Integrated bees algorithm and artificial neural network to propose an efficient controller for active front steering control of vehicles

Abstract

In this paper, a new optimal adaptive controller for the active front steering control of a vehicle is proposed. Due to the availability and applicability of proportional-integrator-derivative (PID) controllers, this controller is picked up; but, to overcome its limitations, two optimization and adaptation schemes are employed. The reference transfer function between the yaw rate of a typical vehicle and its steering angle is derived. The actual dynamics is simulated using CarSim toolbox of MATLAB. Best vehicle handling was aimed to be reached for three famous driving manoeuvres by proposing an efficient but economic controller. An optimization is done on the PID coefficients for a specific road condition using the honey bees' algorithm, and then a two-layer artificial neural network is trained using the back propagation learning rule to adjust the controller coefficients for any arbitrary road conditions. The uncontrolled, desired, optimized controlled, and optimized plus trained controlled yaw rate of vehicles are drawn for three manoeuvers and three road conditions. The integral of squared error between the desired and actual trajectories for different manoeuvers and road conditions are evaluated and compared between each other. The performance of the proposed PID controller that was optimized by Bees Algorithm and trained by a neural network was proved. It is noted that the optimized PID controller is good for all road conditions but not excellent. The more we move away from the reference road (in which, the optimization is done), the error will be larger. Thus for other conditions, using the artificial neural network can help decrease the error significantly.

Fuzzy Versus Neuro-fuzzy Identification of Active Front Steering of a Vehicle on Slippery Roads

“…Here, a fuzzy logic system which takes advantage of the neural network to adapt its parameter according to unpredictable changes is employed (see following sections for more details). In this study, the backpropagation of error [11,12], as a training algorithm, is selected. More specifically, the input and output data of the system under study are collected for three well-known manoeuvres i.e.…”

“…After that, the network is expected to find the appropriate response for a new input relative to its information background; exactly as it does in the process of experiential learning. The efficiency and accuracy of neural networks has been discussed in several studies in the literature (see for example [11,12]). Usually, the mechanism for finding the best answer is performed by minimising a cost function that correlates the identified model response and the actual system.…”

“…Zhang and Wang [10] proposed a controller-gain tuning approach integrating active front steering system and direct yaw moment to enhance vehicle handling under velocity change uncertainties while the road coefficient of friction was not considered as a source of uncertainty. Aalizadeh and Asnafi [11,12] studied the stability and handling of a specific vehicle in uncertain road condition using a combination of artificial neural networks and bio-inspired optimisation algorithms. Aalizadeh [13] investigated the effects of uncertain road conditions on vehicle handling and proposed a neuro-fuzzy controller to enhance system performance.…”

A performance investigation on IoT enabled intra-vehicular wireless sensor networks

“…Different types of sensors are installed (e. g. temperature sensor, speed sensor, defect sensor, water sensor, heat sensor, tire-pressure monitoring sensor, parking sensor, knock sensor, etc.) inside a vehicle to collect the current status of the critical components of a vehicle [33][34][35][36]. The sensors sense the information of a component and the transmitter, which is integrated with the sensor, transmits the information to the CU.…”

A computational approach for optimizing vehicles’ interior noise and vibration

“…In another study, Nopiah et al [30] assessed the vehicle's interior sound quality (noise and vibration) using hybrid classification and clustering techniques including neural networks, hierarchical clustering and Linear Discriminant Analysis (LDA). Other studies have investigated the vertical Whole-Body Vibration (WBV), and steering and engine performances such as in [8,31,32]. Based on the above discussion and literature, it must be pointed out that sound quality differs in different automotive vehicles and thus, the existing models do not provide reliable solutions to the noise and vibration phenomena.…”