Papers by Keyword: Adaptive Control

Abstract: This study investigates the deployment of adaptive neural network-based control strategies for nonlinear dynamic systems, emphasizing the integration of Echo State Networks (ESNs) into a feedforward-feedback control architecture. Traditional controllers relying on precise mathematical modeling often fail to cope with the complexity of systems exhibiting high nonlinearity, time-varying parameters, and external disturbances. The proposed ESN-based approach harnesses reservoir computing to construct a lightweight, data-driven model capable of accurately capturing system dynamics in real time. The feedforward module provides anticipatory control actions, while the feedback loop compensates for deviations, enabling rapid convergence and robustness against parametric drift. Comparative analysis with conventional PID and LQR controllers reveals superior performance in terms of tracking accuracy, stability, and noise resilience. Preliminary simulations predict reduced steady-state error and improved dynamic response even under uncertain operating conditions. This architecture presents a scalable and efficient alternative for advanced applications in robotics, aerospace, and industrial process control. The findings affirm the viability of ESNs in redefining adaptive control paradigms by combining interpretability, computational efficiency, and real-world adaptability. Reference to this paper should be made as follows:MCE 2025, MCE825. (2025) ‘Adaptive neural network-based feedforward-feedback controller for nonlinear dynamic systems.

Abstract: The adaptive control of metal cutting processes is a logical extension of the CNC systems. In CNC systems of metal-cutting processes the machining variables (e.g., the cutting speed and feedrate) are prescribed by the part programmer. The determination of these variables depends on experience and knowledge regarding the workpiece and tool materials, coolant conditions, and other factors.The determination of these operating parameters depends on experience and knowledgeregarding the workpiece and tool materials, coolant conditions, and other factors. By contrast,the main idea in adaptive control is the improvement of the production rate, or the reductionof machining costs, by calculation and setting of the optimal operating parameters duringmachining itself. This calculation is based upon measurements of process variables in real time and is followed by a subsequent on-line adjustment of the machining variables subject to constraints with the objective to optimize the performance of the overall system.The adaptive control is basically a feedback system, in which the operatingparameters automatically adapt themselves to actual condition of the process. AC system formachine tools can be classified into two categories:1.Adaptive control with optimization(ACO);2.Adaptive control with constraints(ACC);ACO refers to systems in which a given performance index (usually an economicfunction) is extremized subject to process and system constraints. With ACC, the machiningparameters are maximized within a prescribed region bounded by process and systemconstraints, such as maximum torque or power. ACC systems, however, do not use aperformance index. In both systems an adaptation strategy is used to vary the operatingparameters in real time cutting progresses. Although there has been considerable research onthe development of ACO systems, few, if any, of these systems are used in practice. The major problems with such systems have been difficulties in defining realistic indexes of performance and the lack of suitable sensors which can reliably measure on-line thenecessary parameters in a production environment. The objective of most AC systems isimprovement in productivity, which is achieved by increasing the metal removal rate (MRR)during rough cutting operations. The increases in productivity range from approximately 20 to 80 percent and clearly depend on the material being machined and the complexity of the part tobe produced.

Abstract: We proposed a performance-improved finite-time adaptive synchronizing controllers and parameter update laws for coupling the dynamics of identical 4D hyperchaotic flows. The four-dimensional hyperchaotic flows consists of 12 terms and 11 system parameters and possessed very rich dynamics and larger parameter space. The performance of the proposed finite-time adaptive synchronizing controller was enhanced by the introduction of scalar quantities known as global controller strength coefficients and parameter update strength coefficients respectively, into the algebraically-derived control and parameter update structures, in order to constrained overshoots of the trajectories of the coupled systems and accelerate their rate of uniform convergence in finite time. Numerical simulation results obtained confirmed that the uniform asymptotic convergence rate of the coupling trajectories was faster, while the parameter update laws give a stable identification of the unknown system parameters in a global synchronizing time. A comparative analysis of the convergence time of the proposed adaptive controllers with recently published works indicated that the proposed controller has faster rates of uniform convergence of system trajectories.

Abstract: A schematic structure of the adaptive control system is presented, the application of which will ensure the consistency of the quality of the surface layer of surfaces obtained by turning non-rigid parts. Refined mathematical models which describe patterns forming the radial component of the cutting forces and roughness of finish turning of steel 18NiCrMo5 are developed, thus forming the basis of a control algorithm of the presented adaptive control system.

Abstract: Grinding performance can be influenced by various grinding conditions including workpiece materials properties, grinding wheel properties, grinding operational parameters and dressing operational parameters. In order to achieve stable optimal grinding performance, it is important to select the most suitable operational control parameters to match grinding requirement and to minimize the effects of grinding wheel wear and other changes in the process environment. The paper presents a simple adaptive control logic strategy for the selection of dressing and grinding conditions based on available sensing techniques. In this study, desirable grinding behaviour is discussed to demonstrate how to extract useful process information to guide process parameter adjustment for a stable satisfactory grinding performance.

Abstract: The production of irregularly shaped deep drawing parts with high quality requirements, which are common in today’s automotive body shell production, consistently challenge production processes. This challenge results from the high design requirements and automotive lightweight design, and hence the necessary use of high strength steels. Metal forming technology deals with these challenges using highly sophisticated methods to control the material flow. Several control loop methods have existed already in order to control the material flow in deep drawing processes, but only methods with a control intervention between two strokes. However, this kind of control method merely allows control intervention on measurements on the previous part or on measurements of material properties before the actual process. The method developed at the Institute for Metal Forming Technology in Stuttgart makes a control intervention possible during the deep drawing stroke. The used reference variable is the part wall stress and the control variable is the blankholder force, which is manipulated by using the segment elastic blankholder as an actuator. In this paper the experimental setup, the control methods, and the control loop itself will be presented. Furthermore, the developments of the new method will be described.

Abstract: Presses with mechanical linkages based on levers between motor and ram (path-linked presses) tend to oscillate due to inertial forces as a consequence of the drive parts motion.In this publication a new approach for a mass-balancing system is presented. This system allows to generate the optimal compensation forces needed to counteract the inertial forces by means of four linear motors. The control signals for the linear motors are specified by an evolutionary optimization algorithm, which operates on the base of measured accelerations of the press frame. The control signals of the linear motors are created in a way that the machines oscillations are reduced to a minimum. This way the presented mass-balancing system adapts itself automatically to varying conditions during the operation of the machine, such as a tool change or a varying stroke rate.In particular, the present publication provides the results of the conceptual design and the virtual testing of this approach, which has been mainly carried out with the help of multiple-body simulations.

Abstract: In this paper, an unmanned aerial vehicle (UAV) with fixed-wing in normal condition flight, and fixed height, is considered and along with this process, kinematics model of UAV, assumed to have parametric uncertainty. In this situation the target of designing of proper controller family, based on switching logic, is to control the speed and roll angle of fixed-wing unmanned aerial vehicle in order to track desired path with minimum error. The desired path will be generated by trajectory maker block. The results of simulation on a fixed-wing UAV are presented to show the efficiency of the method.

Abstract: The sliding mode based differential flatness control is used to stabilize the error dynamics in view of unmodeled dynamics employing position, velocity and acceleration as reference values but feeding back to system only the position and velocity measurements. This controller is able to plan trajectories of control gains within the proposed scheme of the controller. By above this paper describes a sliding mode based differential flatness control to a leg-wheel hybrid robot, in order to design a robotic prototype with the ability to move an uneven ground. To prove the controller working a simulation in Matlab-Simulink using Simmechanics is made. The result of this work shows a controller that is able to follow the reference trajectories without overshoots and small chattering.

Abstract: In this paper, a new integral sliding mode control scheme is designed for the 3-pole active magnetic bearing system. First, a new integral sliding surface is designed such that the 3-pole active magnetic bearing system in the sliding mode is asymptotically stable under certain conditions. Then, an adaptive controller is designed to solve the unknown upper bound of matched uncertainty and guarantee the reachability of the integral sliding surface. Finally, the performance of the proposed integral sliding mode controller is applied to 3-pole active magnetic bearing system to demonstrate the efficacy of the proposed method.