Skip to content

Kianmhz/FaultLens

Repository files navigation

FaultLens Logo FaultLens

FaultLens banner

FaultLens is an AI-powered incident analysis platform that transforms raw operational data into clear, structured fault trees for fast and explainable root-cause analysis.

Instead of manually inspecting thousands of sensor readings and log entries, users upload incident data and FaultLens automatically produces:

  • Event timeline highlighting key anomalies and transitions
  • AI-generated incident summary
  • Multi-layer fault tree with AND / OR logic gates
  • Evidence linked to every node (logs, telemetry, documentation)
  • Confidence scoring for causes and relationships

FaultLens helps maintenance, safety, and reliability engineers quickly understand what failed, why it failed, and how subsystem interactions led to the incident.


How It Works

1. Upload

Users provide:

  • Operational logs (telemetry / sensor time series)
  • A handbook or documentation describing signal meanings and system behavior
  • Optional analyst remarks or context

Example csv files and handbooks can be found here: https://drive.google.com/drive/folders/1z5hGNmzOw6E0qeVdHHFHfcziqmboOze1?usp=sharing


2. Analyze

The backend AI pipeline:

  • Parses and normalizes time-series data
  • Detects anomalies and threshold violations
  • Correlates behavior across subsystems
  • Infers causal relationships
  • Constructs layered fault trees
  • Grounds each node with supporting evidence

All reasoning steps are traceable and explainable.


3. Visualize

FaultLens generates an interactive investigation workspace featuring:

  • High-level incident overview
  • Chronological event timeline
  • Interactive fault tree visualization
  • Node-level evidence inspection
  • Risk and confidence assessment

Users can click any fault tree node to inspect the data and reasoning behind it.


Tech Stack

  • Frontend: Nuxt 4 + Nuxt UI
  • Backend: Node.js
  • Database: MongoDB
  • AI: OpenAI API
  • Visualization: Mermaid.js

Setup

Install dependencies:

npm install

Run the development server:

npm run dev

The app will be available at:

http://localhost:3000

Environment Variables

Create a .env file (see .env.example for details):

OPENAI_API_KEY=your_openai_api_key
MONGODB_URI=your_mongodb_connection_string

Use Cases

  • Industrial equipment failures
  • Safety incidents and near-misses
  • Manufacturing process deviations
  • Infrastructure and reliability investigations

FaultLens is designed as infrastructure AI: one core reasoning engine adaptable across industries.


FaultLens — Because failures have a past.

About

Infrastructure AI for root cause analysis using fault trees, timelines, and grounded evidence.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages