Live Demonstration: Autoencoder-Based Predictive Maintenance for IoT
- Resource Type
- Conference
- Authors
- Gopalakrishnan, Pradeep Kumar; Kar, Bapi; Bose, Sumon Kumar; Roy, Mohendra; Basu, Arindam
- Source
- 2019 IEEE International Symposium on Circuits and Systems (ISCAS) Circuits and Systems (ISCAS), 2019 IEEE International Symposium on. :1-1 May, 2019
- Subject
- Bioengineering
Components, Circuits, Devices and Systems
Power, Energy and Industry Applications
Signal Processing and Analysis
Vibrations
Sensors
DC motors
Feature extraction
Field programmable gate arrays
Anomaly detection
Predictive maintenance
- Language
- ISSN
- 2158-1525
This live demo aims to show the performance of a two-layer neural network applied to predictive maintenance. The first layer encodes features based on prior knowledge, while the second layer is trained online to detect anomalies. The system is implemented on an FPGA, acquiring real-time data from sensors attached to a motor. Faults can be triggered artificially in real-time to demonstrate anomaly detection.