Live demonstration: Autoencoder-based predictive maintenance for IoT
PK Gopalakrishnan, B Kar, SK Bose… - … on Circuits and …, 2019 - ieeexplore.ieee.org
2019 IEEE International Symposium on Circuits and Systems (ISCAS), 2019•ieeexplore.ieee.org
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.
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.
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.
ieeexplore.ieee.org
以上显示的是最相近的搜索结果。 查看全部搜索结果