Bearings are key components in modern power machines. Effective diagnosis of bearing faults is crucial for normal operation. Recently, the deep convolutional neural network (DCNN) with 2D visualization technology has shown great potential in bearing fault diagnosis. Traditional DCNN-based fault diagnosis mostly adopts a single learner with one input and is time-consuming in sample and network construction to obtain a satisfied performance. In this paper, a scheme combining diverse DCNN learners and an AdaBoost tree-based ensemble classifier is proposed to improve the diagnosis performance and reduce the requirement of sample and network construction simultaneously. In this scheme, multiple types of samples can be constructed independently and employed for diagnosis simultaneously; next, the same number of DCNN learners are built for underlying features extraction and the obtained results are integrated and finally fed into the ensemble classifier for fault diagnosis. An illustration based on the Case Western Reserve University datasets is given, which proves the superiority of the proposed scheme in both accuracy and robustness. Herein, we present a universal scheme to improve the diagnosis performance, and give an example for practical application, where the signal preprocessing and image sample construction methods can also be applied in other vibration-based analysis.

Aiming at a Top Gas Recovery Turbine Unit (TRT) with double support rotor and the extending disk end, theoretical and experimental analysis about influence of cylindrical bearing and four-lobe bearing on vibration of TRT rotor system are conducted in this paper. The results indicate that vibration of the rotor supported by cylindrical bearing is more stable than that supported by four-lobe bearing at the driving end (DE) and the nondriving end (NDE). The amplitude of rotor is supported by both of these types of bearing increases as the speed increases at the NDE, while the amplitude of the DE remains unchanged. Comparing with the result of theoretical analysis, the practical test results are more consistent with the theoretical response analysis conducted by applying unbalanced mass at the extending disk end. This paper presents an analysis method of the critical characteristics of a double support rotor system with the extending disk end and provides reference value for dealing with vibration fault of double support rotor system with the extending disk end.