Vibration Analysis Deep Learning
- 0 Collaborators
Streamed vibration charts are analyzed by an AI system in real time. Detected anomalies are logged and surrounding environment data is captured for further model learning purposes. The application is machine anomaly detection for predictive maintenance. ...learn more
Project status: Under Development
HPC, Networking, Internet of Things, Artificial Intelligence
Intel Technologies
Intel Python,
OpenVINO
Overview / Usage
The purpose of this system is to protect very expensive mechanical equipment from damage due to occasional exposure to high stress operations. A Proof of Concept is in operation and being evaluated. The idea is to create an adaptive predictive maintenance system that keeps improving with operation time and reduces the diagnostic work when measurements go out of specified values.
Methodology / Approach
6 Sigma DMAIC methodology is being used to implement this system
Define, Measure, Analyze, Implement and Control. Agile software methods are used between the Analyze and Implement steps to ensure requirements are being met.
The Model development method involved Convolution NN on time series data.
Technologies Used
XEON
Python
OpenVINO
[1] Darveau, P. Prognostics and Availability for Industrial Equipment Using High Performance Computing (HPC) and AI Technology. Preprints 2021, 2021090068 .
[2] Darveau, P., 1993. C programming in programmable logic controllers.
[3] Darveau, P., 2015. Wearable Air Quality Monitor. U.S. Patent Application 14/162,897.
Repository
https://github.com/hexagontechinc/WIP