An investigation into the use of neural networks for the semi-active control of a magnetorheologically damped vehicle suspension

Abstract

Neural networks are highly useful for the modelling and control of magnetorheological (MR) dampers. A damper controller based on a recurrent neural network (RNN) of the inverse dynamics of an MR damper potentially offers significant advantages over conventional controllers in terms of reliability and cost through the minimal use of sensors. This paper introduces a neural-network-based MR damper controller for use in conjunction with the system controller of a semi-active vehicle suspension. A mathematical model of a semi-active quarter-vehicle suspension using an MR damper is derived. Control performance criteria are evaluated in the time and frequency domains in order to quantify the suspension effectiveness under bump and random road disturbance. Studies using the modified Bouc—Wen model for the MR damper as well as an actual damper fitted in a hardware-in-the-loop simulation (HILS) both showed that the inverse RNN damper controller potentially offers a significantly superior ride comfort and vehicle stability over a conventional MR damper controller based on continuous-state control. The neural network controller produces a smoother and lower input voltage to the MR damper coil, ensuring extended damper life and lower power requirement respectively. Further studies performed using an RNN model of the forward dynamics of the MR damper showed that it is a reliable substitute for HILS for validating multi-damper control applications.

Tyre–road grip coefficient assessment – Part II: online estimation using instrumented vehicle, extended Kalman filter, and neural network

“…Using simplified vehicle models, like quarter-car suspension models, [69,70] half-car suspension models, [71] or full-car suspension models, [72,73] the NN is used to control the suspension system in order to improve the handling, stability, or the ride comfort. In the active suspension systems, the spring and damper of the passive system is replaced or supplemented by active force actuators that are regulated using, for example, a control law based on an NN.…”

“…[69] The latest application of the NNs to these suspension systems is the control of the new magnetorheological dampers. [70,[72][73][74] In research papers, there are examples of the application of NNs to predict the kinematic and dynamic response of the suspension system [75] and to estimate the nonlinear model of a suspension [76] and a tyre-road force estimation. Matusko [77] added an RBF NN to the estimator to compensate for the effects of the friction model uncertainties, in order to improve the estimation quality.…”

Fuzzy Hybrid Control of Off-Road Vehicle Suspension Fitted With Magnetorheological Dampers

“…zero or maximum to alter the damper force in order to closely track the desired force produced by the system controller. The governing equation for input voltage and damping force can b follows [12,15]: active control devices that employ a MR damper cannot input energy into the mechanical system being The challenge of controlling these semiactive devices comes from the nonlinear dynamic behavior of such dampers. It is the command voltage applied to the current that is connected to the MR damper and that energizes the damping force, which can be .…”

Damping Force Control of A Semi-active Suspension System Using Cuckoo Search Optimized PID Method

“…In the existing literature, various control strategies are available for the SAS system such as skyhook control [2], proportional-integral-derivative (PID) control [3], ground-hook control [4], and sliding mode control [5]. In conclusion, the control schemes of SAS are classified into three types.…”