Dynamic modeling and control for dual-flexible servo system considering two-dimensional deformation based on neural network compensation

The two-inertia system with variable-length flexible load (TSVFL) is a typical dynamic model uncertain system. It is affected by transmission flexibility, flexible load length variation, and inaccurate friction torque, in which the flexible load will vibrate during rotation. In this study, a neural network compensation sliding mode control (SMC) strategy mixed with the angle-independent method (AIM) is proposed to suppress the vibration of the TSVFL. Among them, the AIM is proposed to design the fluctuating desired input of the motor. The vibration of the flexible load is offset by the speed fluctuation of the motor. The RBF neural networks are proposed to recognize the uncertain term in the TSVFL's dynamic model. First, the nonlinear mathematical model of the TSVFL is deduced based on the assumed mode method. Then, the Lyapunov stability theorem is proposed to design the weight coefficients’ adaptive law in neural networks and the robust term in the control law. Finally, simulation and physical experiments on output speed control are implemented. The results show that the proposed strategy is able to effectively decrease the error and weaken the vibration.

To address non-linear disturbances and uncertainties in complex marine environments, this paper proposes a disturbance-resistant controller for deep-sea cranes. The controller integrates hierarchical sliding mode control, adaptive control, and neural network compensation techniques. By designing a global sliding mode surface, the dynamic coordination between the driving and non-driving subsystems is achieved, ensuring overall system stability. The subsystem surfaces reduce oscillations and enhance tracking accuracy. Adaptive control dynamically adjusts system parameters, enhancing robustness against external uncertainties, while the neural network compensates for time-varying disturbances through real-time learning. The stability of the control scheme is verified on the basis of Lyapunov theory. The simulation results demonstrate that, compared to traditional PID control, the proposed controller exhibits significant advantages in trajectory tracking accuracy, response speed, and disturbance rejection.

This article presents a comparative study between the hybrid impedance control approach and the impedance force control approach with neural networks compensation of manipulator modeling errors. The proposed algorithm consists of an outer hybrid impedance control loop that generates the reference (target) acceleration to an inner inverse dynamics control loop. In order to improve the controller robustness, a compensation action of the manipulator modeling errors is introduced, acting on the target acceleration. This compensation action is based on a neural network model achieved by minimizing the modeling errors along the manipulator trajectory. The neural network algorithm uses an error training signal to model errors, that is minimized along the trajectory. The performance of the hybrid impedance control system with neural network compensation, is compared with the impedance force controller with neural network compensation, and is illustrated by computer simulations with a two degree-of-freedom PUMA 560 robot, whose end-effector is forced to move along a frictionless surface located perpendicular to the horizontal plane. The results obtained reveal even better performance when the desired force profile is not constant along the trajectory. This situation is very important in fine motion tasks where the desired force must have a varying profile along the trajectory, namely at the beginning and the end of the task. The results have also shown accurate force tracking and position control, even when significant uncertainties in the robot dynamic model are assumed.

In this study, based on the slope of power versus voltage, a novel MPPT algorithm using neural network compensator is proposed to avoid the oscillation problem and effect of uncertain parameters in photovoltaic (PV) systems. However, the characteristics of PV output voltage and output current are determined by the solar irradiation conditions, ambient temperature, and the load electrical characteristics, thereby the technologies of changing the location of the maximum power point must be developed in the applications of maximum-power-point-tracking (MPPT) control in order to make the PV arrays get the optimal efficiency from solar energy at different operating conditions. In this study, the uncertainties in PV systems are compensated by a neural network and the duty cycle of dc/dc converter is determined by a PI controller. The control objectives of this study is to achieve MPPT for the PV systems including solar cell arrays, a dc/dc converter, and an output load despite the variation of solar irradiation, ambient temperature, and the load electrical characteristics in PV systems. From experimental results, the validity of the proposed MPPT controller can be verified under a certain solar irradiation and a partially shaded condition, respectively.

Research of modern flight control methods for unmanned aerial vehicles (UAVs), which lower the cost and risk associated with the design of actual physical flight systems, has become research hotspot in recent years. However, design of control laws for UAV is complicated and challengeable due to UAV uncertainties, nonlinearity and coupling. This paper proposes a new hybrid controller design scheme, which consists of a backstepping controller and a neural network compensator. The backstepping controller realizes linearization and decoupling of the highly nonlinear and tightly coupled UAV model. For cancelling out uncertainties such as unmodeled dynamics and external disturbances, the neural network compensator is designed to enhance the robustness of flight system. Pseudoinverse method is applied to establish the mapping between moments and multiple control surfaces. Numerical simulation shows that the UAV equipped the hybrid controller has good maneuverability, strong self-learning ability of compensating the unmodeled dynamics and enough robust stability against constraints of actuators.

A digital signal processor (DSP)-based complementary sliding mode control (CSMC) with Sugeno type fuzzy neural network (SFNN) compensator is proposed in this study for the synchronous control of a dual linear motors servo system installed in a gantry position stage. The dual linear motors servo system comprises two parallel permanent magnet linear synchronous motors (PMLSMs). The dynamics of the single-axis motion system with a lumped uncertainty which contains parameter variations, external disturbances and nonlinear friction force is briefly introduced first. Then, a CSMC is designed to guarantee the precision position tracking requirement in single-axis control for the dual linear motors. Moreover, to enhance the robustness to uncertainties and to eliminate the synchronous error of dual linear motors, the CSMC with a SFNN compensator is proposed where the SFNN compensator is designed mainly to compensate the synchronous error. Finally, some experimental results are illustrated to show the validity of the proposed control approach.

Aiming at the attitude control problem of the gliding vehicle with uncertainty and strong coupling, a dynamic inversion control method based on RBF neural network compensated inversion error is discussed. Firstly, based on the double time scale separation hypothesis, the controlled aircraft model is divided into a fast and slow state subsystem. Then the dynamic inversion control laws are designed for each of the two subsystems. The weight update rule of the RBF neural network is derived online based on the Lyapunov stability principle to compensate for the inversion error caused by the modeling error and uncertainty. The simulation verifies the effectiveness of the control law. The robustness of the control system after neural network compensation is significantly improved.

Environment-independent continuous speech recognition is important for the successful development of speech recognizers in real world applications. Linear compensation methods do not work well if the mismatches between training; and testing environments are not linear. In this paper, a neural network compensation technique is explored to mitigate the distortion resulting from additive noise, distant-talking, or telephone channels. The advantage of the neural network compensation method is that retraining of a speech recognizer for each particular application is avoided. Furthermore, since neural networks are trained to transform distorted speech feature vectors to those corresponding to clean speech, it may outperform a retrained speech recognizer trained on distorted speech. Three experiments are conducted to evaluate the capability of the neural network compensation method; recognition of additive noisy speech, distant-talking speech, and telephone speech.

In this chapter an adaptive sliding mode controller for the Furuta pendulum is proposed. The Furuta pendulum is a class of underactuated mechanical systems commonly used in many control systems laboratories due to its complex stabilization which allows the analysis and design of different nonlinear and multivariable controllers that are useful in some fields such as aerospace and robotics. Sliding mode control has been extensively used in the control of mechanical systems as an alternative to other nonlinear control strategies such as backstepping, passivity based control etc. The design and implementation of an adaptive sliding mode controller for this kind of system is explained in this chapter, along with other sliding mode controller variations such as second order sliding mode (SOSMC) and PD plus sliding mode control (PD \(+\) SMC) in order to compare their performance under different system conditions. These control techniques are developed using the Lyapunov stability theorem and the variable structure design procedure to obtain asymptotically stable system trajectories. In this chapter the adaptive sliding mode consist of a sliding mode control law with an adaptive gain that makes the controller more flexible and reliable than other sliding mode control (SMC) algorithms and nonlinear control strategies. The adaptive sliding mode control (ASMC) of the Furuta pendulum, and the other SMC strategies shown in this chapter, are derived according to the Furuta’s pendulum dynamic equations making the sliding variables, position errors and velocity errors reach the zero value in a specified reaching time. The main reason of deriving two well known sliding mode control strategy apart from the proposed control strategy of this chapter (adaptive sliding mode control) is for comparison purposes and to evince the advantages and disadvantages of adaptive sliding mode control over other sliding mode control strategies for the stabilization of the Furuta pendulum. A chattering analysis of the three SMC variations is done, to examine the response of the system, and to test the performance of the ASMC in comparison with the other control strategies explained in this chapter.

In order to implement the speed control and improve the robustness of permanent magnet synchronous motor (PMSM) servo systems associated with the sliding-mode control (SMC), a compact integrated SMC controller designed for position servo systems is proposed in this paper. The merits of the SMC approach and PID control are combined to design this novel integrated controller. Some integral and feedforward compensatory strategies are also applied to eliminate chattering induced by traditional variable structure control. Both simulations and experimental results demonstrate the validity of the new method and the feasibility of the control strategies.

This article proposed a novel control approach for trajectory tracking of robotic airships. First, the nonlinear dynamics model of a robotic airship is derived and formulated. Second, a sliding mode controller is designed to track the commanded trajectory for its robustness against parametric variations and external disturbances. To address the chattering problem results from the sliding mode controller, a radial basis function neural network is adopted to construct the neural network self-gain-scheduling sliding mode controller in which the control gains are scheduled synchronously with the sliding surface via radial basis function neural network according to the learning algorithm, with switching sliding surface and its differential as radial basis function neural network inputs and control gains as radial basis function neural network outputs. In addition, the stability and convergence of the closed-loop controller are proven using the Lyapunov stability theorem. Finally, the effectiveness and robustness of the proposed controller are demonstrated via numerical simulations. Contrasting simulation results indicate that the neural network self-gain-scheduling sliding mode controller attenuates the chattering effectively and has better performance against the sliding mode controller.

A neural network compensator augmented computed torque control scheme for the compensation of unmodeled frictional effects in manipulators is proposed. The proposed compensator is implemented by a three layer network structure. A weight adaptation methodology based on the extended Kalman filter algorithm is used. Computer simulations are performed to verify and study the stability, convergence and trajectory tracking performance of the proposed control architecture. Results from the simulations show that the training algorithm derived from the extended Kalman filter is stable. Convergence is also verified. The simulations also show the stability of the computed torque control law augmented by the neural network compensator approximating the unmodeled frictional terms.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

A high-accuracy actuation force model of piezoelectric actuator (PEA) is very important for the high-frequency positioning control of the nanopositioning robot because the force measurement is often unavailable. In this article, an actuation force modeling and identification approach with neural network compensator of PEA with nonlinear hysteresis is proposed to realize the accurate driving force prediction, which is called neural-network-based stiffness compensation model (NNSCM). The model inputs are analog voltage signal and actual driving displacement, and the model output is actuation force. The internal creep, vibration, and hysteresis nonlinearity of the PEA are identified simultaneously based on a creep–vibration–hysteresis-dynamics (CVHD) model to calculate the nonload driving displacement from the input voltage signal on the actuator. The actuator stiffness model is compensated by a neural-network-based nonlinear model to reduce the effects of parameter and system uncertainties. The corresponding NNSCM identification algorithm is developed for accurate force prediction. Experiments on the PEA are conducted to verify the effectiveness of the proposed modeling approach and demonstrate a better model accuracy against other methods.

Considerable research has been conducted on the control of pneumatic systems. However, nonlinearities continue to limit their performance. To compensate, advanced nonlinear and adaptive control strategies can be used. But the more successful advanced strategies typically need a mathematical model of the system to be controlled. The advantage of neural networks is that they do not require a model. This paper reports on a study whose objective is to explore the potential of a novel adaptive on-line neural network compensator (ANNC) for the position control of a pneumatic gantry robot. It was found that by combining ANNC with a traditional PID controller, tracking performance could be improved on the order of 45% to 70%. This level of performance was achieved after careful tuning of both the ANNC and PID components. The paper sets out to document the ANNC algorithm, the adopted tuning procedure, and presents experimental results that illustrate the adaptive nature of NN and confirms the performance achievable with ANNC. A major contribution is demonstration that tuning of ANNC requires no more effort than the tuning of PID.

A new force tracking control algorithm of partial actuated lower limb exoskeleton suit, which is designed for enhancing human motion is presented in this paper. Firstly, a mathematical model of the electro-hydraulic servo system was created, and equations for the frictions in the hydraulic valve and actuator were obtained. Secondly, the appropriate observer based on the estimated functions and the measurement error equations are presented for the sliding mode control algorithm. Thirdly, a sliding mode controller with applicable surface coefficient has been designed for force tracking control of the servo system. Fourthly, so as to reduce the error caused by the unchangeable surface of the sliding mode control, a radial basis functions (RBF) neural network control algorithm has been introduced to offset the disadvantage of the sliding mode control by moving the sliding surface effectively. Finally, the simulation results under conditions of different frequencies and the trial results based on the human motion of sliding mode control and the RBF based sliding control are presented, which indicate that RBF based sliding control provides a better performance than regular sliding mode control.