Sensors can be fitted to Electric Motors to monitor a number of data sources, such as Temperature, Humidity and Vibration. In some climates, we use Sump Pumps where basement flooding can regularly happen or help solve dampness issues. These Sump Pumps are either installed in basin dug out in the basement, or along the outside wall of the structure. Most installations are wired directly into the Building's AC power grid, with no Battery Backup supply. Sump Pump's use a float switch to determine the level of water inside the basin, when this reaches a pre-set level, it'll trigger the Pump to remove all water to a second turn off point. Over time, these floats can fail or get stuck, which can cause the motor to run longer than expected, thus causing potential damage to the motor. During the colder months, discharge pipe can also easily freeze up or clog causing more stress on the Pump and pipe. Regular monitoring of these systems is highly recommend during times of extreme wet conditions, such as the spring thaw or during large rain storms. Most current Monitoring systems rely on detecting water seepage in area's you wouldn't normally expect, aka flooding. With STMicroelectonic's' SensorTile.Box our goal is to show another possible Monitoring system, by watching vibrations directly from the Motor or Discharge Pipe, we can watch out for Anomaly's or any other changes to operation of the Sump Pump.
Supplier Documentation and Tools
- SensorTile.box - wireless multi sensor development kit with user friendly app for IoT and wearable sensor applications
- BlueST SDK - Bluetooth Low Energy Sensors Technology Software Development Kit (Python version for Linux Gateways)
- FP-AI-SENSING1 - 4.0.1 -STM32Cube function pack for ultra-low power IoT node with artificial intelligence (AI) application based on audio and motion sensing
- STM32CubeProg - STM32CubeProgrammer software for all STM32
SensorTile.Box Firmware Setup
For this project we will be flashing STMicroelectronic's FP-AI-SENSING1 4.0.01 firmware onto the ST SensorTile.Box. This firmware is an STM32Cube function pack featuring examples to let you connect your SensorTile.Box node to a smartphone over BLE. These examples include, Temperature, Humidity, Pressure, Magnetometer, Gyroscope, Accelerometer, Audio Classification and Activity Recognition.
- Download STM32CubeProg and install the STM32CubeProgrammer application
- Download FP-AI-SENSING1 and unzip the projects.
SensorTile.Box Test Firmware
Boot any Debian based device with WiFi/BLE, such as the STM32MP157C-DK2 install python3
Install blue-st-sdk's python3 dependencies:
Download BlueST SDK repository via git
Run ST's example_ble_1.py project to make sure BLE connection is working:
Known SDK Limitations
Our theory for this project, is to attach the SensorTile.box directly to the discharge pipe of the Sump Pump. As our Sump Pump is installed too deep down the trench for direct connection, the discharge pipe is the best possession.
For this project, we are using a modified version of STMicroelectronic's example_ble_1.py application, patched to log 2400 samples (2 minutes of raw BLE data), and auto-connect to the sensor to work around the current bluepy limitations. Data is stored locally in date stamped log files and served up by Apache for external access.
From our initial findings, we are seeing a consistent vibration pattern from the discharge pipe. At this time, the Motor is consistently running around 8 seconds, every 2 to 3 minutes, so I'm unable to replace it with a broken Sump Pump for comparison purposes. It will take more data samples before we are able to take advantage of STMicroelectronic's AI library. This library would allow us to detect Normal and Ab-Normal vibration patterns.