Neural Network PID Controller Research Articles

Hybrid intelligent control scheme of a polymerization kettle for ACR production

Polymerization kettle is the key controlled plant in ACR (Acrylate Copolymer Resin) production, which is a nonlinear time-delay system with parametric variance. However, modeling difficulties make the plant dynamic model poorly defined. A hybrid intelligent control scheme including an intelligent predictor is designed for this complex plant based on time-delay compensation theory. It consists of a Smith neural-network predictor and a self-adjusting-scaling-factor fuzzy logic controller. The simulation experiments verified the performance of our proposed system in two scenarios: one with invariant parameters and the other with time-varying parameters. Moreover, the comparison to other three typical control methods including Smith PID, Smith neural-network PID and Smith fuzzy logic control is also presented, which demonstrates that the proposed control scheme has satisfactory effect. Even when the system parameters vary with time, the proposed system still gives superior performance and improved robustness.

Evaluation and Development of Advance Control Strategies Which Uses Pattern Recognition Technique for Nonlinear System

A general controller evaluation method is introduced, based on robustness criteria of well-known PID Controller formulate for process of non-linear systems using experimental of coefficients for flank wear of dynamic models obtained are calibrated with the actual conditions. These developed models will be used for the simulation of flank wear and using control variable such as cutting speed; the flank wear will be controlled. For model validation, the flank wear is estimated using a non-linear model. In the present work, an attempt has been made to control the flank wear during turning of on-line cutting process using the Fuzzy Logic Controller and Neural network based on self-tuning of PID controller approaches. Those approaches are treat the material as dynamic system and involve developing state space models from available material behavior model. The evaluation of performance criteria can be compared for those approaches of PI controller with Neural network and Fuzzy PID controller based on self-tuning of PID controller. Simulation studies are carried-out for the non-linear system using MATLAB software.

Methods of Hardware and Software Realization of Adaptive Neural Network PID Controller on FPGA-Chip

Methods of Hardware and Software Realization of Adaptive Neural Network PID Controller on FPGA-Chip

PID Neural Network Based Speed Control of Asynchronous Motor using Programmable Logic Controller

This paper deals with the structure and characteristics of PID Neural Network controller for single input and single output systems. PID Neural Network is a new kind of controller that ...

Dynamic Modeling and Neural Network Self‐tuning PID Control Design for a Linear Motor Driving Platform

AbstractThe purpose of this paper is to design a wavelet neural network self‐tuning proportional–integral–derivative (PID) controller for solving the problem of fast changing payload in a linear motor in the 6‐DOF platform system. The wavelet neural network PID controller demonstrates the special capabilities of fast response and self‐tuning. A practical system identification method is proposed to identify the dynamic model of a linear motor by using the balancing realization theorem and inverse discrete Fourier transform. The experimental results of the real‐time software simulation and hardware‐in‐the‐loop simulation demonstrate the novel ability of self‐tuning PID controller for adapting the quick load change in the forcer of linear motor, which activates the platform system. Copyright © 2010 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

P-CMAC-Based Control Method and its Application in Filament Tension Control

Cerebella Model Articulation Controller (CMAC) is considered as local association and generalization neural network. Parametric CMAC (P-CMAC) is a modification to the original CMAC. The introduction of continuous activation function applied in the input space can overcome the binary behavior of the original CMAC. Takagi-Sugeno(TS) type fuzzy inference is embedded in the internal mapping to improve the approximation accuracy. Hybrid control scheme, which combines P-CMAC neural network and traditional PID controller, is proposed in the paper. The output of P-CMAC network dominates the overall control signal applied to the plant, while the traditional PID controller serves as compensator for reducing tracking error. The application of hybrid control scheme to filament tension control is illustrated. The experimental results have shown the effectiveness and accuracy improvement of the control scheme.

The Electro-Hydraulic Proportional Control and Simulation of the Radial Piston Pump Based on Proportional-Integral-Derivative Neural Network

In this paper a new control method has been studied in which PID control system was integrated into the neural network. It could overcome some disadvantages such as neural network’s slow rate of convergence and PID’s difficulty in application of multivariate nonlinear systems. A controller of the Electro-hydraulic proportional control stroking mechanism for radial piston pump was designed based on the PID neural network control algorithm. The system responses of system variable control signal of system track were achieved by computer simulation. It was found by PIDNN that the control system could reach steady state in a shorter time, compared with PID control system response time by 65% to 80%. The simulation results showed that the controller for the Electro-hydraulic proportional Radial Piston Pump based PID neural network control algorithm would have a good controlling performance.

An intelligent control strategy for plasma arc cutting technology

Adopting digital inverted plasma arc cutting power as a platform and focusing on its strong nonlinearity and time-varying property, this paper puts forward a variable interval fuzzy-PI quantification algorithm with a self-adjustable factor in the full domain. The introduction of the PID neural network is for decoupling parameter variables in the multi-parameter coupling cutting process. This algorithm reduces the complex nonlinear system modeling and realizes real-time and effective online control for the cutting process by combining the advantages of fuzzy control and PID neural network control. Furthermore, the optimized fuzzy control improves the steady-state precision and the dynamic performance of the system simultaneously. The experimental result shows that this control improves the precision, ripples, finish and other comprehensive indexes of the workpiece compared with conventional PI control, and the plasma arc cutting power supply based on the fuzzy-neural network has excellent control performance.

PID neural network control of a membrane structure inflation system

Because it is difficult for the traditional PID algorithm for nonlinear time-variant control objects to obtain satisfactory control results, this paper studies a neuron PID controller. The neuron PID controller makes use of neuron self-learning ability, complies with certain optimum indicators, and automatically adjusts the parameters of the PID controller and makes them adapt to changes in the controlled object and the input reference signals. The PID controller is used to control a nonlinear time-variant membrane structure inflation system. Results show that the neural network PID controller can adapt to the changes in system structure parameters and fast track the changes in the input signal with high control precision.

Driving and control of torque for direct-wheel-driven electric vehicle with motors in serial

The utilization of motor-in-wheel in the electric vehicle (EV) is a very important research topic. In order to simplify the control of EV, a new system is proposed by Guilin Tao, which changes the traditional configuration and control strategy of direct-wheel-driven EV. In this system two permanent-magnet-brushless dc motors (PMBDCMs) are connected directly in serial, in order to cut down the differential algorithm thoroughly in velocity control strategy. This structure can realize the differential automatically when the EV runs on the smooth road at low speed. But this structure considers the characters of the motor only, which is an ideal system. EV is a complex electromechanical system, and its work condition is also complex. The variation of the external condition and the work condition of operation can affect the operation of motor, so the state of the EV will change. In this paper, according to the change of the work condition and road condition, combined with the dynamics of EV, this problem was well studied. The neural network PID control mode was used in this paper, and by means of the Matlab/Simulink and the experimental verification, it reveals that this method can enhance the safety and stability of this system.

Research and Implementation of the Temperature Control System for the Sintering Shaft Furnace

This paper describes the implementation of the temperature control system for sintering shaft furnace. In order to solve the problems caused by pure time-delay and non-linearity, an intelligent serial temperature control system is introduced in this paper, where the fuzzy controller is used in the main control loop and the fuzzy neural network PID controller is adopted in auxiliary loop. Simulation results show that this system is stable and has stronger anti-interference capability. Finally, the hardware and software implementation methods for the firebox temperature control system are introduced. The real production results demonstrate that production requirements are met and better control effects are obtained. The aim of energy saving and consumption reduction and quality improvement is achieved.

The application of the self-tuning neural network PID controller on the ship roll reduction in random waves

In this paper, we present a mathematical model including seakeeping and maneuvering characteristics to analyze the roll reduction for a ship traveling with the stabilizer fin in random waves. The self-tuning PID controller based on the neural network theory is applied to adjust optimal stabilizer fin angles to reduce the ship roll motion in waves. Two multilayer neural networks, including the system identification neural network (NN1) and the parameter self-tuning neural network (NN2), are adopted in the study. The present control technique can save the time for searching the optimal PID gains in any sea states. The simulation results show that the present developed self-tuning PID control scheme based on the neural network theory is indeed quite practical and sufficient for the ship roll reduction in the realistic sea.

Study on Improved Neural Network PID Control for Coal Mining Power Grid Arc Suppression Coil Compensating System

The paper analyzed arc suppression coil with magnetic bias compensating system with linear system rules. The nonlinear and time-variable performances are considered during model building process. In order to optimize control effect, the paper adopted improved BP neural network PID controller with closed loop control method. Improve BP neural network with the combination of the two strategies, adding momentum method and adaptive learning rate adjustment, can not only effectively suppress the network appearing local minimum but also good to shorten learning time and improve stability of the network furthermore. The results of simulation and experiments indicate that arc suppression coil based on improved neural network with PID control method can quickly and accurately control the compensating capacitive current to an expected value and it has strong robustness. The paper also provided core controller with software and hardware designing scheme based on STM32 microcontroller.

Neural network PID control for a water level system

Water level system is a classic device for the research of non-linear system control. It is always represented by a First-Order plus Dead Time (FOPDT) model around the equilibrium point. Based on the water level system, different PID strategies (empirical method and Ziegler-Nichols method) are studied for the improvement of control performance. Optimised by gradient descent method, a PID controller based on a radial based function (RBF) neural network is given and applied to an actual A3000 three-tank water level system. From the experiment result, the effectiveness of the proposed method is tested.

Control of Heat Transfer in Continuous Casting Process Using Neural Networks

摘要: In continuous casting, the cooling-solidification process must be based on the adaptation of heat transfer, which is directly connected to casting conditions such as casting speed, casting temperature, and cooling parameters. Most control schemes are based on the static relation between casting speed and water flow rate in each cooling zone; this constitutes an open loop that does not consider the dynamic surface temperature, which is an important parameter for the final slab quality. In steelmaking, the casting-speed changes affect the global heat transfer. An optimal operation requires an adjustment of the process control variables, i.e., global heat transfer. A learning neural network (NN) allows the identification and the control of a nonlinear heat transfer model in the continuous casting process. A heat transfer model was developed using the dynamic heat balance. A comparison between the experimental open loop results and those of the model simulation is considered. Following adaptation, the model is used for controlling the slab surface temperature in closed loop, using NN technology and PID controllers. The NN identification and control strategy gives a stable temperature closed loop control comparatively to the conventional PID. 关键词: Neural networks / identification / control / heat transfer / continuous casting

Control of Heat Transfer in Continuous Casting Process Using Neural Networks

In continuous casting, the cooling-solidification process must be based on the adaptation of heat transfer, which is directly connected to casting conditions such as casting speed, casting temperature, and cooling parameters. Most control schemes are based on the static relation between casting speed and water flow rate in each cooling zone; this constitutes an open loop that does not consider the dynamic surface temperature, which is an important parameter for the final slab quality. In steelmaking, the casting-speed changes affect the global heat transfer. An optimal operation requires an adjustment of the process control variables, i.e., global heat transfer. A learning neural network (NN) allows the identification and the control of a nonlinear heat transfer model in the continuous casting process. A heat transfer model was developed using the dynamic heat balance. A comparison between the experimental open loop results and those of the model simulation is considered. Following adaptation, the model is used for controlling the slab surface temperature in closed loop, using NN technology and PID controllers. The NN identification and control strategy gives a stable temperature closed loop control comparatively to the conventional PID.

Self-Tuning Pid Neural Network Controller to Control Nonlinear Ph Neutralization in Waste Water Treatment

The conventional PID control (linear) is popular control scheme that is used in almost pH control at waste water treatment process. pH model with respect to titration liquid flow rate has been known to be intrinsically difficult and nonlinear, especially when the process is conducted to non-linear range pH reference (pH 4-8), the settling time reach a long time. Therefore in this paper the nonlinear controller with self-tuning PID scheme is performed handle pH by training a neural-network based on backpropagation error signals. The pH process model is combination between CSTR (Continuous Stirred Tank Reactor) linear dynamic with H3PO4, HF, HCl, H2S flow rate and nonlinear static electro neutrality (wiener process model). The simulation result has a good and suitable performance under several tests (set-point and load change). The simulation result show the pH control system can follow the change of pH set-point and load with the average steady state error 0.00034. The settling time achieved at 50 second faster than conventional PID controller scheme.

신경망을 이용한 엔진/브레이크 통합 VDC 시스템에 관한 연구

This paper presents a engine/brake integrated VDC(Vehicle Dynamic Control) system using neural network algorithm methods for wheel slip and yaw rate control. For stable performance of vehicle, not only is the lateral motion control(wheel slip control) important but the yaw motion control of the vehicle is crucial. The proposed NNPI(Neural Network Proportional-Integral) controller operates at throttle angle to improve the performance of wheel slip. Also, the suggested NNPID controller performs at brake system to improve steering performance. The proposed controller consists of multi-hidden layer neural network structure and PID control strategy for self-learning of gain scheduling. Computer Simulation have been performed to verify the proposed neural network based control scheme of 17 dof vehicle dynamic model which is implemented in MATLAB Simulink.

GA-based PID neural network control for magnetic bearing systems

In order to overcome the system non-linearity and uncertainty inherent in magnetic bear-ing systems,a GA(genetic algorithm)-based PID neural network controller is designed and trained to emulate the operation of a complete system (magnetic bearing,controller,and power amplifiers). The feasibility of using a neural network to control nonlinear magnetic bearing systems with un-known dynamics is demonstrated. The key concept of the control scheme is to use GA to evaluate the candidate solutions (chromosomes),increase the generalization ability of PID neural network and avoid suffering from the local minima problem in network learning due to the use of gradient descent learning method. The simulation results show that the proposed architecture provides well robust performance and better reinforcement learning capability in controlling magnetic bearing systems.

A neural network based controller for a wheel type mobile robot

The transportation using wheels is one of the most popular transportation mechanisms for mobile robots because of its high energy efficiency, simple mechanisms and well-investigated control systems. However, the wheel type mobile robots have the biggest weakness in the rough terrain movement. In the previous researches, a six-wheeled mobile robot employing a linkage mechanism, “Zaurus”, has been developed to extend maneuverability of the conventional wheel type mobile systems. The experiments to climb over single bumps with twice the height of diameter of the robot's wheel have been carried out and succeeded. In this paper, a neural network controller and PID controller are introduced as the control system, and their performances are compared by simulations. The neural network controller shows superior filtering and feature extraction capabilities.