Enhanced Control of Nonlinear Systems with Neural Networks
Author Information
Author(s): Yang Guangyi, Bekiros Stelios, Yao Qijia, Mou Jun, Aly Ayman A., Sayed Osama R.
Primary Institution: Taif University, Saudi Arabia
Hypothesis
Can a neural network-based fuzzy sliding mode control approach effectively manage nonlinear systems under control input constraints and faults?
Conclusion
The proposed control method successfully synchronizes chaotic systems even in the presence of faults and control input limitations.
Supporting Evidence
- The proposed controller integrates neural networks and fuzzy logic to enhance fault tolerance.
- The method guarantees finite-time convergence, ensuring rapid stabilization.
- Simulation results validate the controller's effectiveness in synchronizing chaotic systems.
Takeaway
This study shows how using smart computer programs can help control complicated systems, even when things go wrong.
Methodology
The study employs a neural network-based fuzzy integral sliding mode control strategy to manage nonlinear systems facing faults and input constraints.
Limitations
The study does not address the potential effects of external disturbances on the control performance.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website