Sensor-Driven Data Collection System for Predicting Fan Behavior

This study identifies representative sensors for monitoring fan performance by analyzing vibration data collected from piezoelectric sensors during various operational modes. The dataset, which includes measurements at a rate of 300 samples/sec from 10 sensors, covers six modes of operation: Maximum Speed, Maximum Speed with Oscillation, Minimum Speed, Minimum Speed with Oscillation, Minimum to Maximum Speed, and a comprehensive dataset combining all modes. Using statistical methods such as correlation matrices and eigenvalues, we identify sensors with strong correlations to the fan’s behaviour. Regression techniques are applied to predict the target variable, and the Mean Squared Error (MSE) is used to assess the accuracy of the models. This analysis facilitates sensor optimization, ensuring the minimum number of sensors required for accurate predictions.