The rolling bearing is a critical part of rotating machinery and its condition determines the performance of industrial equipment; it is necessary to detect rolling bearing faults as early as possible. The traditional methods of fault diagnosis are not efficient and are time-consuming. With the help of deep learning, the convolution neural network (CNN) plays a huge role in the data-driven methods of bearing fault diagnosis. However, the vibration signal is non-stationary, contains high noise, and is one-dimensional, which is difficult to analyze directly by the CNN model. Considering the multi-domain learning as an advantage of deep learning, this paper proposes a novel rolling bearing fault diagnosis approach using an improved one-dimensional (1D) and two-dimensional (2D) convolution neural network (CNN) of two-domain information learning. The constructed fault diagnosis model combining 1D and 2D CNN extracts the fault features from the two-domain information of bearing fault samples. The padding and dropout technology are utilized to fully extract features from the raw data and reduce over-fitting. To prove the validity of the proposed method, this paper performs two tests with two bearing datasets, the Case Western Reserve University (CWRU) bearing dataset and the Dalian University of Technology (DUT) vibration laboratory dataset. The experimental results show that our proposed method achieves high recognition accuracy of rolling bearing fault states via two-domain learning of monitoring data, and there is no manual experience necessary. Vibration data under strong noise were also used to test the method, and the results show the superiority and robustness of the proposed method.

Rolling bearings are the vital components of large electromechanical equipment, thus it is of great significance to develop intelligent fault diagnoses for them to improve equipment operation reliability. In this paper, a fault diagnosis method based on refined composite multiscale reverse dispersion entropy (RCMRDE) and random forest is developed. Firstly, rolling bearing vibration signals are adaptively decomposed by variational mode decomposition (VMD), and then the RCMRDE values of 25 scales are calculated for original signal and each decomposed component as the initial feature set. Secondly, based on the joint mutual information maximization (JMIM) algorithm, the top 15 sensitive features are selected as a new feature set and feed into random forest model to identify bearing health status. Finally, to verify the effectiveness and superiority of the presented method, actual data acquisition and analysis are performed on the bearing fault diagnosis experimental platform. These results indicate that the presented method can precisely diagnose bearing fault types and damage degree, and the average identification accuracy rate is 97.33%. Compared with the refine composite multiscale dispersion entropy (RCMDE) and multiscale dispersion entropy (MDE), the fault diagnosis accuracy is improved by 2.67% and 8.67%, respectively. Furthermore, compared with the RCMRDE method without VMD decomposition, the fault diagnosis accuracy is improved by 3.67%. Research results prove that a better feature extraction technique is proposed, which can effectively overcome the deficiency of existing entropy and significantly enhance the ability of fault identification.

As the different distribution between source and target domain, rolling bearing fault diagnosis based on domain adaptation has achieved a good result in unlabeled sample fault diagnosis of target domain. However, most transfer strategies focus mainly on the domain invariant feature between the source and target domains, with little attention paid to the intrinsic feature of the target domain. This limitation causes poor knowledge transfer from the source domain due to domain confusion. Therefore, this paper propose a novel method for unlabeled rolling bearing fault diagnosis in the target domain that leverages both the intrinsic features of the target domain and the shared label space between the two domains. Firstly, a new deep clustering network is constructed to extract the intrinsic features of target domain, where these features are clustered several central areas based on their same attributive feature. Secondly, the novel adversarial domain adaptation network is designed to extract the invariant features in order to construct the sharing label space between source and target domain. Thirdly, the new pseudo label technology is introduced to mark the target unlabeled data by fusing the invariant feature of target domain with the sharing label space, and eliminate the negative knowledge transfer. Finally, these marked labels combining the intrinsic feature of target domain are used to train the fault diagnosis classifier, where this realizes a well-prediction model for the target domain. Several transfer tasks on two rolling bearing datasets demonstrate the efficiency of proposed method. The proposed transfer technology realizes the accuracy prediction of rolling bearing state on target unlabeled samples. Moreover, the efficiency of method is better than the contrasting method, and this new diagnostic technology offers a promising fault diagnosis tool under some practical industrial problem.

Power MOSFETs play a crucial role in power electronic systems, and accurately predicting their remaining useful life (RUL) is fundamentally important for enhancing the reliability, safety, and maintenance planning of such systems. To this end, this paper develops an innovative prognostic framework for predicting RUL of MOSFET devices. Firstly, a power cycle accelerated aging experimental platform under constant shell temperature fluctuation is constructed to obtain the performance degradation parameters of MOSFETs. Secondly, a sample convolutional interaction network (SCINet) is applied to historical data, learning long-term degradation trends via multi-step prediction. Subsequently, a non-linear fractional Brownian motion degradation model is constructed incorporating measurement uncertainties. A state-parameter joint estimation method is then developed by combining a state-space model with Kalman filtering, particle filtering and maximum likelihood estimation. The proposed framework fuses both SCINet predictions and historical observations for self-adaptive updating of states and parameters. Combined with degradation state recursive strategy, a Monte Carlo (MC) simulation scheme derives the remaining useful life and probability distribution function. Validation on real MOSFET degradation data and performance comparisons against multiple advanced methods demonstrate the efficacy and superiority of this novel prognostic framework. This research meaningfully contributes to more accurate reliability evaluation and improved maintenance planning for MOSFET devices.