No abstract

No abstract

To tackle the active control problem of the heavy platform-struts structure, this paper designs a kind of hydraulic servo actuator that can withstand large static load and generate high-precision, small-amplitude dynamic forces as well, and develops a multi-channel cross-coupling suppression control algorithm that can consider the strong coupling effect in structure. Subsequently, combining the designed actuators with the control algorithm, this paper puts forward an active heavy platform-struts structure vibration control method. By embedding the designed actuators into the support struts, a platform-struts structure experimental system is constructed to assess the vibration suppression effect of the proposed method. Excited by the amplitude-varying disturbing force, four different kinds of experiments are conducted. The experimental results show that the distributed multi-channel adaptive active control method without considering the coupling effect will lead to the instability, and the vibration attenuation of the proposed method in this paper exceeds 90%. The proposed method therefore has an important potential in addressing the problem of vibration suppression in the practical engineering. In addition, it has strong convergence and robustness.

Ancient character recognition is not only important for the study and understanding of ancient history but also has a profound impact on the inheritance and development of national culture. In order to reduce the study of difficult professional knowledge of ancient characters, and meanwhile overcome the lack of data, class imbalance, diversification of glyphs, and open set recognition problems in ancient characters, we propose a Siamese similarity network based on a similarity learning method to directly learn input similarity and then apply the trained model to establish one shot classification task for recognition. Multi-scale fusion backbone structure and embedded structure are proposed in the network to improve the model's ability to extract features. We also propose the soft similarity contrast loss function for the first time, which ensures the optimization of similar images with higher similarity and different classes of images with greater differences while reducing the over-optimization of back-propagation leading to model overfitting. Specially, we propose a cumulative class prototype based on our network to solve the deviation problem of the mean class prototype and obtain a good class representation. Since new ancient characters can still be found in reality, our model has the ability to reject unknown categories while identifying new ones. A large number of experiments show that our proposed method has achieved high-efficiency discriminative performance and obtained the best performance over the methods of traditional deep learning and other classic one-shot learning.

No abstract