A neural network controller for Cartesian Plotter

This article analyses the dynamic behaviour of a beam structure containing multiple transverse cracks using neural network controller. The first three natural frequencies and mode shapes have been calculated using theoretical, finite-element, and experimental analysis for the cracked and un-cracked beam. Comparisons of the results among theoretical, finite-element, and experimental analysis have also been presented. The calculated vibration signatures were used to train the feed-forward multi-layered neural network controller with back-propagation technique for the prediction of cracks. Relative crack locations and relative crack depths are the output of the neural controller. Results obtained from the various analyses are validated using the developed experimental set-up. Results from neural controller have been presented for comparison with the output from theoretical, finite-element, and experimental analysis. From the evaluation of the performance of the neural network controller it is observed that the developed method can be used as a crack diagnostic tool in the domain of dynamically vibrating structures.

This benchmark suite presents a detailed description of a series of closed-loop control systems with artificial neural network controllers. In many applications, feed-forward neural networks are heavily involved in the implementation of controllers by learning and representing control laws through several methods such as model predictive control (MPC) and reinforcement learning (RL). The type of networks that we consider in this manuscript are feed-forward neural networks consisting of multiple hidden layers with ReLU activation functions and a linear activation function in the output layer. While neural network con- trollers have been able to achieve desirable performance in many contexts, they also present a unique challenge in that it is difficult to provide any guarantees about the correctness of their behavior or reason about the stability a system that employs their use. Thus, from a controls perspective, it is necessary to verify them in conjunction with their corresponding plants in closed-loop. While there have been a handful of works proposed towards the verification of closed-loop systems with feed-forward neural network controllers, this area still lacks attention and a unified set of benchmark examples on which verification techniques can be evaluated and compared. Thus, to this end, we present a range of closed-loop control systems ranging from two to six state variables, and a range of controllers with sizes in the range of eleven neurons to a few hundred neurons in more complex systems.

In this Chapter we provide the reader with some background material on neural control strategies and we discuss neural optimal control in more detail. The Chapter is organized as follows. In Section 4.1 the basic principles of existing methods in neural control are presented, including direct and indirect adaptive control, reinforcement learning, neural optimal control, internal model control and model predictive control. In Section 4.2 neural optimal control is discussed with respect to classical theory of nonlinear optimal control. The emphasis in this Section is on the formulation of control problems as parametric optimization problems, where static and dynamic nonlinear controllers are parametrized by multilayer perceptrons. Furthermore an efficient way for including a priori results from linear control theory into the neural controller is highlighted. The latter is illustrated on the examples of swinging up an inverted and double inverted pendulum system. New contributions are stated in Section 4.2.6.

This paper describes the visual feedback positional control of the XY piezo actuator stage (PAS). The XY PAS control system consists of four main components, i.e. XY PAS as controlled object, supply electronics for piezoelectric actuators (PEAs), microscope with digital camera for visualization and for measuring the actual position and a vision processing module in combination with a desktop PC, as processing hardware. XY PAS is fabricated by a photo structuring process from photosensitive glass, and PEAs are built-onto meet the request for its precise movement. It is evident from the electromechanical model of XY PAS, that accurate positioning of XY PAS is an exacting piece of work, due to the nonlinear hysteresis inherent in PEAs. Accordingly, two neural network control techniques were developed, i.e. the feedforward neural network controller (FFNNC) and the feedforward/feedback neural network controller (FF/FBNNC). Proposed neural network controllers are compared with the traditional linear controllers.

Objective: BLDC motor specifically used for high speed applications and needs sophisticated speed control. Conventional controls techniques require more physical involvement for assisting BLDC motor to operate with precise speed value. However, soft tuning based controller may give comparatively better results for that and the same has been elaborated in present paper using neural controller of speed as per requirements.the main objective of this study may be summarized as (i) MATLAB simulink model for BLDC motor incorporated with soft tuned controller and inverter simultaneously, (ii) development of neural controller for BLDC motor control, and (iii) validation of results developed through proposed controller with the available results using PI, PID and fuzzy logic controller. Methods: The speed obtained through simulink model with input supply voltage variations are used as a reference signal for the training and testing purpose of neural controller. With the help of these reference signals, neural control executes and gives optimum values of external parameters such as speed and electromagnetic torque. Result: The study outcome provides dynamic execution of proposed controllerbased on neural network. The proposed controller’s results are validated with the reference results obtained mathematically for the system. The controller efficiency and sensitivity has been checked by MATLAB-Simulink software. Novelty: comparative study for mathematically obtained reference values and neural controller based results are proposed in this paper. The results are validated with the help of Matlab produces tables and figures. Keywords: BLDC Motor; speed control; neural network controller

DC-DC converters can be found in almost every power electronics device. To improve the efficiency and controller response of a DC-DC converter to dynamical system changes, neural network has been chosen as an alternative to classic methods. However, no prior work has been done in the neural network approach for control of a PSFB (phase-shifted full-bridge) converter yet. In this research, a multi-layer feedforward neural network controller is proposed. The neural network based controller has the advantage of adaptive learning ability, and can work under the situation when the input voltage and load current fluctuate. Levenberg-Marquardt back-propagation training algorithm is used in computer simulation. The neural controller is then implemented on hardware using a DSP (digital signal processor). Satisfactory experimental results are obtained.

End milling operations are essential to machine complex-contoured parts which are widely used in automobile and aerospace industries. Controlling the cutting force is important in these operations. But this is a difficult task for a number of reasons. A neural network control scheme is developed in this study to control the average resultant cutting force. The control scheme involves a neural identifier and a neural controller. The neural identifier is trained to represent the process accurately, and the neural controller is trained to give an input to the process which will yield the desired output. Recurrent neural networks are employed for both the neural identifier and neural controller, and training is accomplished using a recursive least squares algorithm. Results validating the methodology are presented for one-dimensional milling.

Due to the depletion of fossil fuels, offshore wind turbines have become significant contributors to energy production. The offshore wind turbines are subjected to severe environmental loads like wind, wave, and current. The combined effect of these loads induces significant vibrations in the structure, which may cause economic loss and reduce the power production capacity. Thus, the structure is designed to have a small response under environmental load, but it also increases the cost. Another alternative to reduce the structure’s response is implementing structural control devices. MR dampers are semi-active devices widely used in controlling onshore structures because of their adaptability to various loads. Since the environmental loads on the wind turbine have a wide range of spectral content, semi-active control is best suited due to their adaptability. The force generated by the MR damper is enormous for small input energy, and thus it is an attractive option for adaptive structural control in civil structures. Several semi-active control algorithms are available in the literature for nonlinear MR dampers. The semi-active algorithm obtains the optimal control force of the linearized system and smartly switches off the MR damper according to the system requirement. The offshore structure is nonlinear, so a nonlinear control algorithm is expected to have advantage over other techniques. One of the commonly used nonlinear control algorithms is the backstepping method. This method involves a systematic development of the Lyapunov function for a given nonlinear system. The nonlinearity in the MR damper arises due to the hysteretic property of the MR fluid. Many phenomenological models are studied in the literature to capture MR dampers' nonlinearities effectively. Bouc wen model is one such model that is widely used for modeling MR dampers.The backstepping controller requires full state feedback to produce the control signal but measuring many variables is difficult in real-time. Some controllers do not require an accurate structure model, and the control action is based on the measured response. This paper uses the feed-forward neural network controller (NNC) to control nonlinear dynamic systems. The controller is trained using the displacement time histories of the structure to predict the MR damper voltage. The NNC is trained with the output from the backstepping controller for various environmental conditions. In this study, a fixed offshore wind turbine in a water depth of 64.5m is controlled using NNC and backstepping controllers. Further, the control efficiency of the NNC is compared for different load cases.

<p>Quadcopters are popular UAVs owing to their compact size and maneuverability. Quadcopters are unmanned aircraft guided by remote control, and the demand for them is increasing due to their widespread surveillance, goods delivery, aerial photography, and defense applications. Nonlinear quadcopter operation makes control system implementation very challenging. In this paper, based on artificial intelligence (AI), we train a feedforward neural network (FFNN) controller of a traditional proportional integral derivative (PID). The conventional (PID) is generally tuned to improve the quadcopter control and performance. FFNN can perform offline learning between the inputs and outputs of the controller to learn its behavior. Once the learning is complete, we replace the PID controller with the neural network controller, to get a controller that can maintain system stability,and overcome the limitations of hardware implementation problems caused by the classical PID controller.</p>

Adaptive growing-and-pruning neural network control for a linear piezoelectric ceramic motor

Parameter estimation of fuzzy neural network controller based on a modified differential evolution

On-line adaptive control for inverted pendulum balancing based on feedback-error-learning

The paper presents a neural network controller for trajectory tracking for a two D.O.F. SCARA robot mechanism. Two types of neural network controllers were built: a joint space neural network controller and a task space neural network controller. The two controllers were compared with a computed torque method controller in a joint as well as task space. The four controllers were tested on a real robot mechanism. The Lyapunov theory for deriving the adaptation law, or the learning algorithm of neural networks, was used to prove the robot system stability with a neural network controller. >

The theoretical development of a trajectory tracking neural network controller based on the theory of sliding-mode controllers is shown in the paper. Derived equations of the neural network controller were verified on a direct drive 2-DOF SCARA mechanism model. The new neural network controller was compared with a neural network controller based on the computed torque method. At last we made an application on a real 2-DOF SCARA robot mechanism by the neural network controller based on the computed torque method and a sliding-mode neural network controller on a real single axis direct drive robotic manipulator driven by an induction motor.

This study aims to evaluate the behavior of neural network control method for digitally controlled dc-dc converters when the circuit parameter condition varies from which is in the training of the neural network. Learning based methods, which include the neural network control, are constructed and tuned using the training data to control given plants. They can provide the effective control since they are tuned as the dedicated one, however, they have difficulties when the parameters of components in the plant are changed from original ones, which are used to obtain the training data. Therefore, they may lose the effectivity in control if the the parameters in plant are changed. In the case of controlling dc-dc converters, the circuit parameter condition such as capacitance, reactor and so forth, are varied in the case that the specification of the circuit design is changed. Moreover they are changed by the environmental condition such as temperature, aging degradation and so forth. In this study, we study the effectivity of neural network control method for dc-dc converters when the circuit parameters are changed from the ones which are used in the training. When the circuit parameters are changed from original one, we evaluate that whether the neural network can control without any tuning, such as re-training of the neural network. From evaluation results, we confirm that the neural network control can work effectively even in such situation and it reveals that the neural network control has the robustness against the change of the circuit parameter condition.