Dynamic neural network control through fuzzy Q-learning algorithms

In this paper, the position of a pulse width modulation (PWM)-driven pneumatic actuator has been controlled using a dynamic neural network (DNN) and Proportional Integral Derivative (PID) controller. The harmony search algorithm (HSA) has been used to unravel the optimization problem. The DNN controller is optimally designed to control the position of the actuator. As to the performance of the PID controller, it can assist the DNN controller to give better results. Therefore, an optimal hybrid scheme with both DNN and PID controllers based on HSA is suggested. A pneumatic circuit containing a fast-switching valve is used to reduce the complexity of the PWM-driven servo pneumatic system along with its cost price.

Dynamic neural network control for non-linear systems: optimal neural network structure and stability analysis

DNNC has been successfully applied to nonisothermal CSTR with time varying parameters including activation energy and heat transfer coefficient. Thus, the objectives of the paper are: 1. To study the constraint handling properties of DNNC, 2. To extend SISO-DNNC to MIMO-DNNC, 3. To study the on-line adaptation properties of DNNC. >

Dynamic neural network controller model of PEM fuel cell system

In the applications of the magnetostrictive actuators (MA), hysteresis of the MA is particularly significant and causes undesired effect in the control system. In order to reduce hysteresis effect and obtain precision position in actual application, a neural network supervisory control was proposed and three different neural networks were used. Hysteresis would be compensated and the precision control of the MA would be obtained. These neural networks were respectively radial basis function neural network (RBFNN), dynamic recurrent neural network (DRNN) and cerebellar model articulation controller (CMAC). Through comparing these neural networks in tracking performance, tracking speed and parameter number, the control performance is better when using DRNN and CMAC, especially CMAC with 4 parameters.

This paper describes the design and implementation of a neural network controller capable of printing designs and drawings on paper using a Cartesian Plotter. The Cartesian plotter uses two dc motors with incremental encoders for motion along x and y-axis while third dc motor along z-axis controls the pen assembly for drawing the text and graphics data. The motion commands for the motors are generated with the help of a simple feed forward neural network controller trained with back propagation algorithm. The nine inputs, two output neural controller employs four neurons in the hidden layer with tangent sigmoid being activation function for hidden neurons while linear function is used for output neurons. The proposed neural controller can drive the pen assembly in one of the eight possible directions and thus produces similar results to the famous Bresenham's algorithm. Simulations and practical results validate the neural controller for use with Cartesian plotters.

Wind energy is a widespread natural phenomenon, which receives more and more attention because of its renewable and non-polluting nature, but the unpredictable and unstable wind speed makes the wind power control technology become a hot spot of concern. Firstly, the working principle of the wind turbine system is introduced, and the wind turbine speed model of the wind turbine drive system is established according to the system stability characteristics. Then on the basis of the traditional PID control algorithm, a wind turbine rotation speed regulation optimization algorithm based on PID optimization control is proposed-PID neural network control. The algorithm designs a three-layer forward PID neural network, and through the PID variable structure control, the low-speed axis of the fan connects the rotor axis with the gear box, which excites the operation of the aerodynamic gate for speed regulation, and compared with the traditional PID control, the method can regulate the airflow of the coal mine fan more quickly, and the overshooting amount is reduced by about 22%. Then, the BP neural network control is used to predict the air demand, and the deviation of the predicted air demand from the current air demand and its chemical rate are input into the controller. Finally, through the comparison of the control system and simulation experiments, it is proved that the BP neural network control has stronger robustness and adaptability, and can achieve better control effect.

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.

Recently intelligent control has received increased attention in various applications. With PID controllers, it is difficult to obtain gain suitable to the load because of disturbances, parameter variations and measurement noise. In order to reduce mechanical parameter variations, and to obtain good dynamic performance, PID controllers and neural network controllers for AC servomotor control are investigated. The microprocessor provides an output to the difference in command. The servo system improves the characteristics of speed control. When the motor is running at the same speed as set by the reference signal, the speed encoder also provides a signal of the same frequency. From the viewpoint of wide control range, a good dynamic performance and a cost effective approach, the NNE of an adaptive neural network controller is used to identify the parameters and characteristics of the AC servomotor. To train the controller, the weights are dynamically adjusted using the backpropagation algorithm. Neural networks are used so PID control can control, efficiently, the speed of the AC servomotor. Finally experimental results prove the excellent performance of this control system.

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.

Nowadays, the New energy vehicles(NEVs) have been developed in a key way as an industry adjusted by China’s national strategy. Aiming at the problems of poor parameter adjustment and low response speed existing in traditional PID control of energy vehicles in the complex driving environment, a speed control method of DC motor based on BP neural network and traditional PID was proposed, which greatly improved the speed control efficiency and accuracy of new energy vehicles. According to the nonlinear and multivariable characteristics of brushless DC motor control system, the motor and control principle are modeled and analyzed by Simulink. Then based on Proteus, STC89C51 single-chip microcomputer combined with the drive control module is used to simulate motor speed control. Meanwhile, in order to enhance the adaptability and rapidity of the parameter adjustment in speed regulation system, BP neural network and traditional PID control are applied in the designation of controller, which can implement the self-adaptation control of system and self-tuning of PID parameters. At last, the simulation is verified by MATLAB. The experimental results show that the BP-PID neural network controller has the advantages of good robustness, strong stability and fast response. At the same time, the BP-PID neural network controller has stronger anti-disturbance performance under the disturbed conditions, which can prove the correctness and feasibility of the designed model above. This approach provides a new solution to improve the performance of NEVs.

To address the training challenges of more-adaptive control in water quality management and inefficiency in maintaining carbon balance in environmental monitoring systems, this study designs a neural network-based controller for enhancing water quality and carbon balance used in teaching platform of a rural sewage treatment system. Firstly, a dynamic model of water quality parameters and carbon balance is established with the integration of biochemical processes and environmental conditions. Then, A neural network controller is trained to modulate dissolved oxygen levels, nutrient concentrations, and carbon sequestration rates adaptively by environmental legislation. The control system is simulated and validated in MATLAB/Simulink, where the neural network modulates system inputs in real time based on sensor readings. Experimental validation is conducted using a pilot-scale water treatment facility, and the efficacy of the neural network controller is compared to that of traditional PID control. The experiment results show a 78.6% decrease in root mean square error (RMSE) regarding dissolved oxygen monitoring and a 19.4% enhancement in carbon balance efficiency. Incorporating neural network control improves system stability during changing influent conditions and achieves an 18.2% decrease in energy consumption. This study can promote the teaching platform development of intelligent water management technologies in urban and rural ecosystems.

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

Through the analysis of the mathematical model of multi induction motor synchronous drive system, a new control method based on neural network is proposed and applied into the system.The neural network controller is composed of self-tuning PID controller based on diagonal recurrent neural network (DRNN) and neuron decoupling compensator. The three self-tuning PID controllers are used in the speed and tension control loops respectively, making the system possess stronger adaptive capability and robustness. The neuron decoupling compensator integrates the effect of the three loops and realizes the adaptive decoupling control between speed and tension by training the weights of network to compensate the coupling relation. The experiment results show that, compared with traditional PID control, the control system can obtain optimal parameters according to online identification of the DRNN network, realizing the better decoupling control of speed and tension, and the system has better dynamic, static characteristics and robustness.

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. >