MCU Based Edge Computing Platform for Liquid Level Measurement

Abstract

An edge computing system based on micro control unit (MCU) for liquid level measurement is proposed in this paper. The system includes a solenoid electromagnet for bottle hit and a microphone to capture sound waves. The signals are converted from time domain to frequency domain by Fast Fourier Transform (FFT), employing an artificial intelligence (AI) model to predict the water level. Artificial Neural Network (ANN) model is applied for classification on the MCU. When optimizing hyperparameters, the accuracy of each parameter combinations should be considered. Ensure the model size suits the limited MCU memory and computing capabilities. The experimental results can be up to 99% accurate under multiple tests.