# Self-Sensing of Piezoelectric Micropumps: Gas Bubble Detection by Artificial Intelligence Methods on Limited Embedded Systems

## TL;DR

This paper introduces a self-sensing piezoelectric micropump that uses AI on embedded systems to detect gas bubbles, improving drug dosing accuracy in portable devices.

## Contribution

A novel self-sensing approach using AI on embedded systems for gas bubble detection in micropumps, avoiding additional sensors.

## Key findings

- An embedded AI model detects gas bubbles with 99.41% accuracy using the piezoelectric diaphragm's sensing capability.
- The deployed model has a memory footprint of 15.23 kB and a runtime of 182 µs on an STM32G491RE microcontroller.
- Training datasets were generated from 11 micropumps at an automated testbench for bubble injections.

## Abstract

Gas bubbles are one of the main disturbances encountered when dispensing drugs of microliter volumes using portable miniaturized systems based on piezoelectric diaphragm micropumps. The presence of a gas bubble in the pump chamber leads to the inaccurate administration of the required dose due to its impact on the flowrate. This is particularly important for highly concentrated drugs such as insulin. Different types of sensors are used to detect gas bubbles: inline on the fluidic channels or inside the pump chamber itself. These solutions increase the complexity, size, and cost of the microdosing system. To address these problems, a radically new approach is taken by utilizing the sensing capability of the piezoelectric diaphragm during micropump actuation. This work demonstrates the workflow to build a self-sensing micropump based on artificial intelligence methods on an embedded system. This is completed by the implementation of an electronic circuit that amplifies and samples the loading current of the piezoelectric ceramic with a microcontroller STM32G491RE. Training datasets of 11 micropumps are generated at an automated testbench for gas bubble injections. The training and hyper-parameter optimization of artificial intelligence algorithms from the TensorFlow and scikit-learn libraries are conducted using a grid search approach. The classification accuracy is determined by a cross-training routine, and model deployment on STM32G491RE is conducted utilizing the STM32Cube.AI framework. The finally deployed model on the embedded system has a memory footprint of 15.23 kB, a runtime of 182 µs, and detects gas bubbles with an accuracy of 99.41%.