Researchers Soha Ilbeigi, Ashkan Bagherzadeh, and Alireza Sharifi have introduced a groundbreaking approach to controlling Vortex-Induced Vibrations (VIVs) in cylindrical structures, a persistent challenge in marine engineering and beyond. Their study, published in the journal “Applied Ocean Research,” presents a novel model-based active control strategy integrated with a Neural Network (NN), offering a robust solution to mitigate VIVs even in the presence of uncertainty.
The proposed method leverages a closed-loop control system, where real-time feedback from the system’s dynamic state is used to generate adaptive control commands. This adaptability allows the system to respond effectively to changing flow conditions and nonlinearities, a common issue in marine risers, tall buildings, and renewable energy systems. The researchers conducted a controllability analysis to assess the efficiency of their control strategy in suppressing VIVs.
Two control approaches were implemented: simple learning and composite learning. Both strategies demonstrated significant enhancements in vibration suppression, achieving up to 99% reduction in vibrations despite uncertainties in the system. The results underscore the potential of the proposed method to improve the efficiency, stability, and lifespan of structures subject to VIVs.
The integration of a Neural Network into the control strategy is a key innovation. The NN’s ability to learn and adapt from data enables the system to handle complex, nonlinear dynamics that are typical in real-world applications. This adaptability is crucial for marine risers, which are subjected to varying ocean currents and environmental conditions.
The practical implications of this research are substantial. By effectively suppressing VIVs, the proposed method can enhance the durability and safety of marine structures, reduce maintenance costs, and extend the operational life of offshore installations. Moreover, the approach can be applied to other fields, such as tall buildings and renewable energy systems, where VIVs pose significant challenges.
The researchers’ work represents a significant advancement in the field of structural control and vibration mitigation. By combining model-based control with the adaptive capabilities of Neural Networks, they have developed a versatile and effective solution for managing VIVs. This innovative approach not only addresses current engineering challenges but also paves the way for future advancements in structural design and control. Read the original research paper here.