Optimizing alpha–beta filter for enhanced predictions accuracy in industrial applications using Mamdani fuzzy inference system

Abstract

This work presents a novel approach for dynamically optimizing the alpha–beta filter parameters through the Mamdani fuzzy inference system (MFIS) for industrial applications to estimate the state of dynamic systems based on sensor measurements. Our proposed method has two important components: the primary predictor utilizing the alpha–beta algorithm, and a rule-based mechanism leveraging the Mamdani fuzzy inference system. To illustrate our approach and simplify the demonstration, we selected two types of sensors: temperature and humidity. The model efficiently processes input from these sensors, refining the sensor data to filter out noise and improve prediction accuracy. The integration of MFIS significantly improves the system’s performance, significantly reducing the root mean square error (RMSE) and mean absolute error (MAE), which are critical indicators of predictive accuracy. To validate the effectiveness and robustness of our method, we executed an extensive set of experiments , which affirm the superior performance of our model. • Integrates Mamdani fuzzy inference with the alpha-beta filter for better estimation. • Improves accuracy in sensors, reducing RMSE and MAE in dynamic state estimation. • Extensive experiments confirm superior performance for industrial applications. • Future work explores robotics, surveillance, and autonomous navigation enhancements.