Abstract: A system and method concerns accurate bearing fault diagnosis and prognosis (FDP), critical for optimal maintenance schedules, safety and reliability. Existing methods face challenges: the bearing condition is healthy in most of the service time, so it is critical to detect the occurrence of faults and the start point for prognosis in real applications. Due to differences in manufacturing quality, assembly quality, and different operating conditions, it is difficult to describe the fault dynamic using one single fault model. A hybrid Bayesian estimation-based bearing FDP framework with fault detection and automatic fault model selection is disclosed. A convolutional neural network is used to detect fault and select the appropriate fault dynamic model. To improve performance with different bearings under different operating conditions, continuous wavelet coefficient matrices power spectrum of vibration are fused with operating conditions to build information maps for fault detection and model selection.

Abstract: Fault diagnosis and prognosis (FDP) is critical for ensuring system reliability and reducing operation and maintenance (O&M) costs. Lebesgue sampling based FDP (LS-FDP) is an event-based approach with the advantages of cost-efficiency, uncertainty management, and less computation. In previous works, LS-FDP approaches are mainly model-based. However, fault dynamic modeling is difficult and time consuming for some complex systems and this severely hinders the applications of LS-FDP. To address this problem, this present disclosure presents a data-driven based LS-FDP framework in which deep belief networks (DBN) and particle filter (PF) are integrated to achieve fault state estimation and remaining useful life (RUL) prediction. In the proposed approach, DBN learns the state evolution model and the Lebesgue time transition model, which are used as diagnostic and prognostic models in PF for FDP.

Abstract: Deep learning-based diagnosis methods currently face some challenges and open problems. First, domain knowledge of fault modes and operating conditions are not integrated in most existing approaches, which results in low diagnosis accuracy and training efficiency. Second, existing methods treat all features with indiscriminate attention, which causes unnecessary computation and even false diagnosis results in some cases. Third, multi-task diagnosis becomes more important for health maintenance. To address these challenges, a deep residual convolutional neural network is provided with an enhanced discriminate feature learning capability and information fusion for multi-task bearing fault diagnosis. Domain knowledge is integrated with monitoring data to build the information map. Two attention modules are introduced to enhance the discriminate feature learning ability, and two classifiers are employed for multi-task diagnosis, providing significant improvements in diagnostic accuracy and training efficiency.

Abstract: Described herein are methods of Lithium battery health management based on a single particle model as shown and described herein to provide for reliable and accurate battery factor estimation to ensure efficient system operation.