Vibration Classification and Anomaly Detection with BrainChip’s Akida

Many predictive maintenance applications can use neural networks to classify vibration data from accelerometers. In this Expert Project we walk you through data collect, model training, and deployment to BrainChip's Akida™ Development Kit Raspberry Pi containing an Akida AKD1000 for neural network acceleration.

Some key highlights of this project include:

Time Between Samples for Accelerometer Data
Validation Training Results for Vibration Classification
Anomaly Explore (k-means) for Accelerometer Data
center: 0.121976525
edge: 1.9035794e-11
off: 0.790965
on: 0.08705848
/home/ubuntu/brainchip-accelerometer
Loaded runner for "Brainchip / bc-pred-main-anom"
classification:
{'anomaly': -0.4078322649002075}
timing:
{'anomaly': 0, 'classification': 0, 'dsp': 0, 'json': 0, 'stdin': 28}

Command Line Output showing Classification and Anomaly

Find the full documentation here.

Comments

Subscribe

Are you interested in bringing machine learning intelligence to your devices? We're happy to help.

Subscribe to our newsletter