With the rapid growth of the aviation fields, the remaining useful life (RUL) estimation of aero-engine has become the focus of the industry. Due to the shortage of existing prediction methods, life prediction is stuck in a bottleneck. Aiming at the low efficiency of traditional estimation algorithms, a more efficient neural network is proposed by using Convolutional Neural Networks (CNN) to replace Long-Short Term Memory (LSTM). Firstly, multi-sensor degenerate information fusion coding is realized with the convolutional autoencoder (CAE). Then, the temporal convolutional network (TCN) is applied to achieve efficient prediction with the obtained degradation code. It does not depend on the iteration along time, but learning the causality through a mask. Moreover, the data processing is improved to further improve the application efficiency of the algorithm. ExtraTreesClassifier is applied to recognize when the failure first develops. This step can not only assist labelling, but also realize feature filtering combined with tree model interpretation. For multiple operation conditions, new features are clustered by K-means++ to encode historical condition information. Finally, an experiment is carried out to evaluate the effectiveness on the Commercial Modular Aero-Propulsion System Simulation (CMAPSS) datasets provided by the National Aeronautics and Space Administration (NASA). The results show that the proposed algorithm can ensure high-precision prediction and effectively improve the efficiency.

Stroke extraction of Chinese characters plays an important role in the field of character recognition and generation. The most existing character stroke extraction methods focus on image morphological features. These methods usually lead to errors of cross strokes extraction and stroke matching due to rarely using stroke semantics and prior information. In this paper, we propose a deep learning-based character stroke extraction method that takes semantic features and prior information of strokes into consideration. This method consists of three parts: image registration-based stroke registration that establishes the rough registration of the reference strokes and the target as prior information; image semantic segmentation-based stroke segmentation that preliminarily separates target strokes into seven categories; and high-precision extraction of single strokes. In the stroke registration, we propose a structure deformable image registration network to achieve structure-deformable transformation while maintaining the stable morphology of single strokes for character images with complex structures. In order to verify the effectiveness of the method, we construct two datasets respectively for calligraphy characters and regular handwriting characters. The experimental results show that our method strongly outperforms the baselines. Code is available at https://github.com/MengLi-l1/StrokeExtraction.

Stroke extraction of Chinese characters plays an important role in the field of character recognition and generation. The most existing character stroke extraction methods focus on image morphological features. These methods usually lead to errors of cross strokes extraction and stroke matching due to rarely using stroke semantics and prior information. In this paper, we propose a deep learning-based character stroke extraction method that takes semantic features and prior information of strokes into consideration. This method consists of three parts: image registration-based stroke registration that establishes the rough registration of the reference strokes and the target as prior information; image semantic segmentation-based stroke segmentation that preliminarily separates target strokes into seven categories; and high-precision extraction of single strokes. In the stroke registration, we propose a structure deformable image registration network to achieve structure-deformable transformation while maintaining the stable morphology of single strokes for character images with complex structures. In order to verify the effectiveness of the method, we construct two datasets respectively for calligraphy characters and regular handwriting characters. The experimental results show that our method strongly outperforms the baselines. Code is available at https://github.com/MengLi-l1/StrokeExtraction.