Performance evaluation of neural network algorithms for multisensor data fusion in an airborne track while scan radar

This paper deals with the solution to the problem of multisensor data fusion for a single target scenario as detected by an airborne track-while-scan radar. The details of a neural network implementation, various training algorithms based on standard backpropagation, and the results of training and testing the neural network are presented. The promising capabilities of RPROP algorithm for multisensor data fusion for various parameters are shown in comparison to other adaptive techniques

Tractable theories for the synthesis of neural networks

The Radius of Direct attraction of a discrete neural network is a measure of stability of the network. it is known that Hopfield networks designed using Hebb's Rule have a radius of direct attraction of Omega(n/p) where n is the size of the input patterns and p is the number of them. This lower bound is tight if p is no larger than 4. We construct a family of such networks with radius of direct attraction Omega(n/root plog p), for any p greater than or equal to 5. The techniques used to prove the result led us to the first polynomial-time algorithm for designing a neural network with maximum radius of direct attraction around arbitrary input patterns. The optimal synaptic matrix is computed using the ellipsoid method of linear programming in conjunction with an efficient separation oracle. Restrictions of symmetry and non-negative diagonal entries in the synaptic matrix can be accommodated within this scheme.

A neural network based automatic generation control design through reinforcement learning

This paper presents the design and implementation of a learning controller for the Automatic Generation Control (AGC) in power systems based on a reinforcement learning (RL) framework. In contrast to the recent RL scheme for AGC proposed by us, the present method permits handling of power system variables such as Area Control Error (ACE) and deviations from scheduled frequency and tie-line flows as continuous variables. (In the earlier scheme, these variables have to be quantized into finitely many levels). The optimal control law is arrived at in the RL framework by making use of Q-learning strategy. Since the state variables are continuous, we propose the use of Radial Basis Function (RBF) neural networks to compute the Q-values for a given input state. Since, in this application we cannot provide training data appropriate for the standard supervised learning framework, a reinforcement learning algorithm is employed to train the RBF network. We also employ a novel exploration strategy, based on a Learning Automata algorithm,for generating training samples during Q-learning. The proposed scheme, in addition to being simple to implement, inherits all the attractive features of an RL scheme such as model independent design, flexibility in control objective specification, robustness etc. Two implementations of the proposed approach are presented. Through simulation studies the attractiveness of this approach is demonstrated.

Neural network based power system damping controller for SVC

The development of a neural network based power system damping controller (PSDC) for a static VAr compensator (SVC), designed to enhance the damping characteristics of a power system network representing a part of the Electricity Generating Authority of Thailand (EGAT) system is presented. The proposed stabilising controller scheme of the SVC consists of a neuro-identifier and a neuro-controller which have been developed based on a functional link network (FLN) model. A recursive online training algorithm has been utilised to train the two networks. The simulation results have been obtained under various operating conditions and disturbance cases to show that the proposed stabilising controller can provide a better damping to the low frequency oscillations, as compared to the conventional controllers. The effectiveness of the proposed stabilising controller has also been compared with a conventional power system stabiliser provided in the generator excitation system

Neural network based power system damping controller for SVC

The development of a neural network based power system damping controller (PSDC) for a static Var compensator (SVC), designed to enhance the damping characteristics of a power system network representing a part of the Electricity Generating Authority of Thailand (EGAT) system is presented. The proposed stabilising controller scheme of the SVC consists of a neuro-identifier and a neuro-controller which have been developed based on a functional link network (FLN) model. A recursive online training algorithm has been utilised to train the two networks. The simulation results have been obtained under various operating conditions and disturbance cases to show that the proposed stabilising controller can provide a better damping to the low frequency oscillations, as compared to the conventional controllers. The effectiveness of the proposed stabilising controller has also been compared with a conventional power system stabiliser provided in the generator excitation system.

A neural network based power system stabilizer suitable for on-line training-a practical case study for EGAT system

This paper presents the development of a neural network based power system stabilizer (PSS) designed to enhance the damping characteristics of a practical power system network representing a part of Electricity Generating Authority of Thailand (EGAT) system. The proposed PSS consists of a neuro-identifier and a neuro-controller which have been developed based on functional link network (FLN) model. A recursive on-line training algorithm has been utilized to train the two neural networks. Simulation results have been obtained under various operating conditions and severe disturbance cases which show that the proposed neuro-PSS can provide a better damping to the local as well as interarea modes of oscillations as compared to a conventional PSS

Artificial neural network application to power system voltage stability improvement

As power systems grow in their size and interconnections, their complexity increases. Rising costs due to inflation and increased environmental concerns has made transmission, as well as generation systems be operated closer to design limits. Hence power system voltage stability and voltage control are emerging as major problems in the day-to-day operation of stressed power systems. For secure operation and control of power systems under normal and contingency conditions it is essential to provide solutions in real time to the operator in energy control center (ECC). Artificial neural networks (ANN) are emerging as an artificial intelligence tool, which give fast, though approximate, but acceptable solutions in real time as they mostly use the parallel processing technique for computation. The solutions thus obtained can be used as a guide by the operator in ECC for power system control. This paper deals with development of an ANN architecture, which provide solutions for monitoring, and control of voltage stability in the day-to-day operation of power systems.

Novel algorithm for online voltage stability assessment based on feed forward neural network

This paper presents an artificial feed forward neural network (FFNN) approach for the assessment of power system voltage stability. A novel approach based on the input-output relation between real and reactive power, as well as voltage vectors for generators and load buses is used to train the neural net (NN). The input properties of the feed forward network are generated from offline training data with various simulated loading conditions using a conventional voltage stability algorithm based on the L-index. The neural network is trained for the L-index output as the target vector for each of the system loads. Two separate trained NN, corresponding to normal loading and contingency, are investigated on the 367 node practical power system network. The performance of the trained artificial neural network (ANN) is also investigated on the system under various voltage stability assessment conditions. As compared to the computationally intensive benchmark conventional software, near accurate results in the value of L-index and thus the voltage profile were obtained. Proposed algorithm is fast, robust and accurate and can be used online for predicting the L-indices of all the power system buses. The proposed ANN approach is also shown to be effective and computationally feasible in voltage stability assessment as well as potential enhancements within an overall energy management system in order to determining local and global stability indices

Flux tube model signals for baryon correlations in heavy ion collisions

The flux tube model offers a pictorial description of what happens during the deconfinement phase transition in QCD. The three-point vertices of a flux tube network lead to formation of baryons upon hadronization. Therefore, correlations in the baryon number distribution at the last scattering surface are related to the preceding pattern of the flux tube vertices in the quark-gluon plasma, and provide a signature of the nearby deconfinement phase transition. I discuss the nature of the expected signal, and how to extract it from the experimental data for heavy ion collisions at RHIC and LHC.

Numerical analysis on thermoacoustic prime movers for development of pulse tube cryocoolers

Thermo Acoustic Prime Movers (TAPMs) are being considered as the ideal choice for driving the Pulse Tube Cryocoolers replacing the conventional compressors. The advantages are the absence of moving components and they can be driven by low grade energy as such as fuel, gas, solar energy, waste heat etc. While the development of such TAPMs is in progress in our laboratory, their design and fabrication should be guided by numerical modeling and this may be done by several methods such as solving the energy equation 1], enthalpy flow model 2], CFD 3], etc. We have used CFD technique, since it provides a better insight into the velocity and temperature profiles. The analysis is carried out by varying parameters such as (a) temperature difference across the stack, (b) stack and resonator lengths and (c) different working fluids such as air, nitrogen, argon etc. The theoretical results are compared with the experimental data wherever possible and they are in reasonably good agreement with each other. The analysis indicate that (i) larger temperature difference across the stack leads to increased acoustic amplitude, (ii) longer resonator leads to decrease in frequency with lesser amplitude and (iii) there exists an optimal stack length for the best performance of TAPM. These results are presented here.

Development of moving magnet type linear motor for dual piston compressor for pulse tube cryocooler

This paper describes the design, fabrication and testing of a moving magnet type linear motor of dual piston configuration for a pulse tube cryocooler for ground applications. Eight radially magnetized segmented magnets were used to form one set of a magnet ring. Four magnet rings of such type were constructed, in which one pair of rings has north-pole on its outer diameter and south-pole on inner diameter, while the other pair is it's complementary. The magnets were mounted with opposite poles together on the magnet holder with an axial moving shaft having a piston mounted on both ends of the shaft. The shaft movement was restricted to the axial direction by using C-clamp type flexures, mounted on both sides of the shaft. The force requirement for driving the compressor was calculated based on which the electrical circuit of motor is designed by proper selection of wire gauge and Ampere-turns. The flexure spring force estimation was done through simulation using ANSYS 11.0 and was verified experimentally; while the magnet spring force was determined experimentally. The motor with mounted piston was tested using a variable voltage and variable frequency power supply capable of driving 140 watts of load.

Performances of single and two-stage pulse tube cryocoolers under different vacuum levels with and without thermal radiation shields

Single and two-stage Pulse Tube Cryocoolers (PTC) have been designed, fabricated and experimentally studied. The single stage PTC reaches a no-load temperature of similar to 29 K at its cold end, the two-stage PTC reaches similar to 2.9 K in its second stage cold end and similar to 60 K in its first stage cold end. The two-stage Pulse Tube Cryocooler provides a cooling power of similar to 250 mW at 4.2 K. The single stage system uses stainless steel meshes along with Pb granules as its regenerator materials, while the two-stage PTC uses combinations of Pb along with Er3Ni/HoCu2 as the second stage regenerator materials. Normally, the above systems are insulated by thermal radiation shields and mounted inside a vacuum chamber which is maintained at high vacuum. To evaluate the performance of these systems in the possible conditions of loss of vacuum with and without radiation shields, experimental studies have been performed. The heat-in-leak under such severe conditions has been estimated from the heat load characteristics of the respective stages. The experimental results are analyzed to obtain surface emissivities and effective thermal conductivities as a function of interspace pressure.

High-temperature kinetics of the reaction between CN and hydrocarbons using a novel high-enthalpy flow tube

More than 70 molecules of varied nature have been identified in the envelopes of carbon-rich stars through their spectral fingerprints in the microwave or far infrared regions. Many of them are carbon chain molecules and radicals, and a significant number are unique to the circumstellar medium. The determination of relevant laboratory kinetics data is critical to keep up with the development of the high spectral and spatial resolution observations and of the refinement of chemical models. Neutralneutral reactions of the CN radical with unsaturated hydrocarbons could be a dominant route in the formation of cyanopolyynes, even at low temperatures and deserve a detailed laboratory investigation. The approach we have developed aims to bridge the temperature gap between resistively heated flow tubes and shock tubes. The present kinetic measurements are obtained using a new reactor combining a high-enthalpy source with a flow tube and a pulsed laser photolysislaser-induced fluorescence system to probe the undergoing chemical reactions. The high-enthalpy flow tube has been used to measure the rate constant of the reaction of the CN radical with propane (C3H8), propene (C3H6), allene (C3H4), 1,3-butadiene (1,3-C4H6), and 1-butyne (C4H6) over a temperature range extending from 300 to 1200 K. All studied reactions of CN with unsaturated hydrocarbons are rapid, with rate coefficients greater than 10-10 cm3 center dot molecule-1 center dot s-1 and exhibit slight negative temperature dependence above room temperature. (c) 2012 Wiley Periodicals, Inc. Int J Chem Kinet 44: 753766, 2012

Theoretical-experimental study of shock wave-assisted metal forming process using a diaphragmless shock tube

The use of high-velocity sheet-forming techniques where the strain rates are in excess of 10(2)/s can help us solve many problems that are difficult to overcome with traditional metal-forming techniques. In this investigation, thin metallic plates/foils were subjected to shock wave loading in the newly developed diaphragmless shock tube. The conventional shock tube used in the aerodynamic applications uses a metal diaphragm for generating shock waves. This method of operation has its own disadvantages including the problems associated with repeatable and reliable generation of shock waves. Moreover, in industrial scenario, changing metal diaphragms after every shot is not desirable. Hence, a diaphragmless shock tube is calibrated and used in this study. Shock Mach numbers up to 3 can be generated with a high degree of repeatability (+/- 4 per cent) for the pressure jumps across the primary shock wave. The shock Mach number scatter is within +/- 1.5 per cent. Copper, brass, and aluminium plates of diameter 60 mm and thickness varying from 0.1 to 1 mm are used. The plate peak over-pressures ranging from 1 to 10 bar are used. The midpoint deflection, circumferential, radial, and thickness strains are measured and using these, the Von Mises strain is also calculated. The experimental results are compared with the numerical values obtained using finite element analysis. The experimental results match well with the numerical values. The plastic hinge effect was also observed in the finite element simulations. Analysis of the failed specimens shows that aluminium plates had mode I failure, whereas copper plates had mode II failure.