You are on page 1of 1

Pump anomaly detection based on More details on this use-case 

vibrations Approach
In this project, we used a first circuit to log the vibration data of the
pump using an accelerometer. We gathered both normal and abnormal
signals, which were created by closing the taps that diverted the flow of
water.
We then created an anomaly detection model in the NanoEdge AI
Studio. The software tool generated the most optimized model for our
learning data. The model created was loaded on a Proteus board and
connected to a first circuit. This prototype allowed us to detect both
normal and abnormal data in real time.
We then moved the Proteus board containing the model to a second
circuit. We used on-edge learning to retrain the same model with the
signals of the new circuit in few seconds. The model performed well on
the new circuit, even if it was originally optimized for the first one.
Sensor
Accelerometer (3-axis): ISM330DHCX
Data
Regular and abnormal signals:
- Regular signals: 640 signals of pump vibrations with the first circuit in
Predictive maintenance is a maintenance strategy that uses machine learning to predict when
equipment is likely to fail. Industrial equipment, such as water pumps, produce different signals a normal state
during operation. By placing sensors on these pieces of equipment for data collection, it is - Abnormal signals: 440 signals of pump vibrations with one of both
possible to use machine learning to recognize normal and abnormal behavioral patterns. This deviations blocked
proactive approach aims at minimizing downtime, increasing efficiency, and extending Signal length: 768 (256 per axis, 3 axes)
equipment lifespan. We implemented the following approach on a water pump: we collected Data rate: 6667 Hz, range: 2g
and analyzed its vibrations and used a machine learning model to detect anomalies. This
approach can easily be adapted to many other industrial machines. Results
Anomaly detection classes:
100% accuracy, 7.8 Kbytes RAM, 6.1 Kbytes Flash

stm32ai.st.com

You might also like