Damping Magnetorheological Systems Based on Optimal Neural Networks Preview Control Integrated with New Hybrid Fuzzy Controller to Improve Ride Comfort

Abstract

Adaptive neural networks (ANNs) have become famous for modeling and controlling dynamic systems. However, because of their failure to precisely reflect the intricate dynamics of the system, these have limited use in practical applications and perform poorly during training and testing. This research explores novel approaches to this issue, including modifying the simple neuron unit and developing a generalized neuron (GN). The revised version of the neuron unit helps to develop the system controller, which is responsible for providing the desired control signal based on the inputs received from the dynamic responses of the vehicle suspension system. The controller is then tested and evaluated based on the performance of the magnetorheological (MR) damper for the main suspension system. These results of the tests show that the optimal preview controller designed using the GN both ∑-Π-ANN and Π-∑-ANN can accurately capture the complex dynamics of the MR damper and improve their damping characteristics compared with other methods. The seat and main suspension systems work together to provide more support and comfort for the driver and passengers. The short stroke of the MR damper is used in seat suspension as it allows for more precise control over the suspension and can provide a smoother ride. The new hybrid fuzzy type-2 (T-2) control is designed to accurately estimate the desired damping force for the seat MR damper. This system also allows for the damping force to be adjusted to meet the desired requirements of the seat MR damper. This integration of damping systems allows better control and stability of the vehicle and provides a smoother ride for drivers and passengers. Furthermore, integrating the damping systems increases the overall performance of the vehicle, making it better able to handle various road conditions.