Neuro-control System Research Articles

Machine Learning Model for Quality Parameters Prediction and Control System Design in the Kecombrang Flower (Etlingera elatior) Extraction Process

Kecombrang flowers have bioactive components that can be used as food additives. The development of the kecombrang functional food industry for the production of food additives requires information on production parameters. The extraction process for kecombrang to obtain bioactive components, especially phenols and flavonoids, requires maximum temperature treatment and extraction time. This study aims to determine the standard for the kecombrang flower extraction process, create a machine learning model to estimate the quality parameters of the extraction results (phenol, flavonoid, pH, color, and viscosity), and design a strategy for controlling the extraction machine work to maintain the quality of the extraction, especially of phenols and flavonoids. This research was conducted at extraction temperatures of 60 °C, 65 °C, 70 °C, and 75 °C. During the extraction process, the quality of the material was checked by measuring phenol and flavonoid contents, as well as color, pH, and viscosity. Sampling was carried out at 5 min intervals. The data on the quality parameters during the extraction process were analyzed for trends. A machine learning model, which is an artificial neural network, was developed using a 2–6–1 architecture for each quality parameter. The two inputs of ANN were temperature of extraction and extraction time (duration). The output was the quality parameters of the products (phenols, flavonoids, pH, viscosity, and color), which were evaluated separately. The results show a good correlation between the model and the experimental data, with both the training dataset and the testing dataset. These results were then used to formulate a strategy for controlling the extraction process. A neuro-control system was used as a strategy. This control system was adaptive to changes that occurred during the extraction process so that phenols and flavonoids could be maintained.

SUBSTANTIATION OF NEUROCONTROLER PARAMETERS FOR THE CONTROL SYSTEM OF THE VIBRATOR DRIVE OF ADAPTIVE VIBRATION TECHNOLOGICAL MACHINES

The article proposes and analyzes the structure of the neurocontroller for controlling the vibratory drive of adaptive vibrating technological machines (AVTM), which allows to implement a two-circuit neurocontrol system of energy and technological parameters of AVTM that its each circuit takes into account inertial and dissipative characteristics. By monitoring the phase shift between the frequency of forced oscillations of the AVTM working body and the frequency of cyclic forcing force of the vibrating drive and using predictive model neurocontrol technology to correct the frequency of cyclic forcing force of the vibrating drive, the neurocontroller provides mini resonant operation. The second circuit of neurocontrol provides on the resonant frequency tracking and stabilization of the specific work of the vibration field of AVTM during the vibration cycle using to adjust the amplitude of oscillations of the working body hybrid neuro-PID control system with self-tuning based on neuromodel AVTM system. The proposed design of the neurocontroller to control the vibratory drive of adaptive vibrating technological machines can improve the quality characteristics of the control of dynamic parameters of both electromagnetic and unbalanced vibratory drive. The use of neural network technologies in the design solution allows the introduction of neurocontrol algorithms that change the parameters of the process of vibration processing implemented by AVTM, or change the load mass of the working body AVTM, through the use of predictive model neurocontrol based on the simplex method or quasi-Newtonian algorithm that will optimally choose a strategy for correcting the frequency of cyclic forcing force of the vibrator to ensure and maintain a constant resonant mode of AVTM and at the resonant frequency AVTM will stabilize the specific operation of the neural network PID-controller with self-adjustment on the basis of the direct AVTM neuroemulator.

Sensory regulation of stance-to-swing transition in generation of adaptive human walking: A simulation study

In this paper, we investigated sensory mechanisms to regulate the transition from the stance to swing phases in the generation of adaptive human bipedal walking based on a neuromusculoskeletal model. We examined the contributions of the sensory information from the force-sensitive afferents in the ankle extensor muscle and from the position-sensitive afferents from the hip, inspired by a neuro-mechanical simulation for the stepping of the hind legs of cats. Our simulation results showed that the sensory signals related to the force in the ankle extensor muscle make a larger contribution than sensory signals related to the joint angle at the hip to produce robust walking against disturbances, as observed in the simulation results of cat locomotion. This suggests that such a sensorimotor mechanism is a general property and is also embedded in the neuro-control system of human bipedal walking.

Control de Robots Móviles con Incertidumbres Dinámicas usando Redes de Base Radial

This paper presents an adaptive trajectory tracking control for mobile robots for which stability conditions and performance evaluation are given. The proposed control structure combines a feedback linearization model, based on a kinematics nominal model, and a direct neural network-based adaptive dynamics control. The control system design is done considering uncertain dynamic parameters in the dynamic model of the robot. The uncertainty in the dynamics model is learned by a RBF neural network in an adaptive feedback loop, adjusting the weight and the radial basis functions. The proposed RBF-NN scheme 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 back propagate the control errors through the model (or network model) to adjust the neurocontroller. The resulting adaptive controller is efficient and robust in the sense that it succeeds to achieve a good tracking performance with a small computational effort. Stability result for the adaptive neuro-control system is given. It is proved that control errors are ultimately bounded as a function of the approximation error of the RBF-NN. Experimental results show the practical feasibility and performance of the proposed approach to mobile robots.

Control de Robots Móviles con Incertidumbres Dinámicas usando Redes de Base Radial

This paper presents an adaptive trajectory tracking control for mobile robots for which stability conditions and performance evaluation are given. The proposed control structure combines a feedback linearization model, based on a kinematics nominal model, and a direct neural network-based adaptive dynamics control. The control system design is done considering uncertain dynamic parameters in the dynamic model of the robot. The uncertainty in the dynamics model is learned by a RBF neural network in an adaptive feedback loop, adjusting the weight and the radial basis functions. The proposed RBF-NN scheme 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 back propagate the control errors through the model (or network model) to adjust the neurocontroller. The resulting adaptive controller is efficient and robust in the sense that it succeeds to achieve a good tracking performance with a small computational effort. Stability result for the adaptive neuro-control system is given. It is proved that control errors are ultimately bounded as a function of the approximation error of the RBF-NN. Experimental results show the practical feasibility and performance of the proposed approach to mobile robots.

Semiactive Neurocontrol for Seismic Response Reduction Using Smart Damping Strategy

A new semiactive control strategy that combines a neurocontrol system with a smart damper is proposed to reduce seismic responses of structures. In the proposed semiactive control system, the improved neurocontroller, which was developed by employing a training algorithm based on a cost function and a sensitivity evaluation algorithm to replace an emulator neural network, produces the desired active control force, and then a bang-bang-type controller clips the control forces that cannot be achieved by a smart damper (e.g., a variable orifice damper, controllable fluid damper, etc.). Therefore, the proposed semiactive control strategy is fail-safe in that the bounded-input, bounded-output stability of the controlled structure is guaranteed. Numerical simulation results show that the proposed semiactive control system that employs a neural network-based control algorithm is quite effective in reducing seismic responses.

Neural networks for advanced control of robot manipulators

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, 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 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.

Neuro‐control of seismically excited steel structure through sensitivity evaluation scheme

AbstractThe neuro‐controller training algorithm based on cost function is applied to a multi‐degree‐of‐freedom system; and a sensitivity evaluation algorithm replacing the emulator neural network is proposed. In conventional methods, the emulator neural network is used to evaluate the sensitivity of structural response to the control signal. To use the emulator, it should be trained to predict the dynamic response of the structure. Much of the time is usually spent on training of the emulator. In the proposed algorithm, however, it takes only one sampling time to obtain the sensitivity. Therefore, training time for the emulator is eliminated. As a result, only one neural network is used for the neuro‐control system. In the numerical example, the three‐storey building structure with linear and non‐linear stiffness is controlled by the trained neural network. The actuator dynamics and control time delay are considered in the simulation. Numerical examples show that the proposed control algorithm is valid in structural control. Copyright © 2001 John Wiley & Sons, Ltd.

Adaptive Neuro Controller for a Precise Maneouvring of Underwater Vehicle

A neuro controller for high precision manoeuvring of underwater vehicles require special attention to a number of factors including thruster and vehicle’s nonlinearities, couplings which exist between various degrees of freedom as well as effects of the sea currents. The neuro control system for underwater vehicle maneouvring described here is based on the conventional controller supported with the so called adaptive neural network.

Track-following control of a dual-stage hard disk drive using a neuro-control system

This paper describes the track-following control of a dual-stage hard disk drive system using neural-networks. A neural-network approach to on-line learning control, and a real-time implementation for a dual-stage hard disk drive, are presented. The use of the dual-stage actuator in hard disk drive systems has become a means of achieving increased servo actuator bandwidth. The dual-stage actuator presented here uses a voice-coil motor (VCM) as a coarse actuator, and a piezoelectric actuator (PZT) as a fine actuator. The control system consists of a series combination of both a plant with a feedback loop and a neural-network with a feedforward loop. The neural-network functions as the reference input filter, and it organizes a new reference signal to the closed-loop circuit. Numerical and experimental results for the track-following control system of the dual-stage hard disk drive show the validity of the proposed neuro-control system.

PLS: A Pseudo Least Squares Method for Neural Network Training

The paper presents a least squares based estimator for training the weights of a feedforward neural network. Although retaining the algorithmic simplicity of the backpropagation method, it has the advantage of a far better convergence rate. The algorithm is the core of a neurocontrol system for a semiconductor deposition reactor.

A neuro-control system for the knee joint position control with quadriceps stimulation

A neuro-control system was designed to control the knee joint to move in accordance with the desired trajectory of movement through stimulation of quadriceps muscle. This control system consisted of a neural controller and a fixed parameter proportional-integral-derivative (PID) feedback controller, which was designated as a neuro-PID controller. A multilayer feedforward time-delay neural network was used and trained as an inverse model of the functional electrical stimulation (FES)-induced quadriceps-lower leg system for direct feedforward control. The training signals for neural network learning were obtained from experimentation using a low-pass filtered random sequence to reveal the plant characteristics. The Nguyen-Widrow method was used to initialize the neural connection weights. The conjugate gradient descent algorithm was then used to modify these connection weights so as to minimize the errors between the desired outputs and the network outputs. The knee joint angle was controlled with only small deviations along the desired trajectory with the aid of the neural controller. In addition, the PID feedback controller was utilized to compensate for the residual tracking errors caused by disturbances and modeling errors. This control strategy was evaluated on one able-bodied and one paraplegic subject. The neuro-PID controller showed promise as a position controller of knee joint angle with quadriceps stimulation.

Damping enhancement of multimachine power system using adaptive generator control system with neural networks

AbstractThe authors proposed a nonlinear adaptive generator control system with neutral networks for improving damping of power systems, and showed its effectiveness in a one‐machine infinite bus test power system in a previous paper. The proposed neurocontrol system adaptively generates appropriate supplementary control signals to the conventional controllers such as the automatic voltage regulator and speed governor so as to enhance transient stability and damping of the power system.In this paper, the applicability of the proposed neurocontrol system to multimachine power systems is discussed. Digital time simulations are carried out for a 4‐machine test power system, where one or several synchronous generators is equipped with the neurocontrol system. As a result, also in the multimachine power system, the proposed adaptive neurocontrol systems improve the system damping effectively and they work adaptively against the wide changes of the operating conditions and the network configuration.

An adaptive neuro-control system of synchronous generator for power system stabilization

This paper proposes a nonlinear adaptive generator control system using neural networks, called an adaptive neuro-control system (ANCS). This system generates supplementary control signals to conventional controllers and works adaptively in response to changes in operating conditions and network configuration. Through digital time simulations for a one-machine infinite bus test power system, the control performance of the ANCS and advanced controllers such as a linear optimal regulator and a self-tuning regulator is evaluated from the viewpoint of stability enhancement. As a result, the proposed ANCS using neural networks with nonlinear characteristics improves system damping more effectively and more adaptively than the other two controllers designed for the linearized model of the power system.

Synchronous generator control using neural network‐based nonlinear adaptive regulator

AbstractControl equipment of synchronous generators such as automatic voltage regulators, speed governors and power system stabilizers have been developed to maintain stability and to improve damping of power systems. When an operating condition changes greatly, however, such controllers may become less effective because of nonlinearity of the power system.In this paper, a nonlinear adaptive generator control system using neural networks is proposed. The proposed neurocontrol system consists of two neural networks which work as an identifier and a controller, respectively, and generates supplementary control signals to the conventional controllers. An essential feature of the proposed system is that the internal connection weights of both neural networks are adjusted adaptively so as to generate appropriate control signals for transient stability and damping enhancement in response to changes of the operating conditions and the network configuration.To investigate the control performance of the proposed neurocontrol system, digital time simulations are carried out for a one‐machine infinite bus model system. As a result, it is clarified that the proposed adaptive neurocontrol system effectively improves the system damping and shows adaptability against the wide changes of the operating conditions.

Temperature regulation with neural networks and alternative control schemes

In this article, we compare the neuro-control algorithm to three other control algorithms: fuzzy logic control, generalized predictive control, and proportional-plus-integral control. Each of these four algorithms is implemented on a water bath temperature control system. The four systems are compared through experimental studies under identical conditions with respect to set-point regulation, the effect of unknown load disturbances, large parameter variation, and variable deadtime in the system. It is found that the neurocontrol system compares well with the other three control systems and offers encouraging advantages. From the results of the experimental studies, however, the best characteristics of each of these different classes of control systems may be combined for realizing a more efficient and intelligent control scheme.

発電機励磁制御における適応型ニューロ制御系とSTRの安定度向上性能の比較

発電機励磁制御における適応型ニューロ制御系とSTRの安定度向上性能の比較

GMV technique for nonlinear control with neural networks

A nonlinear extension of minimum variance and generalised minimum variance control strategies is developed. The plant is modelled with a linear autoregressive part and a nonlinear dependency on the input. A neural network based implementation of the control law is discussed. This results in a nonlinear controller constituted by a few linear blocks complemented with not more than two neural networks. The weights of the networks are estimated off-line and the learning is carried out with input-output data provided by suitable open loop identification experiments. The performance of the time-invariant neuro-control system is compared with the one achievable by adaptive controllers based on linear models of the plant.