In smart cities and factories, robotic applications require high accuracy and security, which depends on precise inverse dynamics modeling. However, the physical modeling methods cannot include the nondeterministic factors of the manipulator, such as flexibility, joint clearance, and friction. In this paper, the Semiparametric Deep Learning (SDL) method is proposed to model robot inverse dynamics. SDL is a type of deep learning framework, designed for optimal inference, combining the Rigid Body Dynamics (RBD) model and Nonparametric Deep Learning (NDL) model. The SDL model takes advantage of the global characteristics of classic RBD and the powerful fitting capabilities of the deep learning approach. Moreover, the parametric and nonparametric parts of the SDL model can be optimized at the same time instead of being optimized separately. The proposed method is validated using experiments, performed on a UR5 robotic platform. The results show that the performance of SDL model is better than that of RBD model and NDL model. SDL can always provide relatively accurate joint torque prediction, even when the RBD or NDL model is not accurate.

This paper proposes a shore-based constant tension mooring system, which improves the cable tension distribution by adjusting the length of the cable to maintain the constant tension of the cable between the ship and the mooring pile in order to solve the problem of poor safety and reliability of the traditional mooring system in the mooring process. First, based on the three-dimensional potential flow theory, this paper uses the hydrodynamic software AQWA to numerically simulate the dynamic response of the traditional mooring system under the coupling of wind, wave, and current in different sea states. Subsequently, a shore-based constant tension mooring system using the principle of volume-varying hydraulic control was studied. On the basis of a comprehensive analysis of the working principle of the constant tension hydraulic control mooring system, a mathematical model of the main working circuit is established. The system was numerically simulated by relying on matlab/Simulink simulation software. Finally, by comparing with traditional mooring systems, the results show that the maximum cable tension of the shore-based constant tension mooring system is significantly reduced so that the tension is controlled within a fixed range, and the safety factor of the mooring cable is significantly improved, thus reducing the risk of mooring system failure and improving the ship's survivability.

In this paper, a new solution is proposed for the problem of mooring safety of large ships in complex sea conditions. Firstly, a dual-mode mooring system is designed to adaptively switch between active control and passive energy storage, adjusting the mooring strategy based on real-time sea conditions. Second, a collaborative analysis platform based on AQWA-Python-MATLAB/Simulink was researched and developed. Thirdly, based on the above simulation platform, the performance of the mooring system and the effects of different configurations on the stability of ship motion and dynamic tension of the cable are emphasized. Finally, by comparing the different mooring positions under various sea conditions with the traditional mooring system, the results show that the constant tension mooring system significantly improves the stability and safety of the ship under both conventional and extreme sea conditions, effectively reducing the fluctuation of cable tension. Through the optimization analysis, it is determined that the configuration of bow and stern cables is the optimal solution, which ensures safety while also improving economic benefits.