This article presents a new cascaded extended state observer (CESO)-based sliding-mode control (SMC) for an underactuated flexible joint robot (FJR). The control of the FJR has many challenges, including coupling, underactuation, nonlinearity, uncertainties and external disturbances, and the noise amplification especially in the high-order systems. The proposed control integrates the CESO and SMC, in which the CESO estimates the states and disturbances, and the SMC provides the system robustness to the uncertainty and disturbance estimation errors. First, a dynamic model of the FJR is derived and converted from an underactuated form to a canonical form via the Olfati transformation and a flatness approach, which reduces the complexity of th

As one type of heating furnaces, the electric heating furnace (EHF) typically suffers from time delay, non-linearity, time-varying parameters, system uncertainties, and harsh en-vironment of the furnace, which significantly deteriorate the temperature control process of the EHF system. In order to achieve accurate and robust temperature tracking performance, an integration of robust state feedback control (RSFC) and a novel sliding mode-based disturbance observer (SMDO) is proposed in this paper, where modeling errors and external disturbances are lumped as a lumped disturbance. To describe the characteristics of the EHF, by using convection laws, an integrated dynamic model is established and identified as an uncertain nonlinear second ord

An adaptive nonlinear neural controller to reduce the nonlinear flutter in 2-D wing is proposed in the paper. The nonlinearities in the system come from the quasi steady aerodynamic model and torsional spring in pitch direction. Time domain simulations are used to examine the dynamic aero elastic instabilities of the system (e.g. the onset of flutter and limit cycle oscillation, LCO). The structure of the controller consists of two models :the modified Elman neural network (MENN) and the feed forward multi-layer Perceptron (MLP). The MENN model is trained with off-line and on-line stages to guarantee that the outputs of the model accurately represent the plunge and pitch motion of the wing and this neural model acts as the identifier. Th

The flexible joint robot manipulators provide various benefits, but also present many control challenges such as nonlinearities, strong coupling, vibration, etc. This paper proposes optimal second order integral sliding mode control (OSOISMC) for a single link flexible joint manipulator to achieve robust and smooth performance. Firstly, the integral sliding mode control is designed, which consists of a linear quadratic regulator (LQR) as a nominal control, and switching control. This control guarantees the system robustness for the entire process. Then, a nonsingularterminal sliding surface is added to give a second order integral sliding mode control (SOISMC), which reduces chartering effect and gives the finite time convergence as well. S

The need for quick airborne transportation is critical, especially in emergencies. Drones with suspended payloads might be used to accomplish quick airborne transportation. Due to the environment or the drone's motion, the slung load may oscillate and lead the drone to fall. The altitude and attitude controls are the backbones of the drone's stability, and they must be adequately designed. Because of their symmetrical and simple structure, quadrotor helicopters are one of the most popular drone classes. In this work, a genetic algorithm with two weighted terms fitness function is used to adjust a Proportional-Integral-Derivative (PID) controller to compensate for the altitude and attitude controllers in a quadrotor drone

This paper presents a modified training method for Recurrent Neural Networks. This method depends on the Non linear Auto Regressive (NARX) model with Modified Wavelet Function as activation function (MSLOG) in the hidden layer. The modified model is known as Modified Recurrent Neural (MRN). It is used for identification Forward dynamics of four Degrees of Freedom (4-DOF) Selective Compliance Assembly Robot Arm (SCARA) manipulator robot. This model is also used in the design of Direct Inverse Control (DIC). This method is compared with Recurrent Neural Networks that used Sigmoid activation function (RS) in the hidden layer and Recurrent Neural Networks with Wavelet activation function (RW). Simulation results shows that the MRN model is bett

This paper presents L₁-adaptive controller for controlling uncertain parameters and time-varying unknown parameters to control the position of a DC servomotor. For the purpose of comparison, the effectiveness of L₁-adaptive controller for position control of studied servomotor has been examined and compared with another adaptive controller; Model Reference Adaptive Controller (MRAC). Robustness of both L₁-adaptive controller and model reference adaptive controller to different input reference signals and different structures of uncertainty were studied. Three different types of input signals are taken into account; ramp, step and sinusoidal. The L₁-adaptive controller ensured uniformly bounded

The aim of human lower limb rehabilitation robot is to regain the ability of motion and to strengthen the weak muscles. This paper proposes the design of a force-position control for a four Degree Of Freedom (4-DOF) lower limb wearable rehabilitation robot. This robot consists of a hip, knee and ankle joints to enable the patient for motion and turn in both directions. The joints are actuated by Pneumatic Muscles Actuators (PMAs). The PMAs have very great potential in medical applications because the similarity to biological muscles. Force-Position control incorporating a Takagi-Sugeno-Kang- three- Proportional-Derivative like Fuzzy Logic (TSK-3-PD) Controllers for position control and three-Proportional (3-P) controllers for force contr

Software Defined Networking (SDN) with centralized control provides a global view and achieves efficient network resources management. However, using centralized controllers has several limitations related to scalability and performance, especially with the exponential growth of 5G communication. This paper proposes a novel traffic scheduling algorithm to avoid congestion in the control plane. The Packet-In messages received from different 5G devices are classified into two classes: critical and non-critical 5G communication by adopting Dual-Spike Neural Networks (DSNN) classifier and implementing it on a Virtualized Network Function (VNF). Dual spikes identify each class to increase the reliability of the classification