|
|
|
|
Home > Products > Journal and Reviews > I.RE.A.CO. > Latest issue
International Review of Automatic Control (Theory and Applications) - September 2011 (Vol. 4 N. 5) - Papers
International Review of Automatic Control - Papers
Vol. 4. n. 5, pp. 594-601
Abstract - A new approach for active noise and disturbance control based on sensitivity function loop shaping design is presented. The proposed method combines pole placement with sensitivity function loop shaping in the frequency domain using extended observers. The approach is non adaptive and the frequencies are chosen according to the desired shape of the sensitivity function in the corresponding bandwidth. Damped sine wave models are introduced in the observer for disturbance tuning reduction, active damping control, and stability robustness achievement. Copyright © 2011 Praise Worthy Prize S.r.l. - All rights reserved
Keywords: Loop Shaping, Sensitivity Function, Disturbance Estimator, Damping Factor.
Vol. 4. n. 5, pp. 602-609
Abstract - In this paper, a method for on-line fault detection and isolation (FDI) of non linear uncertain parameters systems modelled by bond graphs (BG) is proposed. Residuals are generated from the Diagnostic Bond Graph (DBG) which is a direct residuals generator. Detection is based on fuzzy logic approach and its different parameters are determined off line. For isolation, three methods based on causal properties of the BG model, that we deduced, are used: Fault Signature Matrix (FSM), exoneration and cover of a causal graph. A real simulation example is provided to show the efficiency of the proposed detection method and a comparison between the three isolation approaches is made. Copyright © 2011 Praise Worthy Prize S.r.l. - All rights reserved
Keywords: Fault Detection and Isolation (FDI), Bond Graph (BG), Parameters Uncertainties, Fuzzy Logic, Causal Reasoning.
Vol. 4. n. 5, pp. 610-619
Abstract - In this
paper, the Fault Detection and Isolation (FDI) problem for nonlinear
dynamic power systems based on observers is treated. The nonlinear
dynamic model based on differential algebraic equation (DAE) is
transformed to ordinary differential equation (ODE). By combining a
relevant version of the Extended Kalman Filter with moving horizon (E.K.F-MH)
and the version with Unknown Inputs (U.I.E.K.F), we propose a robust FDI.
Simulation of IEEE 3 buses test system demonstrates the robustness and
effectiveness of the proposed FDI for nonlinear dynamic power systems.
Keywords: FDI, Dynamic Power System, U.I.E.K.F, E.K.F-MH, Convergence Analysis.
Vol. 4. n. 5, pp. 620-629
Abstract - This work proposes a new methodology for sensor fault detection and localization using principal component analysis (PCA). Several fault detection indices in the literature are analyzed and unified. A proposed index is adopted in order to detect simple and multiple faults affecting the dependent and independent process variables. A new iterative selection method of principal component number is presented. This method determines a model allowing the detection of faults without a priori knowledge of their natures. The fault localization is carried out using hierarchical contribution plots applied to the adopted detection index. The performance of this approach becomes poor for a bad partitioning of the variables into blocs. A new partitioning method is proposed to identify correctly all the faults affecting the process. The whole proposed results were applied to a non linear noisy system subjected to simple and multiple faults. Copyright © 2011 Praise Worthy Prize S.r.l. - All rights reserved
Keywords: PCA, Number of Principal Components, Sensor Fault, Detection, Localization, Contribution Plots.
Vol. 4. n. 5, pp. 630-639
Abstract - This paper presents a fuzzy sliding mode position control based on direct thrust force control for permanent magnet linear synchronous motors and field weakening strategy for utilizing maximum capacity of these motors. A Particle Swarm Optimization (PSO) based optimum control scheme is fully derived. The fuzzy inference mechanism is used to reduction of chattering phenomena in sliding mode control. The proposed scheme incorporates maximum thrust force per ampere and field weakening strategies to keep operate the drive within the voltage and current limits of the motor/inverter. Copyright © 2011 Praise Worthy Prize S.r.l. - All rights reserved
Keywords: Direct Thrust Force Control, Field Weakening Strategy, Fuzzy Logic Controller, Maximum Force Per Ampere, Permanent Magnet Linear Synchronous Motor, Sliding Mode Control.
Vol. 4. n. 5, pp. 640-648
Abstract - This paper presents a nonlinear control of 900-kW wind farm, to track the maximum power point (MPPT,) and control Power Factor Correction (PFC) of wind farm using three Squirrel Cage Induction Generators (SCIGs) driven by 300-kW wind turbines. The wind farm delivers an active and reactive power to grid via common DC-bus and Voltage Source Inverter (VSI), The proposed control provides perfect tracking performances of the DC-bus voltage and the active and reactive powers to their references trajectories. The proposed control laws are derived from the Lyapunov approach using backstepping controllers. All theoretical and simulations results verified the accuracy and effectiveness of the proposed MPPT and PFC nonlinear control laws. Copyright © 2011 Praise Worthy Prize S.r.l. - All rights reserved
Keywords: Wind Farm, Scigs, MPPT, PFC, VSC, VSI, Nonlinear Control, Buckstepping Controller, Lyapunov Approach.
Vol. 4. n. 5, pp.
649-658 Abstract - The switch-mode power supplies have been controlled using different control algorithms like PID control, current mode control etc. Since, Switch-mode power supplies represent a particular class of variable structure systems (VSS). Thus, they can take advantage of non-linear control techniques developed for the variable structure systems. In this paper the sliding mode control is analyzed and developed with preference to buck converter. The simulation model of buck converter with its control circuit was build up in MATLAB/SimulinkTM and simulation results are obtained. Then the dynamic response of buck converter controlled by SMC is studied. Sliding mode control extends the properties of hysteresis control to multi-variable environments, resulting in stability even for large supply and load variations. It presents a good dynamic response and simple implementation. The performance of SM control is compared with that of conventional PID control. It has been shown that the use of SM control can lead to an improved robustness in providing consistent transient responses over a wide range of operating conditions. Copyright © 2011 Praise Worthy Prize S.r.l. - All rights reserved
Keywords: DC-DC Converter, Non-Linear Controller, Sliding-Mode (SM) Control.
Vol. 4. n. 5, pp. 659-668
Abstract - This paper presents the oriented control of a salient pole wound field synchronous machine(WFSM) in stator flux coordinates. The procedure for derivation of flux linkage equations along any general rotating axes including stator flux axes is given. The stator flux equations are used to identify the cross-coupling occurring between the axes due to saliency in the machine. The coupling terms are canceled as feedforward terms in the generation of references for current controllers to achieve good decoupling during transients. The design of current controller for stator-flux-oriented control is presented. This paper proposes the method of extending rotor flux closed loop observer for sensorless control of wound field synchronous machine. This paper also proposes a new sensorless control by using stator flux closed loop observer and estimation of torque angle using stator current components in stator flux coordinates. all of the bottom cases are studied with dampers windings and will be show that the dampers of d-q axis are effected on stator flux amplitude directly. Matlab Simulink is used for simulation results. Copyright © 2011 Praise Worthy Prize S.r.l. - All rights reserved
Keywords: Field Oriented Control (FOC), Salient Pole, Stator Flux, Synchronous Machine, Damper Windings.
Vol. 4. n. 5, pp. 669-677
Abstract - In this paper, counter-based pulse-width-modulated (PWM) control according to the output voltage ripple using a one-comparator scheme without any analog-to-digital converter (ADC) utilized is presented herein, which is implemented based on the field programmable gate arrays (FPGA) and applied to DC-DC converters. However, too small or distorted output ripple limits its performance. Consequently, a sawtoothed wave injection method is proposed to overcome this problem and enhance its application capability greatly. In the paper, the one-comparator counter-based pulse-width-modulated (PWM) control strategy and the sawtoothed wave injection method are firstly described in details. And finally, some simulation and experimental results are provided to demonstrate the effectiveness of the proposed control scheme. Copyright © 2011 Praise Worthy Prize S.r.l. - All rights reserved
Keywords: One-Comparator, Counter-Based, PWM, Sawtoothed Wave Injection.
Vol. 4. n. 5, pp. 678-687
Abstract - This paper presents a two stage wide input-output voltage range ac-dc converter. First stage of the converter is a commercially available front-end boost power factor corrector (PFC) and second stage is a simple step-down dc-dc converter. This work is based on classical off-line ac-dc power supplies architecture. The main improvement is the employment of Fuzzy Proportional-Integral-Derivative (FPI+D) controller to control the step-down converter. The main goal of the utilized controller is to regulate the output voltage in a wide range of reference voltage and load changes. Achieving these goals is possible by applying this robust controller that can handle inherent nonlinearities of dc-dc converters operating in both continuous-conduction-mode (CCM) and discontinuous-conduction-mode (DCM). Besides simulation results, a 200W universal-line hardware prototype was built to evaluate the proposed scheme experimentally. Developed prototype has the input voltage range of 85-265 Vac and the wide output voltage range between 10-200 Vdc. Copyright © 2011 Praise Worthy Prize S.r.l. - All rights reserved
Keywords: Fuzzy PI+D Controller, Pulse-Width-Modulated (PWM) Converter, Switched-Mode Power Supplies (SMPS), Universal-Line AC-DC Converter.
Vol. 4. n. 5, pp. 688-693
Abstract - Nowadays power factor correction (PFC) rectifiers are an essential part of power system to improve power quality and decrease total harmonic distortion THD. Various PFC circuits were introduced in recent years. Base component of these circuits is BOOST converters. Proposed circuits differ in topology, IC used, control loop and algorithm. In some cases, PFC circuits were modified to obtain better characteristics due to their particular application. A PFC circuit with SEPIC rectifiers employing IC UC3854 proposed, simulated and built in laboratory. This method compared to BOOST PFC circuit. Copyright © 2011 Praise Worthy Prize S.r.l. - All rights reserved
Keywords: Brushless DC Motor, PFC, BOOST, SEPIC converter, Harmonics.
Vol. 4. n. 5, pp. 694-699
Abstract
- Stochastic nature of the wind speed is the main reason that leads to
variability of output power of wind farm. Thus high penetration of the
wind farm will cause power fluctuations and voltage variations in the
grid system. Due to these factors, a control method based on Voltage
Source Converter has been implemented to control power flow in the grid
connected wind turbine to eliminate the fluctuation of power in the
network. This paper presents and focused on the designing and
implementation of linear dynamic model of current-controlled Voltage
Source Converter (VSC). Mathematical equations representing the model
are obtained from the dynamic analysis of VSC circuit. The effectiveness
of the controller is investigated by comparing between with and without
control system as well as during disturbances. Results show that the
current-controlled Voltage Source Converter has a potential to control
independently real and reactive power of the grid system.
Keywords: Current-Controlled VSC, Linear Dynamic Model, Mathematical Equation, Power Fluctuation.
Vol. 4. n. 5, pp. 700-706
Abstract - The
frequency converter is the most sensitive part in the variable-speed
wind turbine generator system equipped with a double-fed induction
generator (DFIG). The frequency converter is normally controlled by a
set of PI controllers. In order to improve the response of DFIG when
subjected to system disturbances, the best way is to tune the PI
controllers of the frequency converter. Due to the high complexity of
the system, the tuning of these PI controllers is very difficult. In
this paper an approach is offered to improve the response of DFIG when
subjected to system disturbances using Hybrid Particle Swarm
Optimization and Genetic Algorithm (PSO-GA). In this case, tuning all PI
controllers parameters is considered. The results show that the proposed
algorithm is well suited in terms of accuracy and quick response.
Keywords: Double-Fed Induction Generator (DFIG), Variable-Speed Wind Turbine, Electrical Grids, Genetic Algorithm (GA), Particle Swarm Optimization (PSO).
Vol. 4. n. 5, pp. 707-718
Abstract - In this
paper we study controlling chaos when chaotic ferroresonant oscillations
occur in voltage transformers is carried out. A strategy to control
chaotic oscillations is presented. In this control method controller is
a time delay feedback controller (TDFC) used to stabilize unstable
periodic orbits (UPOs). Also using multiple scales method chaotic
behavior and types of fixed points in occurrence of ferroresonance in
voltage transformers is analyzed and investigated. It is proved that
ferroresonance phenomenon in voltage transformer can be classified in
chaotic dynamics systems. In this contribution chaos occurs in system
from a sequence of period doubling bifurcation (PDB). This phenomenon
includes different types of bifurcations such as period doubling
bifurcation (PDB), saddle node bifurcation (SNB), hopf bifurcation (HB)
and chaos. Analysis of dynamics of ferroresonant circuit is carried out
using bifurcation theory. For this work bifurcation diagrams and phase
plane diagrams are drawn using a continuation method for linear and
nonlinear core loss models, lyapunov exponents are gained using multiple
scales method is used. Bifurcation diagrams show with changing parameter
of control and its increasing chaos occur in system.
Keywords: Time Delay Feedback Controller, Ferroresonant oscillations, Lyapunov Exponent, Feigenbaum Number, Chaos.
Vol. 4. n. 5, pp. 719-732
Abstract - In this
paper controlling chaos when chaotic ferroresonant oscillations occur in
voltage transformer with nonlinear core loss model is carried out. A
time delay feedback controller (TDFC) is used to stabilize unstable
periodic orbits (UPOs). Also using multiple scales method chaotic
behavior and types of fixed points in occurrence of ferroresonance in
voltage transformer with considering a nonlinear core loss model is
analyzed and investigated. It is proved that ferroresonance phenomenon
in voltage transformer can be classified in chaotic dynamics systems. In
this contribution chaos occurs in system from a sequence of period
doubling bifurcation (PDB). This phenomenon includes different types of
bifurcations such as period doubling bifurcation (PDB), saddle node
bifurcation (SNB), hopf bifurcation (HB) and chaos. Analysis of dynamics
of ferroresonant circuit is carried out using bifurcation theory. For
this work bifurcation diagrams and phase plane diagrams are drawn using
a continuation method for linear and nonlinear core loss models,
lyapunov exponents are gained using multiple scales method and
feigenbaum number are used. Bifurcation diagrams show with changing
parameter of control and its increasing chaos occur in system. Border
collision is shown in bifurcation diagrams.
Keywords: Chaos Theory, Ferroresonance, Unstable Periodic Orbit, Nonlinear Core Loss Model, Period Doubling.
Vol. 4. n. 5, pp. 733-739
Abstract - This
paper presents the optimal location of Flexible AC Transmission System
(FACTS) devices to achieve maximum transmission loadability (TL) with
minimum cost of installation of FACTS devices. While finding the optimal
location, thermal limit for the lines and voltage limit for the buses
are taken as constraints. Two types of FACTS devices, Thyristor
Controlled Series Compensator (TCSC) and Static VAR Compensator (SVC)
are considered. In this paper, there are three main steps in the FACTS
devices installation strategy proposed. In step 1, based on the
peak-load state, the OPF technique is used to formulate the maximum
transmission loadability (MTL) problem to maximize the TL increased from
the peak-load through installation of the FACTS devices. Here, the MTL
without FACTS device installed is first calculated. While in step 2,
based on the power flow solution for the MTL obtained in step 1, the
positions proper to place SVCs and TCSCs are determined using the
tangent vector technique and real power flow performance index (PI)
sensitivity factors, respectively. Nine FACTS devices installation
schemes are then built with these candidate positions and, for each
scheme, the MTL is solved by determining the ratings for the SVCs and
TCSCs installed. Finally in step 3, by comparing the ratios of the TLs
increased to the investment costs between various schemes, a
correspondingly most advantageous scheme is suggested. Mathematical
formulation and optimization of this problem is performed by GAMS
software.
Keywords: FACTS Devices, Transmission Loadability (TL), Tangent Vector Technique, Sensitivity Factor, Improvement Factor (IF).
Vol. 4. n. 5, pp. 740-748
Abstract - In this
paper, optimal design of fuzzy logic controller for a static VAR
compensator to enhance the damping of power system oscillations is
investigated. This problem is formulated as an optimization problem,
which is solved by particle swarm optimization algorithm. Particle swarm
optimization technique is utilized to adjust the membership functions
and scaling factors of input/output of fuzzy logic controller to achieve
a good control performance. Also, a conventional fuzzy logic controller
(with non optimal parameters) is introduced and responses of both
controllers in terms of damping effect and settling time are compared.
Keywords: Low Frequency Oscillations, Static VAR Compensator, Fuzzy Logic Controller, Particle Swarm Optimization.
Vol. 4. n. 5, pp. 749-754
Abstract - Any
sudden change in the configuration or the loading of an electrical
network causes power swing between the load concentrations of the
network. Power swing can affect the distance relay performance by
entering the impedance locus into protection zone of the relay causing
unnecessary tripping. In this paper a novel technique to prevent the
distance relay from tripping during power swing is presented. The
presented method is based on adaptive neuro fuzzy inference system (ANFIS)
which has three inputs, include the rate of change of positive sequence
current, active and reactive powers. Adaptive neuro fuzzy method is
implemented utilizing MATLAB/ANFIS toolbox. For the purpose of testing a
typical power network which is used in previous works is modeled in
PSCAD software, a data set consisting of more than 2500 different power
swing scenarios is also considered to guarantee the results are accurate
in different conditions.
Keywords: Active And Reactive Power, Adaptive Neuro Fuzzy Inference System (ANFIS), Distance Relay, Power Swing Detection.
Vol. 4. n. 5, pp. 755-765
Abstract - The aim
of this paper is to deal with regional stabilization of the flux of
linear distributed systems evolving on a spatial domain Ω. This means
the study of the asymptotic behavior of the gradient of such a system
only in a subregion 𝜔 of Ω. So we give necessary and sufficient
conditions which characterize stabilizing controls. Also we give the
control that stabilizes regionally the gradient, minimizes a given
performance cost and ensures a bounded state in the whole domain. The
obtained results are illustrated by numerical simulations.
Keywords: Distributed Systems, Gradient Stability, Regional Gradient Stability, Stability, Stabilization.
Vol. 4. n. 5, pp. 766-772
Abstract - In this
paper a complementary damping controller is proposed for static VAR
compensator (SVC). Power system stability improvement using this damping
controller has been perused. The Real Coded Generic Algorithm (RCGA)
which has been known to be immediately perceptive, well performing, and
capable to impressively solve highly non-linear objective, has been
applied to the proposed controller based on an optimization problem to
achieve optimal controller parameter of SVC. In this paper both local
and remote signals with associated time delays are considered and these
signals have been compared together. The SVC-based damping controller is
evaluated under severe disturbances for single-machine infinite-bus &
multi-machine (two-machine) power system.
Keywords: SVC-Based Damping Controller, Transient Stability, Remote Signal, Local Signal, RCGA Optimization Technique, Single-Machine Infinite-Bus Power System, Multi-Machine Power System.
Vol. 4. n. 5, pp. 773-781
Abstract - IThis
paper presents an improved method for determining the contribution of
harmonic distortion generated by utility and customer at the Point of
Common Coupling (PCC) in radial distribution systems. For this purpose,
first the magnitude and phase of voltage and current at the PCC in each
frequency are estimated by adaptive Kalman filter. Then the parameters
of Thevenin equivalent circuits of load and utility sides are estimated
using the recursive least squares technique based on singular value
decomposition (SVD). Finally, the contribution of utility and customer
in harmonic distortion of the 3-phase voltage waveforms has been
calculated by three approaches. A case study has been made to verify the
accuracy of the proposed method. Also, the presented method has been
used in a 13-bus IEEE standard distribution system. Presented simulation
results show that the proposed method can accurately determine the
harmonic contributions of utility and customer for measurements made at
the PCC.
Keywords: Contribution of Harmonic Distortion, Adaptive Kalman Filter, Recursive Least-Squares Based Singular Value Decomposition.
Vol. 4. n. 5, pp. 782-790
Abstract - Unit
commitment (UC) is a very significant optimization task. The unit
commitment problem (UCP) involves the energy dispatch cost minimization
in the competitive electric power market over a given scheduling period.
In general the UCP is a large scale, nonconvex, nonlinear, mixed-integer
and complex combinatorial optimization problem. A new mixed-integer
linear formulation is obtained to model the unit commitment problem.
Additionally to overcome the complexity of the UCP, a linearization
method employed to present the equivalent linear expression of the
problem. Although the unit startup and operation cost is not considered
in this model by special objective function, the solution of this
optimization represents a generation schedule with minimum number of
unit in the given time horizon. In this paper the artificial generators
are used to model loss of load in power system. This generators cause to
avoid divergence in solution process. To demonstrate the efficiency of
the presented method, a system as the same structure as Iranian power
market is used as a case study.
Keywords: Mixed-Integer Programming, Linearization Method, Artificial Generator, Unit Commitment.
Vol. 4. n. 5, pp. 791-797
Abstract - In this
paper, the problems of optimal mixed variable-pitch-angle control and
variable-speed control of wind turbines for all operating regions are
considered. A new optimal controller, based on minimum torque control
and minimum lost wind-energy capture, for maximizing wind energy
extraction is designed. Furthermore, a new optimal controller, based on
minimum torque control, for output power leveling is designed. In
special cases, such as saturated controller, fixed-pitch-angle control,
and constant rotor speed, control mixed control problems are studied.
Keywords: Variable-Pitch-Angle Control, Variable-Speed Control, Wind Turbines.
Vol. 4. n. 5, pp. 798-806
Abstract - In this
paper, a new scheme has been proposed to improve the performance of
Interacting Multiple Model (IMM) algorithm in presence of maneuver. This
method uses the Modified Input Estimation (MIE) technique to augment the
acceleration state to the target model, and consequently each sub-filter
obtains the ability of estimating target acceleration along with the
other states. In addition, due to the shortcoming of MIE technique in
presence of high maneuvers, an intelligent approach based on Fuzzy
Forgetting Factor (FFF) is used to modify the state estimation of each
sub-filter in these maneuvering levels. By doing these modifications,
the proposed IMM algorithm shows an excellent ability for tracking
maneuvering targets. The Monte-Carlo simulation results show the
effectiveness of proposed method with respect to the Wang’s method and
conventional IMM algorithm with quite large number of sub-filters.
Keywords: Maneuvering Target Tracking, Interacting Multiple Model, Modified Input Estimation Technique, Fuzzy Forgetting Factor.
Vol. 4. n. 5, pp. 807-814
Abstract -This paper
reviews the methods used to find the inverse kinematics of redundant
manipulators, with focus on the secondary performance criteria of
singularity avoidance. Redundant manipulators have infinite solutions
for its inverse kinematics; therefore, one solution among these infinite
solutions should be chosen. Consequently, secondary performance criteria
such as singularity avoidance or obstacles avoidance optimization gain
importance. This paper focuses on the methods used to optimize
singularity avoidance of manipulators. Most of these methods based on
the manipulator Jacobian Pseudoinverse, but in the case of hyper
redundant manipulators with a high number of degrees of freedom, the
computational burden of pseudoinverse Jacobian becomes prohibitive,
despite proposed improvements. Therefore, this paper presents all the
well-know methods that deal with inverse kinematics of redundant
manipulators and using to optimize the singularity avoidance and no
matter whether this method is based on Jacobian Pseudoinverse or not.
Keywords: Redundant Manipulators, Inverse Kinematics, Singularity Avoidance, Pseudoinverse.
Vol. 4. n. 5, pp. 815-820
Abstract -The
present work carries on the use of a method based on the wavelet
transform to detect the internal flaws of composite materials. The
objective of this work consists in working out a data processing
sequence of an ultrasonic signal identifying nearly flaws in composite
laminate materials and estimating their position. The use of a numerical
signal processing technique, based on the Fast Wavelet Transforms is
applied. The method is implanted and optimized for detection and
classification of delamination and porosity flaws in manufactured
materials. Since the information about the signal requires a large
amount of computation time and resources, a technique is used to reduce
the dimensions of the sampling signals. In Non-destructive evaluation of
stratified composite materials, the identification of some defect
features requires more recent and advanced methods than classical
techniques. Notably, in thin composite materials, the reflected NDE
ultrasonic signals are overlapping. As a result, the flaws evaluation is
becoming unfeasible. Many works dedicated to advanced signal processing
based on time-frequency analysis has been widely used in non-destructive
evaluation (NDE) applications.
Keywords: Ultrasonic Signal, Wavelet Transforms, Composite Materials, Nearly Flaws, Algorithm.
Vol. 4. n. 5, pp. 821-829
Abstract -Research
in the field of cyto-pathology was able to develop artificial
intelligence systems for the diagnosis based on the development of new
analytical technologies and segmentation of the image cell. These tools
are intended to facilitate the task of the expert without pretending to
replace him. The objective of this work is to present a means for
detecting cancerous and precancerous lesions using the technique of
human and automatic intelligent supervisor. Three types of supervisors
were tested; the first based on a neural network and has a success rate
of 43.3%, the second by the technique of fuzzy logic with a success rate
equal to 56.7% and a third by a neuro-fuzzy approach with a success rate
of around 94%..
Keywords: Cancer of the Cervix, Uterine Cervico - Smears (Ucss), Artificial Intelligence, Supervisor, Fuzzy Logic, Neural Networks.
|
|
Please send any questions about this web site
to
info@praiseworthyprize.com
|
