In this paper, a robust adaptive sliding mode (ASM) controller for improving vehicle maneuverability and lateral stability of steer-by-wire (SBW) vehicles. The proposed stability control algorithm is composed of the following three remarkable characteristics: 1) As the vehicle sideslip angle which is very useful in vehicle stability control is often unavailable or unmeasurable for practical applications, a sliding mode-based state observer is proposed to online estimate the actual sideslip angle via the yaw rate and the lateral acceleration measurements. 2) ASM lateral stability controller, as an upper level controller, is designed to calculate the corrected steering angle for driving both the yaw rate and the sideslip angle to achieve their desired values in the presence of modelling uncertainties and external disturbances. Moreover, an adaptive law is incorporated in the control law to estimate the switching gain such that the complex uncertainty bound information can be avoided. 3) The desired steering angle is realized by a lower steering controller via ASM for an SBW system. The hardware-in-the-loop simulation results demonstrate the excellent stability control performance of the proposed control for different steering maneuvers.

In this article, a novel active front steering (AFS) control strategy including the upper controller and the lower controller is proposed to improve the yaw stability and maneuverability for steer-by-wire (SbW) vehicles. The adaptive recursive integral terminal sliding mode (ARITSM) control is adopted in the upper controller for guaranteeing the convergence performance of both the actual sideslip angle and the yaw rate with strong robustness and fast convergence rate. Then, a fast nonsingular terminal sliding mode (FNTSM) control with extreme learning machine (ELM) estimator to estimate its equivalent control is designed in the lower controller to track the desired front wheel steering angle calculated from the upper controller for driving the sideslip angle and the yaw rate to converge ideal value. It is shown that the upper controller takes two controlled variables (vehicle sideslip angle and yaw rate) and only one control input (front steering angle) into consideration, which can obtain a better performance compared with the case of using only one of these values. Since using the ELM technique in the lower controller to estimate the equivalent control of the FNTSM, not only the dependence of SbW system dynamics can be alleviated in the process of designing controller but also the excellent steering control performance can be achieved. Comparative simulations are carried out by utilizing Carsim and Matlab software to validate the excellent performance of the proposed control strategy for different steering maneuvers.

For the purpose of simplifying the physical structure, improving the anti-disturbance performance and enhancing the response performance of permanent magnet synchronous motor (PMSM), this article proposes a novel sensorless fixed-time sliding mode control scheme with fast fixed-time convergence for PMSM. First, to realize sensorless control, a barrier function (BF)-based adaptive super-twisting observer (BF-ASTO) is designed to accurately estimate the rotor's position and speed of the PMSM. The BF is chosen as an adaptive algorithm for online tuning the parameters of BF-ASTO to achieve a better speed estimation performance. Then, an adaptive fixed-time integral sliding mode controller (AFTISMC) is proposed based on fixed-time stability theory, which guarantees both the independence of the settling time on the initial conditions and the finite time speed tracking error convergence. Lyapunov stability analysis is rigorously given for both the designed BF-ASTO and the AFTISMC, respectively. Finally, real-time experimental results are provided to verify the effectiveness of the proposed control method with the BF-ASTO.

A continuous adaptive fast terminal sliding mode based speed regulation control is proposed for a permanent magnet synchronous motor (PMSM) drive, where an improved super-twisting algorithm with linear terms (STLT) is constructed in the super-twisting speed observer. First, the STLT observer introduces a first-order term on the basis of conventional super-twisting sliding mode observer to improve the speed estimation convergence rate and to reduce the estimation error. Second, an adaptive function is added to the reaching law for the continuous fast terminal sliding mode speed controller to produce a faster response speed and stronger control robustness. In addition, the total disturbance of the system is estimated via Luenberger disturbance observer, which contributes to the feedforward compensation control component. The closed-loop stability analysis is rigorously given by the Lyapunov stability theory. Finally, real-time experiments on a PMSM platform are carried out to show the effectiveness and superior performance of the proposed control approach.

Fatigue driving (FD) is one of the main causes of traffic accidents. Traditionally, machine learning technologies such as back propagation neural network (BPNN) and support vector machine (SVM) are popularly used for fatigue driving detection. However, the BPNN exhibits slow convergence speed and many adjustable parameters, while it is difficult to train large-scale samples in the SVM. In this paper, we develop extreme learning machine (ELM)-based FD detection method to avoid the above disadvantages. Further, since the randomness of the weight and biases between the input layer and the hidden layer of the ELM will influence its generalization performance, we further apply a differential evolution ELM (DE-ELM) method to the analysis of the driver’s respiration and heartbeat signals, which can effectively judge the driver fatigue state. Moreover, not only will the Doppler radar and smart bracelet be used to obtain the driver respiration and heartbeat signals, but also the sample database required for the experiment will be established through extensive signal collections. Experimental results show that the DE-ELM has a better performance on driver’s fatigue level detection than the traditional ELM and SVM.