Abstract—Mechanical vibrations have a big effect on how reliable, accurate, and long-lasting mechanical, robotic, and mechatronic devices. Conventional strategies to control vibrations work well in certain situations, but they are frequently unable to keep working when there are nonlinearities, unknowns, and changing dynamics over time. Artificially intelligent-based control techniques emerged as effective remedies to these issues, facilitating adaptive, information-driven and capable of learning vibration prevention. An extensive simulation-based study of artificial intelligence methods for actively mechanically control of vibration is demonstrated in this article. Neural network training is incorporated into intelligent vibration control frameworks using a focused on control systems paradigm. Lyapunov concept is used to give a mathematical evaluation of stability for machine learning control systems. When compared to traditional Proportional-Integral-Derivative (PID) and Linear-Quadratic Regulation (LQR) control algorithms, computer simulations on an elastic mechanical framework show enhanced vibration reduction. The proposed control method achieves a peak vibration reduction of approximately 45% compared to PID and 30% compared to conventional LQR under identical operating conditions. Settling time is reduced by 15–20% relative to PID control, and 10% relative to LQR. RMS vibration amplitude is decreased from 7 mm (PID) and 5 mm (LQR) to 3 mm with the proposed approach. Prospective study guidance, implementation obstacles, and practical implications are highlighted. The findings demonstrate that artificial intelligence-based vibration control is a reliable and expandable solution for the robotics and mechanical devices.

Keywords—Proportional-Integral-Derivative (PID), Linear- Quadratic Regulation (LQR), neural networking, artificially intelligent systems, effective vibration control, and mechanical platforms

Cite: Thamir Hassan Atyia, "Artificial Intelligence in Controlling Mechanical Vibrations: An Active Control Systems Perspective," International Journal of Mechanical Engineering and Robotics Research, Vol. 15, No. 3, pp. 281-289, 2026. doi: 10.18178/ijmerr.15.3.281-289

Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).