Abstract: The neural network's performance can be measured by efficiency and accuracy. The major disadvantages of neural network approach are that the generalization capability of neural networks is often significantly low, and it may take a very long time to tune the weights in the net to generate an accurate model for a highly complex and nonlinear systems. This paper presents a novel Neuro-fuzzy architecture based on Extended Kalman filter. To test the performance and applicability of the proposed neuro-fuzzy model, simulation study of nonlinear complex dynamic system is carried out. The proposed method can be applied to an on-line incremental adaptive learning for the prediction of financial time series. A benchmark case studie is used to demonstrate that the proposed model is a superior neuro-fuzzy modeling technique.
Abstract: A supervisory scheme is proposed that implements Stepwise Safe Switching Logic. The functionality of the supervisory scheme is organized in the following eight functional units: Step- Wise Safe Switching unit, Common controllers design unit, Experimentation unit, Simulation unit, Identification unit, Trajectory cruise unit, Operating points unit and Expert system unit. The supervisory scheme orchestrates both the off-line preparative actions, as well as the on-line actions that implement the Stepwise Safe Switching Logic. The proposed scheme is a generic tool, that may be easily applied for a variety of industrial control processes and may be implemented as an automation software system, with the use of a high level programming environment, like Matlab.
Abstract: This paper discusses a design of nonlinear observer by
a formal linearization method using an application of Chebyshev Interpolation
in order to facilitate processes for synthesizing a nonlinear
observer and to improve the precision of linearization.
A dynamic nonlinear system is linearized with respect to a linearization
function, and a measurement equation is transformed into
an augmented linear one by the formal linearization method which is
based on Chebyshev interpolation. To the linearized system, a linear
estimation theory is applied and a nonlinear observer is derived. To
show effectiveness of the observer design, numerical experiments
are illustrated and they indicate that the design shows remarkable
performances for nonlinear systems.
Abstract: Variable speed drives are growing and varying. Drives expanse depend on progress in different part of science like power system, microelectronic, control methods, and so on. Artificial intelligent contains hard computation and soft computation. Artificial intelligent has found high application in most nonlinear systems same as motors drive. Because it has intelligence like human but there are no sentimental against human like angriness and.... Artificial intelligent is used for various points like approximation, control, and monitoring. Because artificial intelligent techniques can use as controller for any system without requirement to system mathematical model, it has been used in electrical drive control. With this manner, efficiency and reliability of drives increase and volume, weight and cost of them decrease.
Abstract: In this paper a new control strategy based on Brain
Emotional Learning (BEL) model has been introduced. A modified
BEL model has been proposed to increase the degree of freedom,
controlling capability, reliability and robustness, which can be
implemented in real engineering systems.
The performance of the proposed BEL controller has been
illustrated by applying it on different nonlinear uncertain systems,
showing very good adaptability and robustness, while maintaining
stability.
Abstract: In this paper, we use nonlinear system identification method to predict and detect process fault of a cement rotary kiln. After selecting proper inputs and output, an input-output model is identified for the plant. To identify the various operation points in the
kiln, Locally Linear Neuro-Fuzzy (LLNF) model is used. This model is trained by LOLIMOT algorithm which is an incremental treestructure
algorithm. Then, by using this method, we obtained 3
distinct models for the normal and faulty situations in the kiln. One of the models is for normal condition of the kiln with 15 minutes
prediction horizon. The other two models are for the two faulty situations in the kiln with 7 minutes prediction horizon are presented.
At the end, we detect these faults in validation data. The data collected from White Saveh Cement Company is used for in this study.
Abstract: A neurofuzzy approach for a given set of input-output training data is proposed in two phases. Firstly, the data set is partitioned automatically into a set of clusters. Then a fuzzy if-then rule is extracted from each cluster to form a fuzzy rule base. Secondly, a fuzzy neural network is constructed accordingly and parameters are tuned to increase the precision of the fuzzy rule base. This network is able to learn and optimize the rule base of a Sugeno like Fuzzy inference system using Hybrid learning algorithm, which combines gradient descent, and least mean square algorithm. This proposed neurofuzzy system has the advantage of determining the number of rules automatically and also reduce the number of rules, decrease computational time, learns faster and consumes less memory. The authors also investigate that how neurofuzzy techniques can be applied in the area of control theory to design a fuzzy controller for linear and nonlinear dynamic systems modelling from a set of input/output data. The simulation analysis on a wide range of processes, to identify nonlinear components on-linely in a control system and a benchmark problem involving the prediction of a chaotic time series is carried out. Furthermore, the well-known examples of linear and nonlinear systems are also simulated under the Matlab/Simulink environment. The above combination is also illustrated in modeling the relationship between automobile trips and demographic factors.
Abstract: This paper uses the radial basis function neural
network (RBFNN) for system identification of nonlinear systems.
Five nonlinear systems are used to examine the activity of RBFNN in
system modeling of nonlinear systems; the five nonlinear systems are
dual tank system, single tank system, DC motor system, and two
academic models. The feed forward method is considered in this
work for modelling the non-linear dynamic models, where the KMeans
clustering algorithm used in this paper to select the centers of
radial basis function network, because it is reliable, offers fast
convergence and can handle large data sets. The least mean square
method is used to adjust the weights to the output layer, and
Euclidean distance method used to measure the width of the Gaussian
function.
Abstract: This paper presents a new stable robust adaptive controller and observer design for a class of nonlinear systems that contain i. Coupling of unmeasured states and unknown parameters ii. Unknown dead zone at the system actuator. The system is firstly cast into a modified form in which the observer and parameter estimation become feasible. Then a stable robust adaptive controller, state observer, parameter update laws are derived that would provide global adaptive system stability and desirable performance. To validate the approach, simulation was performed to a single-link mechanical system with a dynamic friction model and unknown dead zone exists at the system actuation. Then a comparison is presented with the results when there is no dead zone at the system actuation.
Abstract: In this paper, we are interested in attitude control of a satellite, which using wheels of reaction, by state feedback. First, we develop a method allowing us to put the control and its integral in the state-feedback form. Then, by using the theorem of Gronwall- Bellman, we put the sufficient conditions so that the nonlinear system modeling the satellite is stabilisable and observed by state feedback.
Abstract: State-dependent Riccati equation based controllers are
becoming increasingly popular because of having attractive
properties like optimality, stability and robustness. This paper focuses
on the design of a roll autopilot for a fin stabilized and canard
controlled 122mm artillery rocket using state-dependent Riccati
equation technique. Initial spin is imparted to rocket during launch
and it quickly decays due to straight tail fins. After the spin phase, the
roll orientation of rocket is brought to zero with the canard deflection
commands generated by the roll autopilot. Roll autopilot has been
developed by considering uncoupled roll, pitch and yaw channels.
The canard actuator is modeled as a second-order nonlinear system.
Elements of the state weighing matrix for Riccati equation have been
chosen to be state dependent to exploit the design flexibility offered
by the Riccati equation technique. Simulation results under varying
conditions of flight demonstrate the wide operating range of the
proposed autopilot.
Abstract: Performance control law is studied for an
interconnected fractional nonlinear system. Applying a backstepping
algorithm, a backstepping sliding mode controller (BSMC) is
developed for fractional nonlinear system. To improve control law
performance, BSMC is coupled to an adaptive sliding mode observer
have a filtered error as a sliding surface. The both architecture
performance is studied throughout the inverted pendulum mounted on
a cart. Simulation result show that the BSMC coupled to an adaptive
sliding mode observer have stable control law and eligible control
amplitude than the BSMC.
Abstract: Local Linear Neuro-Fuzzy Models (LLNFM) like other neuro- fuzzy systems are adaptive networks and provide robust learning capabilities and are widely utilized in various applications such as pattern recognition, system identification, image processing and prediction. Local linear model tree (LOLIMOT) is a type of Takagi-Sugeno-Kang neuro fuzzy algorithm which has proven its efficiency compared with other neuro fuzzy networks in learning the nonlinear systems and pattern recognition. In this paper, a dedicated reconfigurable and parallel processing hardware for LOLIMOT algorithm and its applications are presented. This hardware realizes on-chip learning which gives it the capability to work as a standalone device in a system. The synthesis results on FPGA platforms show its potential to improve the speed at least 250 of times faster than software implemented algorithms.
Abstract: In this paper, we propose synchronization of an array of nonlinear systems with time delays. The array of systems is decomposed into isolated systems to establish appropriate Lyapunov¬Krasovskii functional. Using the Lyapunov-Krasovskii functional, a sufficient condition for the synchronization is derived in terms of LMIs(Linear Matrix Inequalities). Delayed feedback control gains are obtained by solving the sufficient condition. Numerical examples are given to show the validity the proposed method.
Abstract: LABVIEW is a graphical programming language that has its roots in automation control and data acquisition. In this paper we have utilized this platform to provide a powerful toolset for process identification and control of nonlinear systems based on artificial neural networks (ANN). This tool has been applied to the monitoring and control of a lab-scale distillation column DELTALAB DC-SP. The proposed control scheme offers high speed of response for changes in set points and null stationary error for dual composition control and shows robustness in presence of externally imposed disturbance.
Abstract: In this paper, investigation of subsynchronous
resonance (SSR) characteristics of a hybrid series compensated
system and the design of voltage controller for three level 24-pulse
Voltage Source Converter based Static Synchronous Series
Compensator (SSSC) is presented. Hybrid compensation consists of
series fixed capacitor and SSSC which is a active series FACTS
controller. The design of voltage controller for SSSC is based on
damping torque analysis, and Genetic Algorithm (GA) is adopted for
tuning the controller parameters. The SSR Characteristics of SSSC
with constant reactive voltage control modes has been investigated.
The results show that the constant reactive voltage control of SSSC
has the effect of reducing the electrical resonance frequency, which
detunes the SSR.The analysis of SSR with SSSC is carried out based
on frequency domain method, eigenvalue analysis and transient
simulation. While the eigenvalue and damping torque analysis are
based on D-Q model of SSSC, the transient simulation considers both
D-Q and detailed three phase nonlinear system model using
switching functions.
Abstract: State Dependent Riccati Equation (SDRE) approach is
a modification of the well studied LQR method. It has the capability of being applied to control nonlinear systems. In this paper the technique
has been applied to control the single inverted pendulum (SIP) which represents a rich class of nonlinear underactuated systems. SIP
modeling is based on Euler-Lagrange equations. A procedure is developed
for judicious selection of weighting parameters and constraint handling. The controller designed by SDRE technique here gives better results than existing controllers designed by energy based techniques.
Abstract: The objective of this paper is to compare the time
specification performance between conventional controller PID and
modern controller SMC for an inverted pendulum system. The goal is
to determine which control strategy delivers better performance with
respect to pendulum-s angle and cart-s position. The inverted
pendulum represents a challenging control problem, which
continually moves toward an uncontrolled state. Two controllers are
presented such as Sliding Mode Control (SMC) and Proportional-
Integral-Derivatives (PID) controllers for controlling the highly
nonlinear system of inverted pendulum model. Simulation study has
been done in Matlab Mfile and simulink environment shows that both
controllers are capable to control multi output inverted pendulum
system successfully. The result shows that Sliding Mode Control
(SMC) produced better response compared to PID control strategies
and the responses are presented in time domain with the details
analysis.
Abstract: A nonlinear optimal controller with a fuzzy gain
scheduler has been designed and applied to a Line-Of-Sight (LOS)
stabilization system. Use of Linear Quadratic Regulator (LQR)
theory is an optimal and simple manner of solving many control
engineering problems. However, this method cannot be utilized
directly for multigimbal LOS systems since they are nonlinear in
nature. To adapt LQ controllers to nonlinear systems at least a
linearization of the model plant is required. When the linearized
model is only valid within the vicinity of an operating point a gain
scheduler is required. Therefore, a Takagi-Sugeno Fuzzy Inference
System gain scheduler has been implemented, which keeps the
asymptotic stability performance provided by the optimal feedback
gain approach. The simulation results illustrate that the proposed
controller is capable of overcoming disturbances and maintaining a
satisfactory tracking performance.
Abstract: The majority of existing predictors for time series are
model-dependent and therefore require some prior knowledge for the
identification of complex systems, usually involving system
identification, extensive training, or online adaptation in the case of
time-varying systems. Additionally, since a time series is usually
generated by complex processes such as the stock market or other
chaotic systems, identification, modeling or the online updating of
parameters can be problematic. In this paper a model-free predictor
(MFP) for a time series produced by an unknown nonlinear system or
process is derived using tracking theory. An identical derivation of the
MFP using the property of the Newton form of the interpolating
polynomial is also presented. The MFP is able to accurately predict
future values of a time series, is stable, has few tuning parameters and
is desirable for engineering applications due to its simplicity, fast
prediction speed and extremely low computational load. The
performance of the proposed MFP is demonstrated using the
prediction of the Dow Jones Industrial Average stock index.