The compositive passive control (CPC) method of “interlayer seismic isolation “plus “shock absorption between adjacent towers” was applied to a multi-tower building (MTB) with a large podium. The interaction between adjacent towers was used to reduce the structural response under seismic action. Based on the Clough–Penzien spectral seismic model, the extended state equation of random response of MTB was derived with the minimum total energy of structural vibration as the optimization control objective. By comparing the seismic scheme and interlayer seismic isolation scheme, the relationship between the control parameters of the connecting control device and the random response of the structure was discussed and analyzed, and the control effect of the composite passive control system under different control schemes was also studied from the perspective of seismic response time history and vibration cumulative energy time history. Through numerical analysis, it was proved that the damping coefficient of the Kelvin-Voigt model has a great influence on the mean square error of total vibration energy while the stiffness coefficient has a poor sensitivity to it. Under the optimization control objective, the connection control device was better arranged at the top of the structure. The control effect can reach 84.64% under the condition of random ground motion as input. The CPC method maintains the advantages of the interlayer seismic isolation scheme and reduces the defect of the response amplification caused by the interlayer isolation, which provides a reference for the follow-up study of the CPC method of MTB.
The ship appearance inspection and classification technology can ensure a reduction in maritime accidents and monitor the marine environment, with widespread applications in both civilian and military domains. Technology for intelligent ships has been pushed forward thanks to advancements in deep learning and AI. Consequently, this work investigates deep learning-based algorithms for ship appearance recognition and categorization. In this work, we present a ship recognition system that builds on top of YOLOv5 with several improvements to make it more accurate. Because much of the background in ship photographs is water and sky, the primary network of the algorithm is enhanced with an attention mechanism. This allows for better extraction of ship features, focusing more on these useful features and suppressing other irrelevant ones. Improvements are made to the YOLOv5 network structure, including modifications to its neck structure and enhancements to feature extraction from the backbone to the neck. Additionally, a new fusion module is used in the neck to assign different weights to different feature layers for fusion, achieving better integration of the feature extraction network and enhancing the model's feature extraction and fusion capabilities.