Renesas RA Family Motor Failure Detection Example by TensorFlow for RA6T1

PublishTime：2022-08-03

■Improving operational reliability is an important milestone for increasing stability and quality. Maintenance is one of the crucial disciplines that harbors great potential for improvement and cost savings and increases the operational reliability at the same time. New technologies like the Embedded AI (e-AI) leads to a significant improvement within the maintenance discipline. Specifically, within the motor driven systems, e-AI does not only make maintenance more efficient but also enables understanding of the reasons which could lead to downtime and enables also preventing them in the first place.
■In this example, the maintenance discipline has been realized and implemented by involving a simple use case that is able to detect an abnormal state within the system behavior as a potential failure. Implemented e-AI algorithm (based on TensorFlow) discovers a failure due to an abnormal load condition of the motor. The abnormal load condition is detected by monitoring the current and rotation speed by a so-called inference model representing a trained neural network. Using only a single MCU (RA6T1), the motor control and fault detection algorithm are run simultaneously.

Brand of Product：	Renesas
Part#：	RA 、 RA Family 、 RA6T1 More Part#
Product Category：	MCU More
Application：	More
Data Type：	Application note & Design Guide More
Safety & Environment Standards：	More
Operating Temperature：	Please see the document for details
Qualification Grade：	More
Qualification Approval：	More
Package：
Language：	English Chinese Chinese and English Japanese
Date of Creation：	Mar.5.2021
Version Number：	Revision 1.00
Data Encoding：
Data Size：	4.1 MB

Data section preview(2pages)

- The full preview is over. If you want to read the whole 33 page document,please Sign in/Register -

Download

+1 Like
Add to Favorites

Recommend

Technical Resources

More>

All reproduced articles on this site are for the purpose of conveying more information and clearly indicate the source. If media or individuals who do not want to be reproduced can contact us, which will be deleted.

Integrated Circuits