.png){kind=icon}
Return
Mechanical Anomaly Detection on an Embedded Microcontroller
.png){kind=icon}
PRE
AI
DOI：10.1109/CSCI54926.2021.00159.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper explores machine learning on an embedded device to detect anomalies with sophisticated low-power neural networks. We leverage this deep learning approach to detect mechanical anomalies as they occur on a top-load washing machine. We collect normal data from balanced laundry loads and abnormal data from unbalanced laundry loads, as they are being washed by the machine. The normal data is then used to train two different neural network models: autoencoder and variational autoencoder. This model is ported to an Arduino Nano microcontroller mounted to the washing machine. Using the autoencoder model, the microcontroller detects unbalanced washing machine loads with 92% accuracy, 90% precision and 99% recall. The battery life for this autoencoder model is 20 hours on 5 V lithium batteries, which is only 14.9% less than the life of a basic LED-blink application on the same platform.
Keywords:
anomaly
neural network
autoencoder
VAE
Journal
I
IF:
0
Papers:
6
Citations:
0
Organization
Cited Papers
Geographical patterns of Toxoplasma gondii genetic diversity revealed by multilocus PCR-RFLP genotyping.png)
Parasitology
ParasitologyIF0
PREAI
ShareSaveProbiotic and postbiotic activity in health and disease: comparison on a novel polarised ex-vivo organ culture modelGut
OAAI
GutIF0
OAAIShareSaveBehavior of Neutrophil Granulocytes during Toxoplasma gondii Infection in the Central Nervous SystemOAAI
OAAIShareSaveShareSave
View more