Bearing failure is the most common failure mode in rotating machinery and can result in large financial losses or even casualties. However, complex structures around bearing and actual variable working conditions can lead to large distribution difference of vibration signal between a training set and a test set, which causes the accuracy-dropping problem of fault diagnosis. Thus, how to improve efficiently the performance of bearing fault diagnosis under different working conditions is always a primary challenge. In this paper, a novel bearing fault diagnosis under different working conditions method is proposed based on domain adaptation using transferable features(DATF). The datasets of normal bearing and faulty bearings are obtained through the fast Fourier transformation (FFT) of raw vibration signals under different motor speeds and load conditions. Then we reduce marginal and conditional distributions simultaneously across domains based on maximum mean discrepancy (MMD) in feature space by refining pseudo test labels, which can be obtained by the nearest-neighbor (NN) classifier built on training data, and then a robust transferable feature representation for training and test domains is achieved after several iterations. With the help of the NN classifier trained on transferable features, bearing fault categories are identified accurately in final. Extensive experiment results show that the proposed method under different working conditions can identify the bearing faults accurately and outperforms obviously competitive approaches.
Through studying the mechanics, energy, and deformation features of rock under uniaxial cyclic loading and unloading, the findings are as follows: (1) under cyclic loading and unloading, the curve of stress and strain for loading and unloading in every cycle was not superposition reciprocally but formed an acutifoliate hysteresis loop. The distribution of the hysteresis loop became denser with the cycles and moved toward the direction of strain increasing. (2) The area of the hysteresis loop indicated the inner damage degree of rock. And the hysteresis energy accumulated was stronger; the damage of rock was more serious. Furthermore, the hysteresis energy grew linearly along with load, and the hysteresis energy accumulated had a trend exponential growth with cycle continuing. (3) The elasticity modulus grew in the form of logarithm as a whole. In each cycle, elasticity modulus for unloading was greater than that for loading. When it exceeded a certain value, elasticity modulus for reloading was less than elasticity modulus for unloading. (4) The cyclic loading and unloading had a strength impact that was gradually stronger and stronger as the cycle went on the sample of rock.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.