How to classify the different actions performed by a drilling machine with ST AIoT Craft

Denise SANFILIPPO · ‎2025-12-18

Introduction

This article showcases how to implement the classification of the different actions performed with a drilling machine, such as idle, screw, drilling, and percussive drilling states. STMicroelectronics offers a solution using the machine learning core (MLC) integrated into the smart MEMS sensor ISM330DHCX available on the STWIN.box (STEVAL-STWINBX1). For wireless tracking, the ST AIoT Craft mobile app, available on Google Play Store and Apple Store, can be used.

1. Getting started

To begin, click on the drilling machine project example. A pop-up window appears with a brief description, as shown in Figure 1. Next, click on the three vertical dots next to the [Try out] button and select [View details].

Figure 1: Drilling machine project

This reveals that the project uses a single AI model named drilling_machine, targeting the STEVAL-STWINBX1 and the STEVAL-STWINKT1B and the IMU ISM330DHCX with a machine learning core. The model classifies data into four categories: idle, screwing, drilling, and percussive_drilling.

Figure 2: Drilling Machine: a ready-to-run use case

You can evaluate the AI model either through the web application or via the mobile app. If you choose the mobile app, QR codes for installation are provided.

Figure 3: Choose your environment: either Web browser or ST AIoT Craft mobile app

For now, let's focus on evaluating the AI model directly on the web application using the STWIN.box (STWINBX1). The same procedure is valid for the STWIN SensorTile wireless industrial node (STWINKT1B).

2. Firmware update and connection

Update the firmware: connect the STWINBX1 to your PC using a USB Type-C® cable.
Turn on the board in DFU mode by holding down user button and powering on the board via the power switch.
Flash the firmware: Click the [Flash firmware] button to download and stream the firmware binary to the board.
Ensure that your browser detects the connected STWINBX1. Once the firmware update is complete, establish a connection with the board by clicking [Connect device].
Enable sensors: The AI model is downloaded and programmed onto the STWINBX1. The accelerometer settings are configured as follows:

ODR = 6667 Hz
FS = 16 g
Machine learning core enabled

3. Evaluation phase

Click the [Start] button to begin evaluating the AI model.
STWINBX1 recognizes the following states based on its placement and movement:

Idle
Screwing
Drilling
Percussive Drilling

To end the evaluation, click the [Stop] button.

Conclusion

You can effectively classify the state of your activity using the drilling machine project example on the ST AIoT Craft platform: share your experience!

Create your own solution exploring the "My datasets" section and the "My Projects" section.

Figure 4: Explore My datasets and My Projects sections

Stay tuned for more insights on how to leverage ST AIoT Craft for your projects!