Electrical power system (EPS) of more electric aircraft (MEA) is a complex multi-state system, of which three issues of multi-state modeling, state transition uncertainty, and computational complexity pose challenges to its reliability modeling and analysis. This paper proposes a multi-state reliability modeling and analysis method for MEA EPS considering state transition uncertainty based on Markov process, fuzzy theory, and universal generating function (UGF). First, an equivalent structural model is established according to system architecture. For each component, a fuzzy state transition model is built based on triangular fuzzy numbers and Markov process. Then, the UGF method is integrated to express and infer the state probability and performance level distribution of system paths and branches, based on which three multi-state reliability indexes are calculated, respectively reliability, average performance, and performance shortfall. The propagation of component state transition uncertainty results in system reliability uncertainty. Their uncertain degree is quantified by a fuzzy entropy-based index. Finally, a case of MEA EPS is studied, and the comparative results show the effectiveness and superiority of the proposed method, supporting the reliability design and maintenance of MEA EPS.

Intelligent diagnosis based on deep learning can reveal the health status of running equipment and is attracting attention for an increasing number of industrial systems. However, two challenges, namely, the construction of deep models and the accommodation of different data distributions, restrict the effective application of such methods. To bridge these gaps, this article proposes an intelligent diagnostic method based on 2-D-gcForest andl2,p-PCA. First, a 2-D sampling strategy is employed before a gcForest model to transform the raw 1-D sequence data into 2-D stacked data, thus reducing the amount of redundant information and the computational burden. Then, gcForest is used as a basic diagnostic model, which learns data features with simple hyperparameter settings by automatically extending layers. Simultaneously,l2,p-PCA is incorporated to optimize the transformed features, improving the feature representation for different data sources. Finally, comparative experiments are reported to validate the effectiveness and superiority of the proposed method.

In recent years, hierarchical features extracted from convolutional neural network (CNN) for robust visual tracking have been developed by several methods. As features from different layers characterize different information of target and are set fixed weighted parameters, the performance of traditional visual tracking methods based on CNN can be further improved. In this letter, we propose a novel online visual tracking method by using hierarchical convolutional features with semiadaptive weights. The responses from different layers are assessed by a novel loss function. It considers the log likelihood and the entropy term of each response. The layer with the lower loss value is set to a higher weight parameter and the layer with the higher loss value is set to a lower one. We further develop a target appearance pyramid to deal with the scale change and an online classifier to redetect targets in case of tracking failures. Extensive experiments on challenging videos demonstrate that our method can achieve better tracking results in terms of lower center location error and higher overlap rate.