Journal bearings are the most common type of bearings in which a shaft freely rotates in a metallic sleeve. They find a lot of applications in industry, especially where extremely high loads are involved. Proper analysis of the various bearing faults and predicting the modes of failure beforehand are essential to increase the working life of the bearing. In the current study, the vibration data of a journal bearing in the healthy condition and in five different fault conditions are collected. A feature extraction method is employed to classify the different fault conditions. Automatic fault classification is performed using artificial neural networks (ANN). As the probability of a correct prediction goes down for a higher number of faults in ANN, the method is made more robust by incorporating deep neural networks (DNN) with the help of autoencoders. Training was done using the scaled conjugate gradient algorithm and the performance was calculated by the cross entropy method. Due to the increased number of hidden layers in DNN, it is possible to achieve a high efficiency of 100% with the feature extraction method.
This paper presents a method of using a sensor with uniform Bragg grating with appropriately generated zone chirp. The presented method can be used for measuring two physical quantities, namely strain and temperature. By providing the same temperature sensitivity and different sensitivity to strain of two parts of a sensor, and experimental measurement of qualities of the proposed system and its calibration (experimental determination of sensitivity), verification of the results obtained from laboratory tests and the possibility of its practical implementation has been confirmed. The sensor grating was placed in such a way that its half was in the zone of a variable value of axial strain caused by changes of the cross-section of the sample. The other half, however, was in the zone of a constant cross-section of the sample and of constant value of strain, caused by the force stretching the sample. The obtained errors of non-linearity of processing characteristics for measuring strain and temperature of the proposed system were 2.7% and 1.5% respectively, while coefficients of sensitivity to strain and temperature were 0.77 x 10-6 m/e and 4.13 x 10-12 m/K respectively. The maximum differences between the values obtained from the indirect measurement and the set values were 110 μe for strain and 3.8°C for temperature, for a strain of 2500 μe and a temperature of 40°C.