Back to projects

Acoustic-Based Real Time Diagnosis for machines

End-to-end engine diagnostic system using audio

Creator/Developer2024
View Project

*Description

Connected a Raspberry Pi with a Node.js server to MongoDB to monitor an engine in real time. Then, I placed a microphone to capture disturbed sounds and, using Vector Search, compared them to a normal/abnormal sound.

*Key Achievements

  • •Leveraged MongoDB Atlas Vector Search for real-time audio diagnostics
  • •Developed a real-time audio-based AI diagnostics system
  • •Improved vehicle diagnostics accuracy and efficiency
  • •Created a real-time audio-based AI diagnostics system
  • •Improved vehicle diagnostics accuracy and efficiency

*Technologies

Raspberry PiNode.jsSwiftUbuntuVector SearchMongoDBPythonAWSBedrockGit

*Project Gallery

Youtube video of the project

High-level architecture diagram

High-level architecture diagram