Utilization of Machine Learning Techniques in Hot-Film Based Airflow Rate Sensors for Improving Flow Measurement

Abstract

This article presents a novel airflow rate sensing method based on the principle of a hot-film flow sensing device with data-driven machine learning (ML) models. In addition, to combine the two signals of the sensor (the resistance changes of the heaters) and predict the output (airflow rate), three different ML multivariate regression models, i.e., multiple linear regression (MLR), k-nearest neighbor (KNN), and deep neural network (DNN) models, are trained and compared using 8400 experimentally obtained data. Using sensor fusion techniques, the average mean absolute error (MAE) and mean squared error (MSE) of the KNN model are determined to be 0.01522 and 0.00132, respectively, in the range of 0–5.07 standard liters per minute. Compared with the average results obtained using only a single input, those obtained using a dual input indicate a significant decrease in the MAE and MSE by 85.69% and 96.68%, respectively. Furthermore, a transient analysis of the ML-based flow sensor is conducted to investigate the response time and transient characteristics of the MLR, KNN, and DNN models. The results of this study contribute to the advancement of airflow management systems for various industrial applications, such as building ventilation, gas leakage detection, and energy systems.