For periodic composite microplates, the microstructure dependent effect has great influence on the elastic wave vibration band gaps. In this paper, an effective isogeometric analysis method based on the modified couple stress theory (MCST) is proposed to calculate the vibration band gaps in periodic composite microplates. The MCST is employed to capture the microstructure effect of vibration band gaps in periodic composite microplates. The high order continuity requirement of MCST can be easily satisfied by applying the NURBS based isogeometric analysis approach. The elasto-dynamics and discrete equations of isogeometric analysis are obtained under the Mindlin kinematics assumptions. The present approach is validated by comparison with the analytical solution. And the influence of microstructure effect, volume fraction and unit cell length on the band gaps are investigated in details.

Stroke and its related complications such as hemiplegia and disability have placed a huge burden on human society in the 21st century, and different disability leads to personalized needs for rehabilitation and assistance in daily living. To addresses this issue, human-computer interaction (HMI) technology strives to detect and recognize the user's intention, to meet the user's needs through physical responses. In this work, the designed pressure film sensor array on the upper limb rehabilitation exoskeleton combined with our ST-GCN network is used to predict the patient's motion intention. Experimental results show that compared with the conventional method, the ST-GCN model meets the requirements in terms of accuracy, response time and model size, and the proposed method can be used as an optional scheme for the application of rehabilitation exoskeleton.

Aiming at resonance-state identification for hydraulic gates, firstly, finite element simulation was employed to analyze the vibration frequencies of the gate under various opening degrees. Subsequently, excitation experiments were conducted to compare the vibration frequencies of the gate at different opening degrees, obtaining the vibration state of the gate. Based on the finite element simulation and experimental data, a Generative Adversarial Network (GAN) data augmentation method was constructed to expand the dataset. The improved multi-scale convolutional neural network algorithm was utilized for training and recognition. Validated by real-world and historical dynamic data, the proposed model achieved an accuracy of 85.00% on the held-out test subset for identifying normal and resonance-induced abnormal vibration states, providing a data-driven basis for subsequent gate condition monitoring.