Olurotimi Akintunde Dahunsi

Neural network based feedback linearization control of a servo-hydraulic vehicle suspension system

Neural network based feedback linearization control of a servo-hydraulic vehicle suspension system This paper presents the design of a neural network based feedback linearization (NNFBL) controller for a two degree-of-freedom (DOF), quarter-car, servo-hydraulic vehicle suspension system. The main objective of the direct adaptive NNFBL controller is to improve the systems ride comfort and handling quality. A feedforward, multi-layer perceptron (MLP) neural network (NN) model that is well suited for control by discrete input-output linearization (NNIOL) is developed using input-output data sets obtained from mathematical model simulation. The NN model is trained using the Levenberg-Marquardt optimization algorithm. The proposed controller is compared with a constant-gain PID controller (based on the Ziegler-Nichols tuning method) during suspension travel setpoint tracking in the presence of deterministic road disturbance. Simulation results demonstrate the superior performance of the proposed direct adaptive NNFBL controller over the generic PID controller in rejecting the deterministic road disturbance. This superior performance is achieved at a much lower control cost within the stipulated constraints.

Differential Evolution-Based PID Control of Nonlinear Full-Car Electrohydraulic Suspensions

This paper presents a differential-evolution- (DE-) optimized, independent multiloop proportional-integral-derivative (PID) controller design for full-car nonlinear, electrohydraulic suspension systems. The multiloop PID control stabilises the actuator via force feedback and also improves the system performance. Controller gains are computed using manual tuning and through DE optimization to minimise a performance index, which addresses suspension travel, road holding, vehicle handling, ride comfort, and power consumption constraints. Simulation results showed superior performance of the DE-optimized PID-controlled active vehicle suspension system (AVSS) over the manually tuned PID-controlled AVSS and the passive vehicle suspension system (PVSS).

PID control of a nonlinear half-car active suspension system via force feedback

This paper presents the design of a two-loop, force/suspension travel PID control system, for a four degree-of-freedom (DOF), nonlinear, half-car active vehicle suspension system (AVSS). The two-loop system consists of an inner PID hydraulic actuator force control loop and an outer PID suspension travel control loop. Performance of the PID based AVSS is compared to a passive, nonlinear, half-car suspension system with the same model parameters. The simulation results showed the superior performance of the AVSS in the presence of the deterministic road disturbance.

Neural network-based model predictive control of a servo-hydraulic vehicle suspension system

This paper presents the design of a multi-layer feedforward neural network-based model predictive controller (NNMPC) for a two degree-of-freedom (DOF), quarter-car servo-hydraulic vehicle suspension system. The nonlinear dynamics of the servo-hydraulic actuator is incorporated in the suspension model and thus a suspension travel controller is developed to indirectly improve the ride comfort and handling quality of the suspension system. A SISO feedforward multi-layer perceptron (MLP) neural network (NN) model is developed using input-output data sets obtained from the mathematical model simulation. Levenberg-Marquandt algorithm was employed in training the NN model. The NNMPC was used to predict the future responses that are optimized in a sub-loop of the plant for cost minimization. The proposed controller is compared with an optimally tuned constant-gain PID controller (based on Ziegler-Nichols tuning method) during suspension travel setpoint tracking in the presence of deterministic road input disturbance. Simulation results demonstrate the superior performance of the NNMPC over the generic PID - based in adapting to the deterministic road disturbance.

Intelligent feedback linearization control of nonlinear electrohydraulic suspension systems using particle swarm optimization

Graphical abstractDisplay Omitted HighlightsWe design an active vehicle suspension system controller using computational intelligence technique.We compare the performance of this controller with the performance of passive, PID and non-optimized intelligent controllers.Robustness to parameter variations analysis is carried out in this paper.The proposed controller improved the vehicle ride comfort, road holding and disturbance rejection properties. The core factors governing the performance of active vehicle suspension systems (AVSS) are the inherent trade-offs involving suspension travel, ride comfort, road holding and power consumption. In addition to this, robustness to parameter variations is an essential issue that affects the effectiveness of highly nonlinear electrohydraulic AVSS. Therefore, this paper proposes a nonlinear control approach using dynamic neural network (DNN)-based input-output feedback linearization (FBL) for a quarter-car AVSS. The gains of the proposed controllers and the weights of the DNNs are selected using particle swarm optimization (PSO) algorithm while addressing simultaneously the AVSS trade-offs. Robustness and effectiveness of the proposed controller were demonstrated through simulations.

Direct adaptive neural control of a quarter-car active suspension system

This paper presents the design and implementation of a direct adaptive neural network (DANN) based feedback linearization controller for a two degree of freedom (2DOF), quarter-car active vehicle suspension system (AVSS). The main objective is to improve ride comfort and handling quality. The constant gain PID controller (based on Ziegler-Nichols tuning method) is used to benchmark the DANN controller during a suspension travel sinusoidal set point tracking in the presence of deterministic road disturbance. The maximum sprung mass acceleration of the DANN controller was about 2.723ms−2, for the PID, it was 2.676ms−2. The tire deflection was approximately 5mm and 4mm for the DANN and the PID controllers. The performance of the DANN controller was achieved at a marginally higher cost of the control input.

Linear Slip Control Formulation for Vehicular Anti-Lock Braking System with Suspension Effects

Abstract This paper presents the formulation of a slip-control model for purposes of performing slip tracking of target slip. System modeling is performed to develop a braking model incorporating an active suspension. Linearisation of the highly non-linear multi-input multi-output developed Anti-lock Braking System model is performed by way of input-output feedback linearisation. Feedback linearisation is shown to provide a transformed linear ABS model while ensuring a verifiable stable state transformation. Lie algebra is used to find the stability of the internal dynamics through zero dynamics analysis. Simulation results demonstrate the validity of the approach along with the development of a stabilising condition for the linearisation approach.

Particle Swarm Optimized Intelligent Control of Nonlinear Full-Car Electrohydraulic Suspensions

Abstract This paper presents the design of an indirect adaptive feedback linearization (FBL)-based control using dynamic neural networks (DNN) for full-car nonlinear electrohydraulic suspensions. Particle swarm optimization (PSO) algorithm is used in training the DNN to learn the dynamics of the system. A multi-loop, PSO-optimized proportional-integral-derivative (PID) control is implemented for the feedback-linearized DNN model to improve system performance. The proposed control scheme outperformed the passive vehicle suspension system (PVSS) and the benchmark PSO-optimized PID controller.

CRS and PS-optimised PID controller for nonlinear, electrohydraulic suspension systems

The compromise between ride comfort, suspension travel, road holding, vehicle handling and power consumption determines the success of an active vehicle suspension system (AVSS). The simplicity of Proportional-Integral-Derivative (PID) controllers has made it the controller of choice for many mechatronic systems including AVSS. This investigation studies the effectiveness of optimal control policies such as Pattern Search (PS), and Controlled Random Search (CRS)-based PID controllers in dealing with the inherent trade-offs of AVSS. A nonlinear servo-hydraulic quarter-car AVSS is considered in this article. The success of these optimal PID controllers may provide a contemporary foundation in selecting optimal gains PID for a control system, which at the moment is a rather rigorous and time consuming process. The objective function is chosen such that each of the AVSS trade-offs are addressed. The PS routine improved significantly from the manually tuned and uncontrolled cases with an overall improvement in ride comfort, suspension travel, settling time and road holding. However, this was attained at the cost of greater power consumption and actuation force. The CRS routine showed a substantial improvement from the manually tuned case in terms of ride comfort and settling time, but exhibited weaker characteristics in terms of road holding and transient behaviour, which implies that its solution may have been caught in a local minimum.

Dynamic neural network-based feedback linearization control of full-car suspensions using PSO

Abstract This paper proposes a nonlinear control approach using dynamic neural network-based input–output feedback linearization to resolve the inherent conflicting performance criteria for a full-car nonlinear electrohydraulic active vehicle suspension system. Particle swarm optimization is applied both for the dynamic neural network models’ trainings and the computation of the controllers’ parameters. The intelligent control scheme outperformed the passive vehicle suspension system and the benchmark particle swarm-optimized proportional+integral+derivative controller. Effectiveness and robustness of the proposed controller are demonstrated through simulations both in time- and frequency-domains.