Bearing fault signal detection and prediction based on an improved particle filter method

Awareness and predicting bearing health are challenging because of uncertainties in the operating environment and noise in fault-signal measurements. Considering the sudden occurrence of bearing faults and their relatively brief duration over the bearing lifespan, this paper presents a fusion framework that combines an eighth-order polynomial model with a cuckoo search thought particle filter (CST-PF) method to estimate the failures occurrences. The fault characteristic signals are extracted from the amplitude spectrum within a specific frequency range and modeled by an eighth-order polynomial model. Cuckoo search (CS) is introduced to address the particle dilution in particle filter (PF). Furthermore, the proposed CST-PF refines the step size update equations and discovery probability for balancing the search speed and accuracy, thus enhancing the adaptability to bearing fault diagnosis and prediction. It ensures the parameter convergences in the prediction model by learning the fault characteristic signal during regular bearing operations, facilitating accurate predictions of subsequent failures. Validation results show that the eighth-order model accurately captures changes in fault characteristic signals throughout the bearing lifespan, with MAE and RMSE metrics surpassing those of traditional models. The CST-PF method demonstrates superior predictive ability compared to the Cuckoo search particle filter (CS-PF), traditional PF, and other PF variants.