Speed Control of a Servo Hydraulic Actuator, Using Artificial Neural Networks and Feedback Error Learning Algorithm (original) (raw)
Related papers
Application of a flexible structure artificial neural network on a servo-hydraulic rotary actuator
International Journal of Advanced Manufacturing Technology, 2008
In this article the results of the application of a flexible structure artificial neural network for controlling the angular velocity of a servo-hydraulic rotary actuator are discussed. A mathematical model for the system is derived, and a flexible artificial neural network (ANN)-based controller with the feedback error learning method as a learning algorithm is applied to the system. The neural network-based controller has a feed-forward structure and three layers. The flexible bipolar sigmoid function was used as the activation function of the network. The simulation and experimental results show good performance of the developed method in learning the inverse dynamic of the system and controlling the angular velocity of the rotary hydro motor. The advantages of the developed method for servo-hydraulic actuators over other traditional approaches are discussed.
IEEE Transactions on Industrial Electronics, 2001
This thesis presents an intelligent strategy for controlling the tip position of a flexible-link manipulator. Motivated by the well-known inverse dynamics control approach for rigid-link manipulators, two multi-layer feedforward neural networks are developed to learn the nonlinearities of the system dynamics. The re-defined output scheme is used by feeding back this output to guarantee the minimum phase behavior of the resulting closed-loop system. No a prion' knowledge about the nonlinearities of the system is needed where the payload mass is also assumed to be unknoa-n. The weights of the networks are adjusted using a modified on-line error backpropagation algorithm that is based on the propagation of the redefined output error, derivative of this error and the tip deflection of the manipulator. Numencal simulations as well as real-time controller hplernentation on an experimental setup are carried out. The results acliieved by the proposed neural network-based controller are compared in simulations and experimentally with conventional PD-type and inverse dynamics controls to substantiate and demonstrate the advantages and the promising potentials of this scheme. work, to Sanjeev for proof-reading of a part of this thesis, and to my best friends, Quan and Qingyuan, who have always given me a spintual support. But last, and always, 1 am indebted t o my mother, the rest of my family in China, and my canadian friend, Dorothy, for their continuing backup and encouragement during my study. Their ambitions on me have always been rny source of strengt h and motivation.
Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2021
In this work, we use a neural network as a substitute for the traditional analytic functions employed as an inversion set in feedback linearization control algorithms applied to hydraulic actuators. Although very effective and with strong stability guarantees, feedback linearization control depends on parameters that are difficult to determine, requiring large amounts of experimental effort to be identified accurately. On the other hands, neural networks require little effort regarding parameter identification, but pose significant hindrances to the development of solid stability analyses and/or to the processing capabilities of the control hardware. Here, we combine these techniques to control the positioning of a hydraulic actuator, without requiring extensive identification procedures nor losing stability guarantees for the closed-loop system, at reasonable computing demands. The effectiveness of the proposed method is verified both theoretically and by means of experimental results.
Indonesian Journal of Electrical Engineering and Computer Science
Servo-hydraulic systems have been extensively employed in various industrial applications. However, these systems are characterized by their highly complex and nonlinear dynamics, which complicates the control design stage of such systems. In this paper, an extended wavelet functional link neural network (EWFLNN) is proposed to control the displacement response of the servo-hydraulic system. To optimize the controller's parameters, a recently developed optimization technique, which is called the modified sine cosine algorithm (M-SCA), is exploited as the training method. The proposed controller has achieved remarkable results in terms of tracking two different displacement signals and handling external disturbances. From a comparative study, the proposed EWFLNN controller has attained the best control precision compared with those of other controllers, namely, a proportional-integralderivative (PID) controller, an artificial neural network (ANN) controller, a wavelet neural netw...
The motion control of an experimental hydraulically actuated robot with structured uncertainty (parameter uncertainty, unknown loads, inaccuracies in the torque constants of the actuators, and others) and unstructured uncertainty (high-frequency modes, neglected time-delays, unknown friction forces, stick-slip oscillations, and unknown oil viscosity, etc…) is considered. As a solution we propose two control techniques based on ANFIS: Adaptive Neuro Fuzzy Inference System based computed torque controller (type PD), and Adaptive Neuro Fuzzy Inference System based PD plus I controller. Comparative evaluations with respect to conventional PD controller are presented to validate the controllers design. The simulated and experimental results presented emphasize that a satisfactory tracking precision could be achieved using ANFIS controllers. Keywords ANFIS based computed torque controller (type PD), ANFIS based computed torque controller (type PD) plus I, ANFIS based PD plus I controller, hydraulically actuated robot arm.
Multiple neural networks in flexible link control using feedback-error-learning
Proceedings of the 16th …, 2001
In this paper two different control approaches using Feedback-Error-Learning are combined. These approaches are used for neural control of a flexible link in order to acquire the inverse dynamic model of the plant. Such systems are characterized as a non-minimum phase system, which is difficult to be controlled by most techniques and by only one neural network, hence this difficulty is overcome by the approaches discussed here: one redefines the output of the plant and the other modifies the reference input. And besides, these approaches are combined in order to obtain a better trained neural ensemble and so a better performance is achieved in neural control.
Being difficult to attain the precise mathematical models, traditional control methods such as proportional integral (PI) and proportional integral differentiation (PID) cannot meet the demands for real time and robustness when applied in some nonlinear systems. The neural network controller is a good replacement to overcome these shortcomings. However, the performance of neural network controller is directly determined by neural network model. In this paper, a new neural network model is constructed with a structure topology between the regular and random connection modes based on complex network, which simulates the brain neural network as far as possible, to design a better neural network controller. Then, a new controller is designed under smallworld neural network model and is investigated in both linear and nonlinear systems control. The simulation results show that the new controller basing on small-world network model can improve the control precision by 30% in the case of system with random disturbance. Besides the good performance of the new controller in tracking square wave signals, which is demonstrated by the experiment results of direct drive electro-hydraulic actuation position control system, it works well on anti-interference performance.
ISA transactions, 2011
This paper presents a new intelligent approach for adaptive control of a nonlinear dynamic system. A modified version of the brain emotional learning based intelligent controller (BELBIC), a bio-inspired algorithm based upon a computational model of emotional learning which occurs in the amygdala, is utilized for position controlling a real laboratorial rotary electro-hydraulic servo (EHS) system. EHS systems are known to be nonlinear and non-smooth due to many factors such as leakage, friction, hysteresis, null shift, saturation, dead zone, and especially fluid flow expression through the servo valve. The large value of these factors can easily influence the control performance in the presence of a poor design. In this paper, a mathematical model of the EHS system is derived, and then the parameters of the model are identified using the recursive least squares method. In the next step, a BELBIC is designed based on this dynamic model and utilized to control the real laboratorial EHS system. To prove the effectiveness of the modified BELBIC's online learning ability in reducing the overall tracking error, results have been compared to those obtained from an optimal PID controller, an auto-tuned fuzzy PI controller (ATFPIC), and a neural network predictive controller (NNPC) under similar circumstances. The results demonstrate not only excellent improvement in control action, but also less energy consumption.
Neural networks for advanced control of robot manipulators
IEEE Transactions on Neural Networks, 2002
This paper presents an approach and a systematic design methodology to adaptive motion control based on neural networks (NNs) for high-performance robot manipulators, for which stability conditions and performance evaluation are given. The neurocontroller includes a linear combination of a set of off-line trained NNs (bank of fixed neural networks), and an update law of the linear combination coefficients to adjust robot dynamics and payload uncertain parameters. A procedure is presented to select the learning conditions for each NN in the bank. The proposed scheme, based on fixed NNs, is computationally more efficient than the case of using the learning capabilities of the neural network to be adapted, as that used in feedback architectures that need to propagate back control errors through the model (or network model) to adjust the neurocontroller. A practical stability result for the neurocontrol system is given. That is, we prove that the control error converges asymptotically to a neighborhood of zero, whose size is evaluated and depends on the approximation error of the NN bank and the design parameters of the controller. In addition, a robust adaptive controller to NN learning errors is proposed, using a sign or saturation switching function in the control law, which leads to global asymptotic stability and zero convergence of control errors. Simulation results showing the practical feasibility and performance of the proposed approach to robotics are given.
ADAPTIVE TRACKING CONTROL OF HYDRAULIC ROBOT MANIPULATOR USING HYBRID INTELLIGENT SYSTEM (ANFIS
The motion control of an experimental hydraulically actuated robot with structured uncertainty (parameter uncertainty, unknown loads, inaccuracies in the torque constants of the actuators, and others) and unstructured uncertainty (high-frequency modes, neglected time-delays, unknown friction forces, stick-slip oscillations, and unknown oil viscosity, etc…) is considered. As a solution we propose two control techniques based on ANFIS: Adaptive Neuro Fuzzy Inference System based computed torque controller (type PD), and Adaptive Neuro Fuzzy Inference System based PD plus I controller. Comparative evaluations with respect to conventional PD controller are presented to validate the controllers design. The simulated and experimental results presented emphasize that a satisfactory tracking precision could be achieved using ANFIS controllers. Keywords ANFIS based computed torque controller (type PD), ANFIS based computed torque controller (type PD) plus I, ANFIS based PD plus I controller, hydraulically actuated robot arm.