Bearings are one of the most critical components in many industrial machines. Predicting remaining useful life (RUL) of bearings has been an important task for condition-based maintenance of industrial machines. One critical challenge for performing such tasks in the era of the Internet of Things and Industrial 4.0, is to automatically process massive amounts of data and accurately predict the RUL of bearings. This paper addresses the limitations of traditional data-driven prognostics, and presents a new method that integrates a deep belief network and a particle filter for RUL prediction of hybrid ceramic bearings. Real data collected from hybrid ceramic bearing run-to-failure tests were used to test and validate the integrated method. The performance of the integrated method was also compared with deep belief network and particle filter-based approaches. The validation and comparison results showed that RUL prediction performance using the integrated method was promising.

In this paper; a new method for gear pitting fault detection is presented. The presented method is developed based on a deep sparse autoencoder. The method integrates dictionary learning in sparse coding into a stacked autoencoder network. Sparse coding with dictionary learning is viewed as an adaptive feature extraction method for machinery fault diagnosis. An autoencoder is an unsupervised machine learning technique. A stacked autoencoder network with multiple hidden layers is considered to be a deep learning network. The presented method uses a stacked autoencoder network to perform the dictionary learning in sparse coding and extract features from raw vibration data automatically. These features are then used to perform gear pitting fault detection. The presented method is validated with vibration data collected from gear tests with pitting faults in a gearbox test rig and compared with an existing deep learning-based approach.

Traditional data driven prognostics requires establishing explicit model equations and much prior knowledge about signal processing techniques and prognostic expertise, and therefore is limited in the age of big data. This paper presents a deep learning based approach for bearing remaining useful life (RUL) prediction with big data. This approach has the ability to automatically extract important features that can be used for RUL predictions. The presented approach is tested and validated using data collected from bearing run-to-failure tests and compared with existing PHM methods. The test results show the promising bearing RUL prediction performance of the deep learning based approach.