Neural Network Inverse Control Research Articles

Observer-based adaptive neutral network inverse optimal containment control for nonlinear multiagent systems with input quantization

This article focuses on the issue of addressing an adaptive neural network (NN) inverse optimal containment control for nonlinear multiagent systems (MASs), which are subject to immeasurable states and quantized input signals simultaneously. To tackle this problem, we utilize a NN to model unknown agents and design a NN observer to estimate the immeasurable states. Additionally, we decompose the hysteretic quantized input into two bounded nonlinear functions. By employing the adaptive backstepping approach and inverse optimal principle, we formulate an adaptive NN inverse optimal containment control method. The developed inverse optimal containment control scheme guarantees that the controlled system is input-to-state stabilizable (ISS). Finally, we validate the effectiveness of our proposed control scheme through simulation results.

Reduction of emissions and improvement of dynamic responses of a supercritical clean coal generation unit via neural network inverse control strategy

Coal power plants have been a major source of undesirable emissions. Despite the technological advancements in renewable energies, coal units are still in-service in many developed and developing countries due to their reliability, adequacy, and flexibility for power delivery. There are some promising technologies for cleaner operation during power production from coal, including supercritical boiler (SC) design and carbon capture and storage (CCS), however, the challenging in innovating effective methods is still open to expand the boundary of knowledge in this speciality. This paper introduces a novel and simple method for reducing CO2 emissions and improving the dynamic responses of a 600 MW SC coal power plant by Artificial Neural Network (ANN) technique. A wide-range data-driven feedforward ANN model has been identified and verified for the various operations recorded as closed-loop data-sets, which covers all situations of startup, once-through mode, and even emergency shutdown of the unit. The closed-loop SC plant model has been augmented with an inverse multivariable coordinate NN controller, developed by analogous learning algorithm to improve the plant automation. With precisely selected setpoints, as operational rules, of temperature, pressure, and earliest possible power demand signals, the automated SC plant has been capable to operate with lower coal consumption - and thus lower emissions – than the existing operation strategy during startup, normal operation, and emergency shutdown modes. The improvement in dynamic responses have been quantified through simulations with comparison with existing performance, which have resulted in an overall average reduction of 2.143 Kg/s in coal consumption.

GRNN inverse system based decoupling control strategy for active front steering and hydro-pneumatic suspension systems of emergency rescue vehicle

Aiming at eliminating the mutual interference and coupling between the active front steering (AFS) and hydro-pneumatic suspension (HPS) subsystems of the emergency rescue vehicle, this paper presents a neural network inverse system based decoupling control strategy, which consists of the neural network inverse system and PID feedback control strategy. At first, a three-degrees of freedom dynamics model of the vehicle is constructed, and the reversibility of the vehicle chassis system is analyzed by the Interactor algorithm. Then, the generalized regression neural network (GRNN) model is used to identify the vehicle chassis inverse system, which decouples the multivariable vehicle chassis system into two independent single input and single output systems. Next, this paper proposes a closed-loop compound controller for the single input and single output systems, which is designed based on the PID control strategy and GRNN inverse system to realize the feedback control of the vehicle chassis system, so that the vehicle can track the desired yaw rate and roll angle well. Simulations and experiments are conducted on the self-developed fire rescue prototype vehicle, and the results prove that the proposed decoupling control strategy can not only eliminate coupling between AFS and HPS subsystems of the vehicle chassis, but also make the vehicle have better handling stability than controlled by the integrated control.

Disturbance rejection based on iterative learning control with extended state observer for a four-degree-of-freedom hybrid magnetic bearing system

Iterative learning control (ILC) is an iterative control strategy which calculates a new input according to the error in previous cycles. It is widely used in industries with repetitive operations. Since magnetic bearing systems can be considered as running in a repetitive task, the ILC could be applied. Hence, this paper proposes a modified iterative learning control (ILC) strategy for a four degree-of-freedom (DOF) hybrid magnetic bearing system to reject the disturbance based on an extended state observer (ESO). The feasibility of applying the ILC to the four-DOF magnetic bearing system is analyzed firstly. It is proved that the tracking error can converge by selecting suitable controller parameters. Secondly, to accurately obtain the uncertainties in the operation process, an ESO is designed. As for a repetitive rotation process, the iteration variant disturbance may have a certain influence on the performance of the system which is not usually considered. Therefore, the iteration variant disturbance is introduced and the effectiveness is derived. Finally, simulations and experiments are carried out to demonstrate the effectiveness of the proposed method. The classical proportion-integration-differentiation (PID) control and an existing proposed neural network inverse (NNI) control are implemented for comparison. The results show that the proposed strategy can achieve better reference tracking and disturbance suppression ability than PID and NNI control.

A Comparative Study of the UPFC System by Simulation with PI-D and (NEWELM and NIMC) Controllers Based on the Adaptive Control for the Compensation of Power

-Flexible Alternating Current Transmission System devices (FACTS) are power electronic components. Their fast response offers potential benefits for power system stability enhancement and allows utilities to operate their transmission systems even closer to their physical limitations, more efficiently, with improved reliability, greater stability and security than traditional mechanical switching technology. The unified Power Flow Controller (UPFC) is the most comprehensive multivariable device among the FACTS controllers. According to high importance of power flow control in transmission lines, new controllers are designed based on the Elman Recurrent Neural Network (NEWELM) and Neural Inverse Model Control (NIMC) with adaptive control. The Main purpose of this paper is to design a controller which enables a power system to track reference signals precisely and to be robust in the presence of uncertainty of system parameters and disturbances. The performances of the proposed controllers (NEWELM and NIMC) are based neural adaptive control and simulated on a two bus test system and compared with a conventional PI controller with decoupling (PI-D). The studies are performed based on well known software package MATLAB/Simulink tool box.

Flexible operation of large-scale coal-fired power plant integrated with solvent-based post-combustion CO2 capture based on neural network inverse control

Post-combustion carbon capture (PCC) with chemical absorption has strong interactions with coal-fired power plant (CFPP). It is necessary to investigate dynamic characteristics of the integrated CFPP-PCC system to gain knowledge for flexible operation. It has been demonstrated that the integrated system exhibits large time inertial and this will incur additional challenge for controller design. Conventional PID controller cannot effectively control CFPP-PCC process. To overcome these barriers, this paper presents an improved neural network inverse control (NNIC) which can quickly operate the integrated system and handle with large time constant. Neural network (NN) is used to approximate inverse dynamic relationships of integrated CFPP-PCC system. The NN inverse model uses setpoints as model inputs and gets predictions of manipulated variables. The predicted manipulated variables are then introduced as feed-forward signals. In order to eliminate steady-state bias and to operate the integrated CFPP-PCC under different working conditions, improvements have been achieved with the addition of PID compensator. The improved NNIC is evaluated in a large-scale supercritical CFPP-PCC plant which is implemented in gCCS toolkit. Case studies are carried out considering variations in power setpoint and capture level setpoint. Simulation results reveal that proposed NNIC can track setpoints quickly and exhibit satisfactory control performances.

Robust stability power in the transmission line with the use of a UPFC system and neural controllers based adaptive control

The main purpose of this paper is to design a regulator which enables a power system to track reference signals precisely and to be robust in the presence of uncertainty of system parameters and disturbances. The performances of the proposed controllers (NEWELM and NIMC) are based neural adaptive control and simulated on a two-bus test system and compared with a conventional PI controller with decoupling (PI-D). The studies are performed based on well known software package MATLAB/Simulink tool box. Flexible Alternating Current Transmission System devices (FACTS) are power electronic components. Their fast response offers potential benefits for power system stability enhancement and allows utilities to operate their transmission systems even closer to their physical limitations, more efficiently, with improved reliability, greater stability and security than traditional mechanical switching technology. The most used component of FACTS systems is the Unified Power Flow Controller (UPFC). According to high importance of power flow control in transmission lines, new controllers are designed based on the Elman Recurrent Neural Network (NEWELM) and Neural Inverse Model Control (NIMC) with adaptive control.

Neural network based controllers for the oil well drilling process

The oil well drilling is a complex process, requiring that the bottomhole pressure be maintained within an operational window, limited by fracture pressure and pore pressure (and/or wellbore collapse). During the drilling process, there are several phenomena that directly influence the annulus bottomhole pressure: kick, lost circulation, inefficient removal of solids, well length increase, reservoir parameters and pipe connection procedure (surge and swab effects). The main objective of this work is to develop neural network controllers able to regulate the annulus bottomhole pressure under pipe connection procedure, kick and lost circulation disturbances. For this purpose, an experimental drilling unit was built, depicting the oil well drilling process primordial characteristics. Besides, real oil well offshore data were employed for validating the neural network controllers. Neural networks were built for predicting the direct plant dynamics (inverse neural network controller) and the inverse plant dynamics (direct neural network controller). It is noteworthy to mention that direct plant dynamics neural modelling was employed as the nonlinear model of a gain scheduling control approach; in addition, the inverse plant dynamics neural modelling constituted a nonlinear controller, directly predicting the manipulated variable. Both controllers employed real-time neural network training, being, therefore, adaptive schemes for regulating the oil well drilling process, which nature is inherently transient.

Adaptive Inverse Neural Network Based DC Motor Speed and Position Control Using FPGA

In this research two types of controllers are designed in order to control the speed and position of DC motor. The first one is a conventional PID controller and the other is an intelligent Neural Network (NN) controller that generate a control signal DC motor. Due to nonlinear parameters and movable laborers such saturation and change in load a conventional PID controller is not efficient in such application; therefore neural controller is proposed in order to decreasing the effect of these parameter and improve system performance. The proposed intelligent NN controller is adaptive inverse neural network controller designed and implemented on Field Programmable Gate Array (FPGA) board. This NN is trained by Levenberg-Marquardt back propagation algorithm. After implementation on FPGA, the response appear completely the same as simulation response before implementation that mean the controller based on FPGA is very nigh to software designed controller. The controllers designed by both m-file and Simulink in MATLAB R2012a version 7.14.0.

Decoupling control of a five-phase fault-tolerant permanent magnet motor by radial basis function neural network inverse

This paper proposes a new decoupled control for a five-phase in-wheel fault-tolerant permanent magnet (IW-FTPM) motor drive, in which radial basis function neural network inverse (RBF-NNI) and internal model control (IMC) are combined. The RBF-NNI system is introduced into original system to construct a pseudo-linear system, and IMC is used as a robust controller. Hence, the newly proposed control system incorporates the merits of the IMC and RBF-NNI methods. In order to verify the proposed strategy, an IW-FTPM motor drive is designed based on dSPACE real-time control platform. Then, the experimental results are offered to verify that the d-axis current and the rotor speed are successfully decoupled. Besides, the proposed motor drive exhibits strong robustness even under load torque disturbance.

A Low-Cost Maximum Power Point Tracking System Based on Neural Network Inverse Model Controller

This work presents the design, modeling, and implementation of a neural network inverse model controller for tracking the maximum power point of a photovoltaic (PV) module. A nonlinear autoregressive network with exogenous inputs (NARX) was implemented in a serial-parallel architecture. The PV module mathematical modeling was developed, a buck converter was designed to operate in the continuous conduction mode with a switching frequency of 20 KHz, and the dynamic neural controller was designed using the Neural Network Toolbox from Matlab/Simulink (MathWorks, Natick, MA, USA), and it was implemented on an open-hardware Arduino Mega board. To obtain the reference signals for the NARX and determine the 65 W PV module behavior, a system made of a 0.8 W PV cell, a temperature sensor, a voltage sensor and a static neural network, was used. To evaluate performance a comparison with the P&O traditional algorithm was done in terms of response time and oscillations around the operating point. Simulation results demonstrated the superiority of neural controller over the P&O. Implementation results showed that approximately the same power is obtained with both controllers, but the P&O controller presents oscillations between 7 W and 10 W, in contrast to the inverse controller, which had oscillations between 1 W and 2 W.

Neural Network Based Modeling and Control for a Batch Heating/Cooling Evaporative Crystallization Process

Crystallization processes have been widely used for separation in many fields to provide a high purity product. In this work, dynamic optimization and neural network (NN) have been applied to improve the quality of the product: citric acid. In the dynamic optimization, optimization problems maximizing both crystal yield and crystal size have been formulated. The neural networks have been developed to provide NN models to be used in the formulation of not only neural network inverse control (NNDIC) but also neural network model predictive control (NNMPC) strategies. The Levenberg Marquadt algorithm has been used to train the network and optimal neural network architectures have been determined by a mean squared error (MSE) minimization technique. In addition, a neural network model has been designed to provide estimates of the temperature and the concentration of the crystallizer. These estimates have been incorporated into the NNMPC controller. In the NNDIC controller, another neural network model has been applied to predict the set point of jacket temperature. The simulation results have shown that the obtained crystal size is increased by 19% and 30% compared to that by cooling and evaporation methods respectively and the obtained yield is increased more than 50%. The robustness of the proposed controller is investigated with respect to parameters mismatches. The results have shown that the NNMPC controller provides superior control performances in all case studies.

INTELLIGENT CONTROLLERS FOR VELOCITY TRACKING OF TWO WHEELED INVERTED PENDULUM MOBILE ROBOT

Velocity tracking is one of the important objectives of vehicle, machines and mobile robots. A two wheeled inverted pendulum (TWIP) is a class of mobile robot that is open loop unstable with high nonlinearities which makes it difficult to control its velocity because of its nature of pitch falling if left unattended. In this work, three soft computing techniques were proposed to track a desired velocity of the TWIP. Fuzzy Logic Control (FLC), Neural Network Inverse Model control (NN) and an Adaptive Neuro-Fuzzy Inference System (ANFIS) were designed and simulated on the TWIP model. All the three controllers have shown practically good performance in tracking the desired speed and keeping the robot in upright position and ANFIS has shown slightly better performance than FLC, while NN consumes more energy.

Comparison of Control Strategies Applied to Nonlinear Quarterly Car Passive Suspension System

Road unevenness causes wheel and engine vibration which in turn lead to internal noise in automobiles. Developing a reliable control algorithm for vehicle suspension system is quite cumbersome due to the nonlinear nature of the system coupled with the issue of improving compromise between the conflicting demands of ride comfort and road handling. This paper presents a comparison of Fuzzy, Neural Network (NN) inverse control and Nonlinear Proportional Integral Derivative (NPID) control applied to the quarterly car passive suspension system. The performances of the controllers were evaluated based on rise time, settling time and peak time as illustrated via set-points tracking. The simulation results indicated that the performances of the Fuzzy controller and NPID are slightly better than neural network inverse control which could be due to lack of obtaining an accurate inverse plant model. The Fuzzy controller and NPID may serve as an alternative and valuable control schemes for the system

Neural-network-based composite disturbance rejection control for a distillation column

Binary distillation columns are essentially multi-variable systems with couplings, non-minimum phase characteristics, model mismatches and various external disturbances. To get the desired top (distillate) and bottom product composition, a composite disturbance rejection control strategy using a radial basis function network (RBFN) is proposed in this paper. The composite controller includes neural network inverse controller (NNIC) and neural network disturbance observer (NNDOB) both using the inverse model of system which is identified by the RBFN. The stability of the identified inverse model is proved, and a rigorous analysis is also given to show why the NNDOB can effectively suppress the disturbances. Performances of the proposed scheme are compared with PID and NNIC without disturbance compensation in three cases by simulation studies. The simulations demonstrate the feasibility, effectiveness and disturbance rejection property of the proposed method in controlling the product composition of the binary distillation columns.

Design and implementation of an Inverse Neural Network Controller applied To VSC Converter for active and reactive Power Flow, based on regions of work

Voltage Source Converter (VSC) usually used in High Voltage Direct Current (HVDC) systems, where a VSC can be used as inverter or rectifier. VSC systems allow the independent control of active or reactive power flow using different techniques. VSC systems present nonlinear behaviors, multiple inputs and multiple outputs, therefore nonlinear controllers can be used to obtain an adequate behavior. Inverse Neural Control is an alternative of an intelligent control since a mathematical model of the system is not required for designing controllers. Additionally, Inverse Neural Control can easily manage uncertainties and nonlinear behaviors typically presented in VSC systems. In this paper are presented the design, simulation and implementation of an Inverse Neural Control applied to the control of active and reactive power flow in a VSC system. Initially, is presented the simulation of the controller, where is evaluated the behavior of the system using a MIMO controller for the control of two parameters in the same time. Subsequently, the implementation of the controller is done and the e obtained is presented. Finally, a modular Inverse Neural Network Control is proposed to overcome the drawbacks presented in the behavior of the system when it was controlled in real implementation.

Delay Separated Neural Network Inverse Control in Main-Steam Temperature System

Delay Separated Neural Network Inverse Control in Main-Steam Temperature System

RBFNDOB-based neural network inverse control for non-minimum phase MIMO system with disturbances

An adaptive control strategy combining neural network inverse controller (NNIC) with RBFN disturbance observer (RBFNDOB) is developed for a multi-input-multi-output (MIMO) system with non-minimum phase, internal and external disturbances in this paper. Since the inverse model of system is unstable due to the non-minimum phase, a pseudo-plant is constructed, then the RBFN is used to identify the inverse model of pseudo-plant, which can track the parameter variations of system. By copying the structure and parameters of the identifier, the NNIC is obtained. Cascading the NNIC with the original plant, the MIMO system can be decoupled and linearized into independent SISO systems. For the independent decoupled system, the RBFNDOB employs a RBFN to observe the external disturbances and this estimate value is used as a feed-forward compensation term in controller. The case study on ball mill grinding circuit is presented. The effectiveness of the proposed method is demonstrated by simulation results and comparisons.

Delay Separated Neural Network Inverse Control in Main-Steam Temperature System

In order to improve the control effect of the main steam temperature with large time delay, this paper proposed a delay separated neural network inverse (DSNNI) control scheme. The delay time and the positive model without delay were given by using adaptive linear element and BP network. The neural network inverse model of the positive model without delay was built on that basis. An appropriate reference model was selected to make the inverse model’s output smoothing. It is an open-loop control system when the model is cascaded into original system. It will avoid the instability caused by the closed-loop control systems. Off-line identification and on-line identification are combined to get the inverse model in order to reduce the steady-state error and make the system have fine adaptive capacity. Detail simulation tests are carried out on the given 300MW power unit. Tests show that the neural network inverse control with delay time separation can get rapid and smooth output for the main steam temperature system. It is able to overcome the adverse effects caused by the time delay and the parameters changes. Compared with the cascade PID controller, the adjustment time of DSNNI reduces from 600s to380s and shows faster response, better robustness and anti-interference performance. Full Text: PDF DOI: http://dx.doi.org/10.11591/telkomnika.v12i7.4696

Delay Separated Neural Network Inverse Control in Main-Steam Temperature System

Delay Separated Neural Network Inverse Control in Main-Steam Temperature System