Recurrent fuzzy neural network by using feedback error learning approaches for LFC in interconnected power system

Modern greenhouse is becoming more and more complex and big, traditional manual control has been incompetent for the greenhouse control. Automatic control could greatly improve the work efficiency. PID (Proportional Integral and Derivative) controller is the most effective way to control the greenhouse microclimate. Recently some advanced control methods have been investigated, but most of them are still based on PID control, such as neural control and fuzzy control. The PID parameters play the important role for these methods. However the PID parameters can not be determined by a certain principle; they are usually defined by try and error way or some heuristic self-tuning method. How to get the optimal PID parameters is discussed by a number of researchers. And in the end it is still necessary to check these theories on site. The correctness is still uncertain if the season changed or some other climate devices changed beyond the site work. This paper investigates a new method of tuning the PID controller parameters for the greenhouse climate control system using CFD simulation. CFD simulation can correctly predict the greenhouse microclimate status, and can provide 3D results of the simulation process for the complex and comprehensive microclimate situations. CFD software can simulate the main factors of real greenhouse such as temperature and air velocity, and the other factors such as solar radiation heat, buoyancy effect and gravity can also be considered. Another important superiority is that CFD can simulate any climate (winter or summer, etc) by purpose. A greenhouse CAD model with its main accessories is built by a real greenhouse dimensions in this paper. And the rough steps of CFD simulation are introduced first, and then the workflow of tuning the PID values based on greenhouse simulation process is introduced in details. Finally some CFD simulation results are showed and discussed.

Coot optimization algorithm-tuned neural network-enhanced PID controllers for robust trajectory tracking of three-link rigid robot manipulator

Performance of the Permanent Magnet Synchronous Motor (PMSM) drive is reasonably influenced by the speed controller design. Extensively used speed controller is proportional, integral and derivative (PID) controller. Tuning of controller is again a cumbersome task. Normally, the PID controller gains give acceptable results for a low power application drive but when the question of high power application drive arises, an un-tuned PID controller does not provide satisfactory performance. Since, the requirement of tuning of PID is continuously felt; extensively used conventional technique for tuning i.e. Zeigler Nichols (Z-N) method has been considered in this paper. To improve the drive's performance, a proper and continuous tuning of the PID controller is required. Hence, to achieve this objective, and cope with inherent non linearity in PMSM drive, Adaptive Neuro Fuzzy Inference System (ANFIS) have been proposed as a replacement of conventional PID controller. A comparative study on the performance of the PMSM drive has been carried out in this paper.

As the character of brushless DC motor (BLDCM) is nonlinear, the classical control method can not obtain satisfied performance, so the fuzzy control is used to control BLDCM, but the conventional fuzzy controller has no integral part, which performance is similar to Proportional Derivative(PD) controller, so its static control precision cannot be guaranteed. In this paper, a fuzzy Proportional Integral and Derivative(PID) controller that can ensure static precision is proposed to improve the performance of conventional fuzzy controller and is applied to the speed control of brushless DC motor. The proposed fuzzy-PID method employs fuzzy control when the error is big, employs the PID control when the error is small, so it has both the rapid response of ordinary fuzzy controller and the steady precision of PID controller. The experiment results show the dynamic and static performance of the proposed fuzzy-PID controller are all excellent, the overshoot is zero, the speed respond is fast and the static precision is high, better than the conventional PID controller and the conventional fuzzy controller in speed control.

Oscillation mitigation in subsurface and surface couplings using PID controllers

Due to the increasing cost of fossil fuels and other non-renewable resources, Environmental conditions and higher capacity accumulator's transformation method has been changing day by day. Though modern controllers are adopted in Electric vehicles, the primary source of battery which causes error and need to enhance the parameters. In this paper, an Improvement of the dynamic performance of the Battery Electric drive is presented. Here DC-DC Converter with different topologies has been compared for the performance of Electric Vehicles. Battery current ripples and converter losses which creates problem in Electric vehicles. Hence Improved SEPIC Converter is designed for the improvement of Electric vehicles. The Conventional linear controllers such Proportional Integral and Derivative (PID) which require analytical modeling system. Besides a Digital Controller FPGA is complete opposite PID which is based trial and error method, and doesn't include any mathematical analyze modeling of the system. However the FPGA is more sturdy (tough), has more strong study state response, and it is able to attain transient and steady state response as compared to PID controllers. The above approach is applied and experimented with simulation software for the performance the SEPIC (DC to DC converter) is discussed here in this research. Finally, the investigations of selected drive performance such as Battery Voltage, Current, Ultra Capacitor current and PID Controllers parameters and digital controllers Evaluation Parameters are presented here.

In this paper, a framework to automatically generate a set of parameters of PID (proportional, integral and derivative) controllers for the twin rotor multi-input multi-output system (TRMS) by using a simplified genetic algorithm (GA) is proposed. The simplified GA is proposed for tuning the PID parameters. The sequential search method is used to find the desired crossover point for the crossover operation. Finally, the optimal PID parameters are applied to the TRMS. Simulation results and experimental verification are demonstrated to show the effectiveness and performance of the proposed method.

This paper presents the design of a robust proportional integral and derivative (PID) controller for a first-order lag with pure delay (FOLPD) model using particle swarm optimization (PSO)-enabled automated quantitative feedback theory (QFT). The plant model considered here can be approximated as a first-order system with a non-minimum phase (NMP) zero. Synthesis of controller for the FOLPD model via manual graphical technique involved in the QFT method is always a challenging and cumbersome task, because an NMP system stabilizes by a small gain. In this paper, a proposal is being presented to automate the loop-shaping phase in the QFT design method to synthesize a robust controller that can undertake the exact amount of plant uncertainty even in the presence of larger uncertainties than those assumed initially and can ensure a proper trade-off between robust stability and tracking performance specifications over the entire range of design frequencies. In this paper,s the PSO technique has been employed to tune the controller automatically,which can significantly reduce the computational effort compared with manual graphical techniques. It has also been demonstrated that this methodology not only automates loop shaping but also improves design quality and, most usefully, improves performance with optimally tuned PID controller in quantitative manner.

The present paper proposes a system based on the usage of Proportional, Integral and Derivative (PID) Control for stabilizing a quadcopter attached to a metal base. A smartphone Graphic User Interface (GUI) was created so the user can adjust manually, or automatically, the three gains that are characteristic of this type of control (proportional, integral and derivative gains). This system is intended to be seen as an educational concept for exploring PID Control. The user can change each of the three PID gain values and observe what are the consequences reflected on the behavior of the system. To test the latter, an attempt of tuning the three gains in order to stabilize the quadcopter was performed. The system reacted as expected, taking into account the theoretical knowledge about each of the PID gains and their influence on the system response. Overall, the final outcome of this work is an educational tool, designed and implemented by students in a compulsory curricular unit, which allows the user to understand how a PID controller works in an intuitive and practical way.

Fuzzy PID supervised online ANFIS based speed controller for brushless dc motor

This paper presents a recurrent fuzzy neural network (RFNN) controller to provide sensorless speed control for the two-phase linear brushless DC motor. It is not easy to arrange current and speed sensors along the linear motor's required railway. The RFNN controller has the capability of tracing the system dynamics due to the inherent learning function. With the help of RFNN controller, the conventional PID control can be made to provide better performance by tracing the system dynamics. The paper will demonstrate dynamic performance improvement scenarios. The recurrent structure also enhances the conventional fuzzy neural network (FNN) controller with embedded memory function. The results from experimental evaluation indicate that the PID with RFNN controller can provide better performance than the conventional PID controller.

Electromagnetic tomography (EMT) uses the mutual inductance of the coil to visualise the conductivity distribution of interesting regions. Since the conductivity of defects and metal samples are different, the metal samples with defects can be treated as binary-valued material distributions. This paper investigates the closed-loop fuzzy proportional, integral and derivative (PID)-controlled iterative Landweber method. The whole method includes fuzzy PID controller, the Landweber reconstruction method, and the Dirichlet-to-Neumann map. Specifically, the differential signal between the mutual inductance of the coil and the feedback signal is used as the input of the fuzzy PID controller. The fuzzy controller can automatically adjust three parameters ( K p , K i and K d ) of PID controller. Subsequently, the output of the PID controller can serve as the input of the Landweber algorithm to reconstruct the distribution of conductivity. Furthermore, the Dirichlet-to-Neumann map is used to calculate the mutual inductance, acting as the feedback signal based on the reconstruction conductivity distribution. Finally, both the numerical simulation and experiments are applied to verify the proposed method. The results indicate that the proposed method can reconstruct the image with a clear edge, and the average correlation coefficient can reach 0.792.

This paper presents the system identification and design of a neural network based Proportional, Integral and Derivative (PID) controller for a two degree of freedom (2DOF), quarter-car active suspension system. The controller design consists of a PID controller in a feedback loop and a neural network feedforward controller for the suspension travel to improve the vehicle ride comfort and handling quality. Nonlinear dynamics of the servo-hydraulic actuator is incorporated in the suspension model. A SISO neural network (NN) model was developed using the input-output data set obtained from the mathematical model simulation. Levenberg-Marquardt algorithm was used to train the NN model. The NN model achieved fitness values of 99.98%, 99.98% and 99.96% for sigmoidnet, wavenet and neuralnet neural network structures respectively. The proposed controller was compared with a constant gain PID controller in a suspension travel setpoint tracking in the presence of a deterministic road disturbance. The NN-based PID controller showed better performances in terms of rise times and overshoots.

Objectives: To improve the closed loop response by means of reducing the rise time, settling time and overshoots by implementing a suitable method. Methods/Statistical Analysis: Three different higher order transfer functions has been considered for analysis and are approximated to First Order Plus Dead Time models (FOPDT) using process reaction curve method by applying unit step change. Particle Swarm Optimization technique; and Internal Model Control (IMC) method are used to tune Proportional, Integral and Derivative (PID) control values. Findings: The new method, Error Recursive Reduction Computational (ERRC) method has been tested on higher order systems. The proposed method ERRC is merged with PSO based PID and IMC based PID controllers in hybrid form to form new control structure. Comparative analysis was carried out between with ERRC and without ERRC. Application/Improvements: It can be applied to feedback control system i.e., feedback control applications are highly influenced in chemical, manufacturing automobile industries and etc. Keywords: Higher Orders Systems, Modeling, PID Control, Recursive Analysis, Self Regulating Process

A genetic algorithm (GA) based recurrent fuzzy neural network (RFNN) is proposed to control the mover of a linear induction motor (LIM) servo drive for periodic motion in this paper. The GA is developed to search the optimal weights between the membership layer and the rule layer of RFNN. First, the dynamic model of an indirect field‐oriented LIM servo drive is derived. Then, an on‐line training RFNN with backpropagation algorithm is introduced as the tracking controller. Moreover, to guarantee the global convergence of tracking error, analytical methods based on a discrete‐type Lyapunov function are proposed to determine the varied learning rates of the RFNN. In addition, a real‐time GA is developed to search the optimal weights between the membership layer and the rule layer of RFNN on‐line. The theoretical analyses for the proposed GA‐based RFNN controller are described in detail. Finally, simulated and experimental results show that the proposed controller provides good control performance dynamic characteristics and is robust with regard to plant parameter variations and external load disturbance.