must be signed in to change notification settings

chetan0220/Predictive-Maintenance-and-Diagnostic-Report-Generation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🛠 FailGuard AI: Predictive Maintenance and Diagnostic Report Generation ⚙️


Predict. Protect. Prevent. FailGuard AI is an intelligent predictive maintenance system that classifies machine failures, diagnoses reasons for failures, and generates expert-level diagnostic reports using LLMs.


Overview

FailGuard AI combines Machine Learning (ML) and Large Language Models (LLMs) to:

  • Predict machine failure based on real-time attributes.
  • Classify the reason for failure (tool wear, overstrain, power, etc.).
  • Generate natural language diagnostic reports automatically for operators and engineers.

It is designed to minimize downtime, prevent unexpected machine failures, and improve maintenance planning.
Dataset --> Click Here


Methodology

Methodology_Block_Diagram The above figure shows methodology used.


Technologies & Algorithms Used

Machine Learning Algorithms Ensemble Learning Algorithms Synthetic Data Generation:

  • Synthetic Minority Oversampling Technique (SMOTE)
  • Conditional Tabular Generative Adversarial Network (CTGAN)

Large Language Models: LLaMA-3.1-Nemotron-70B-Instruct Python Numpy Pandas Scikit-learn SMOTE CTGAN Streamlit


Demo Video

PdMDemoFinal.mp4

If you have any query, feedback or suggestion feel free to drop a mail at chetan.mahale0220@gmail.com :)

About

This project detects failure of machine. It also detects the type of failure and gives instructions to machine operator in simple language using report.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published