Semi-Active Suspension Design for Truck Using Pneumatic Spring Joining MR Fluid Damper Based on Neural Networks Controller

<div>In order to modify both stiffness and damping rates according to various road conditions, this research introduces a pneumatic spring in conjunction with a magnetorheological (MR) fluid damper as a single suspension unit for each wheel in the truck. Preventing weight transfer and improving riding comfort during braking, acceleration, and trajectory prediction are the main objectives. A two-axle truck has been used, consisting of three degrees of freedom for the sprung mass, including vertical, pitch, and roll motions, and four degrees of freedom for the unsprung masses, which have been redesigned according to the different types of springs and dampers. Pneumatic-controlled springs, often referred to as dynamic or classic models, replace laminated leaf springs commonly found in vehicles. Additionally, an MR damper replaces a hydraulic double-acting telescopic shock absorber. These models are studied to evaluate the effect of pneumatic spring parameters on truck dynamics. Pneumatic stiffness and the intended damping force are monitored by a recurrent neural network in conjunction with leveling control. This process provides the recommended voltage for the MR damper based on the Signum function damper controller. The performance of the suspension is assessed in the time and frequency domains for both step and random road excitations using vehicle dynamic parameters. Six suspension system configurations are compared with the air spring dynamic model integrated with the MR damper (Model 6), which is recommended as a suspension system for trucks. According to simulation data, when compared to alternative suspension systems, Model 6 significantly enhances both ride comfort and vehicle stability. Model 6 offers improvements in tire workload, truck path, tire–ground contact point during acceleration, braking efficiency, and stopping distance. Compared to previous controlled models, Model 6 also demonstrates zero steady-state offset and zero steady-state error.</div>