Intelligent prediction of wastewater treatment blower bearing temperature based on random event agent model

<p indent="0mm">The bearing temperature of a wastewater treatment blower is a critical parameter for assessing operational status. It provides essential insights into the bearing’s working condition and lubricate state. Excessive temperatures can lead to bearing damage, lubrication failure, or even blower shutdown. To achieve an accurate prediction of blower bearing temperature, this study proposes an intelligent prediction method based on a random event agent model. First, a primary model using a fuzzy neural network is established. This model is dynamically adjusted using data from outlet air pressure, high-speed shaft vibration, and inlet air temperature, allowing precise temperature predictions under normal conditions without the influence of random events. Second, a random event agent model (REAM) is designed, incorporating fuzzy rules to describe the impact of different random events on blower bearing temperature. By combining the REAM with the primary model, accurate temperature predictions are achieved even during random events. The proposed model was applied to predict the blower bearing temperatures of wastewater treatment blowers. Its performance, before and after random event triggers, was evaluated through experiments. Results demonstrate that this method enhances the accuracy of blower bearing temperature predictions under random events.