Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Keyword
-
- Power Electronics (7)
- Active Filters (2)
- Automobile Electronic Equipment (2)
- Benchmark Functions (2)
- Electric Automobiles (2)
-
- Electric Current Measurement (2)
- Electric Drives (2)
- Electric Power Transmission (2)
- Multi-Layer Perceptrons (2)
- Nonlinear Functions (2)
- Particle Swarm Optimization (2)
- Power Converters (2)
- Power Generation (2)
- Quality Assurance (2)
- Ship Power System (2)
- Static Synchronous Compensator (STATCOM) (2)
- 3D integration (1)
- Acoustic Signal Detection (1)
- Active Noise Reduction (1)
- Adaptive Critic (1)
- Adaptive Reward-Inaction (1)
- Adaptive-Fair-Scheduling (1)
- Advanced Encryption Standard (AES) (1)
- Algorithm Design And Analysis (1)
- Analysis And Designs (1)
- Application Specific Integrated Circuits (1)
- Arc Furnace Flicker (1)
- Automatic Generations (1)
- Automatic Voltage Control (1)
- Automotive Electronics (1)
Articles 1 - 30 of 56
Full-Text Articles in Engineering
Structural Identification Using A Low-Cost Search Method, James W. Fonda, Steve Eugene Watkins
Structural Identification Using A Low-Cost Search Method, James W. Fonda, Steve Eugene Watkins
Electrical and Computer Engineering Faculty Research & Creative Works
An easily implementable and trainable damage detection method is proposed and implemented for a simple truss structure. The approach uses the iterative search identification method and is compatible with low-cost and low-power microcontroller hardware. This method employs pattern matching for a data set from a strain sensor array and predicts location (truss member) and severity (member cross sectional area) of damage. As a health monitoring approach, the method is not as robust or rigorous as more complex methods. However, it has modest processing requirements and can handle noisy signals. The work presents an algorithm applied to a truss structure, the …
Electrical-Thermal Co-Analysis For Power Delivery Networks In 3d System Integration, Jianyong Xie, Daehyun Chung, Madhavan Swaminathan, Michael Mcallister, Alina Deutsch, Lijun Jiang, Barry J. Rubin
Electrical-Thermal Co-Analysis For Power Delivery Networks In 3d System Integration, Jianyong Xie, Daehyun Chung, Madhavan Swaminathan, Michael Mcallister, Alina Deutsch, Lijun Jiang, Barry J. Rubin
Electrical and Computer Engineering Faculty Research & Creative Works
In this paper, an electrical-thermal co-analysis method for power delivery networks in 3D system integration is proposed. For electrical analysis, temperature-dependent electrical resistivity of conductors is taken into account. For thermal analysis, Joule heating effect due to the current flowing through conductors is considered. The proposed co-analysis method is carried out using Rgen and ChipJoule of IBM EIP Tool Suite. An example of 3D integration system including stacked chips, power delivery network, glass-ceramic substrate, through-silicon vias, controlled collapse chip connections (C4s), underfill material, and TIM is analyzed using the proposed method. The simulation results show that the temperature effect on …
Effect Of System Components On Electrical And Thermal Characteristics For Power Delivery Networks In 3d System Integration, Jianyong Xie, Daehyun Chung, Madhavan Swaminathan, Michael Mcallister, Alina Deutsch, Lijun Jiang, Barry J. Rubin
Effect Of System Components On Electrical And Thermal Characteristics For Power Delivery Networks In 3d System Integration, Jianyong Xie, Daehyun Chung, Madhavan Swaminathan, Michael Mcallister, Alina Deutsch, Lijun Jiang, Barry J. Rubin
Electrical and Computer Engineering Faculty Research & Creative Works
In this paper, parameterized electrical-thermal co-analysis for power delivery networks (PDN) in 3D system integration is carried out. A 3D integrated system including glass-ceramic substrate, single and stacked dies, power delivery network, through-silicon vias (TSVs), controlled collapse chip connections (C4s), underfill material, and thermal interface material (TIM) is analyzed with several variable parameters. The analysis results show that temperature effects on DC IR drop can not be neglected. The TIM thermal conductivity, C4 density, stacking order of stacked dies, and voltage source location affect the final IR drop and hot spot temperature in the system. ©2009 IEEE.
On The Dual Basis For Solving Electromagnetic Surface Integral Equations, Mei Song Tong, Weng Cho Chew, Barry J. Rubin, Jason D. Morsey, Lijun Jiang
On The Dual Basis For Solving Electromagnetic Surface Integral Equations, Mei Song Tong, Weng Cho Chew, Barry J. Rubin, Jason D. Morsey, Lijun Jiang
Electrical and Computer Engineering Faculty Research & Creative Works
A powerful technique for solving electromagnetic (EM) surface integral equations (SIEs) for inhomogenous objects by the method of moments (MoM) involves the well-known RaoWiltonGlisson (RWG) basis function to represent the electric current and, for field orthogonality and numerical stability reasons, a variation of the RWG basis known as the ňx RWG basis (where ň is a unit normal vector at the object surface) to represent the magnetic current. Though this combination provides a numerically efficient and effective solution that has been demonstrated on a variety of structures, one cannot feel entirely comfortable because of the presence of fictitious magnetic current …
Particle Swarm Optimization Tuned Flatness-Based Generator Excitation Controller, Ganesh K. Venayagamoorthy, E. C. Anene, U. O. Aliyu
Particle Swarm Optimization Tuned Flatness-Based Generator Excitation Controller, Ganesh K. Venayagamoorthy, E. C. Anene, U. O. Aliyu
Electrical and Computer Engineering Faculty Research & Creative Works
An optimal transient controller for a synchronous generator in a multi-machine power system is designed using the concept of flatness-based feedback linearization in this paper. The computation of the flat output and corresponding controller for reduced order model of the synchronous generator is presented. The required feedback gains used to close the linearization loop is optimized using particle swarm optimization for maximum damping. Typical results obtained for transient disturbances on a two-area, four-generator power system equipped with the proposed controller on one generator and conventional power system stabilizers on the remaining generators are presented. The effectiveness of the flatness-based controller …
Adaptive Distributed Fair Scheduling For Multiple Channels In Wireless Sensor Networks, Maciej Jan Zawodniok, Jagannathan Sarangapani, Steve Eugene Watkins, James W. Fonda
Adaptive Distributed Fair Scheduling For Multiple Channels In Wireless Sensor Networks, Maciej Jan Zawodniok, Jagannathan Sarangapani, Steve Eugene Watkins, James W. Fonda
Electrical and Computer Engineering Faculty Research & Creative Works
A novel adaptive and distributed fair scheduling (ADFS) scheme for wireless sensor networks (WSN) in the presence of multiple channels (MC-ADFS) is developed. The proposed MC-ADFS increases available network capacity and focuses on quality-of-service (QoS) issues. when nodes access a shared channel, the proposed MC-ADFS allocates the channel bandwidth proportionally to the packet's weight which indicates the priority of the packet's flow. The packets are dynamically assigned to channels based on the packet weight and current channel utilization. The dynamic assignment of channels is facilitated by use of receiver-based allocation and alternative routes. Moreover, MC-ADFS allows the dynamic allocation of …
Neural Network Demodulation For An Optical Sensor, Steve Eugene Watkins, Donald C. Wunsch, Rohit Dua
Neural Network Demodulation For An Optical Sensor, Steve Eugene Watkins, Donald C. Wunsch, Rohit Dua
Electrical and Computer Engineering Faculty Research & Creative Works
Methods and systems of neural network demodulation for an optical sensor. An optical sensor may be coupled to a structure and be capable of reflecting a reflected optical signal. A wavelength of the reflected optical signal may be spread based on a strain being applied to the structure. A replication device may receive the reflected optical signal from the optical sensor and produce a plurality of optical signals. A filter may be coupled to the replication device to receive an optical signal from the plurality of optical signals and filter the received optical signal. A detector may receive the filtered …
Reinforcement-Learning-Based Output-Feedback Control Of Nonstrict Nonlinear Discrete-Time Systems With Application To Engine Emission Control, Peter Shih, Brian C. Kaul, Jagannathan Sarangapani, J. A. Drallmeier
Reinforcement-Learning-Based Output-Feedback Control Of Nonstrict Nonlinear Discrete-Time Systems With Application To Engine Emission Control, Peter Shih, Brian C. Kaul, Jagannathan Sarangapani, J. A. Drallmeier
Electrical and Computer Engineering Faculty Research & Creative Works
A novel reinforcement-learning-based output adaptive neural network (NN) controller, which is also referred to as the adaptive-critic NN controller, is developed to deliver the desired tracking performance for a class of nonlinear discrete-time systems expressed in nonstrict feedback form in the presence of bounded and unknown disturbances. The adaptive-critic NN controller consists of an observer, a critic, and two action NNs. The observer estimates the states and output, and the two action NNs provide virtual and actual control inputs to the nonlinear discrete-time system. The critic approximates a certain strategic utility function, and the action NNs minimize the strategic utility …
Estimation Of Channel Transfer Function And Carrier Frequency Offset For Ofdm Systems With Phase Noise, Jun Tao, Jingxian Wu, Chengshan Xiao
Estimation Of Channel Transfer Function And Carrier Frequency Offset For Ofdm Systems With Phase Noise, Jun Tao, Jingxian Wu, Chengshan Xiao
Electrical and Computer Engineering Faculty Research & Creative Works
The joint estimation of carrier frequency offset (CFO) and channel transfer function (CTF) for orthogonal frequency-division multiplexing (OFDM) systems with phase noise is discussed in this paper. A CFO estimation algorithm is developed by exploring the time-frequency structure of specially designed training symbols, and it provides a very accurate estimation of the CFO in the presence of both unknown frequency-selective fading and phase noise. Based on the estimated CFO, phase noise and frequency-selective fading are jointly estimated by employing the maximum a posteriori (MAP) criterion. Specifically, the fading channel is estimated in the form of the frequency-domain CTF. The estimation …
An Improved Nonlinear Statcom Control For Electric Arc Furnace Voltage Flicker Mitigation, Atousa Yazdani, Mariesa Crow, Jianjun Guo
An Improved Nonlinear Statcom Control For Electric Arc Furnace Voltage Flicker Mitigation, Atousa Yazdani, Mariesa Crow, Jianjun Guo
Electrical and Computer Engineering Faculty Research & Creative Works
Electric arc furnaces (EAFs) are prevalent in the steel industry to melt iron and scrap steel. EAFs frequently cause large amplitude fluctuations of active and reactive power and are the source of significant power-quality (PQ) disturbances. Static synchronous compensators (STATCOMs) provide a power-electronic-based means of embedded control for reactive power support and PQ improvement. This paper introduces a new nonlinear control for the STATCOM that provides significant reduction in EAF-induced aperiodic oscillations on the power system. This method is compared with traditional PI controls and has shown to have improved performance.
Current Sensing For Automotive Electronics -- A Survey, Asha Patel, Mehdi Ferdowsi
Current Sensing For Automotive Electronics -- A Survey, Asha Patel, Mehdi Ferdowsi
Electrical and Computer Engineering Faculty Research & Creative Works
Current sensing is widely used in power electronic applications such as dc-dc power converters and adjustable-speed motor drives. Such power converters are the basic building blocks of drivetrains in electric, hybrid, and plug-in hybrid electric vehicles. The performance and control of such vehicles depend on the accuracy, bandwidth, and efficiency of its sensors. Various current-sensing techniques based on different physical effects such as Faraday's induction law, Ohm's law, Lorentz force law, the magnetoresistance effect, and the magnetic saturation effect are described in this paper. Each technique is reviewed and examined. The current measurement methods are compared and analyzed based on …
Energy-Efficient Multi-Key Security Scheme For Wireless Sensor Network, Sandeep Kolli, Maciej Jan Zawodniok
Energy-Efficient Multi-Key Security Scheme For Wireless Sensor Network, Sandeep Kolli, Maciej Jan Zawodniok
Electrical and Computer Engineering Faculty Research & Creative Works
This paper proposes multi-key encryption scheme and engine architecture (MKE) that increases security and optimizes energy efficiency of sensor networks, while minimizing modifications to existing implementations. The scheme improves security of AES against correlation power analysis (CPA) attack by employing MKE engine, breaking the correlation between power consumption and the used key. Other schemes utilize complex hardware designs, for example by using the inhomogeneous s-boxes that reduce energy efficiency of the engine. In contrast, the proposed hardware engine uses a randomly sequence of few keys to encode subsequent blocks of a messages. Additionally, the scheme improves security of AES against …
Reliability Analysis For The Advanced Electric Power Grid: From Cyber Control And Communication To Physical Manifestations Of Failure, Ayman Z. Faza, Sahra Sedigh, Bruce M. Mcmillin
Reliability Analysis For The Advanced Electric Power Grid: From Cyber Control And Communication To Physical Manifestations Of Failure, Ayman Z. Faza, Sahra Sedigh, Bruce M. Mcmillin
Electrical and Computer Engineering Faculty Research & Creative Works
The advanced electric power grid is a cyber-physical system comprised of physical components, such as transmission lines and generators, and a network of embedded systems deployed for their cyber control. The objective of this paper is to qualitatively and quantitatively analyze the reliability of this cyber-physical system. The original contribution of the approach lies in the scope of failures analyzed, which crosses the cyber-physical boundary by investigating physical manifestations of failures in cyber control. As an example of power electronics deployed to enhance and control the operation of the grid, we study Flexible AC Transmission System (FACTS) devices, which are …
Pulsed Em Field Response Of A Thin, High-Contrast, Finely Layered Structure With Dielectric And Conductive Properties, Adrianus T. De Hoop, Lijun Jiang
Pulsed Em Field Response Of A Thin, High-Contrast, Finely Layered Structure With Dielectric And Conductive Properties, Adrianus T. De Hoop, Lijun Jiang
Electrical and Computer Engineering Faculty Research & Creative Works
The response of a thin, high-contrast, finely layered structure with dielectric and conductive properties to an incident, pulsed, electromagnetic field is investigated theoretically. The fine layering causes the standard spatial discretization techniques to solve Maxwell's equations numerically to be practically inapplicable. To overcome this difficulty, an approximate method is proposed that models the interaction of the layer with an incident electromagnetic field via a boundary condition that expresses the in-plane conduction and contrast electric polarization currents in terms of the exciting incident field by relating the jump in the tangential component of the magnetic field strength across the layer in …
A Novel Tdr-Based Coaxial Cable Sensor For Crack/Strain Sensing In Reinforced Concrete Structures, Shishuang Sun, David Pommerenke, James L. Drewniak, Genda Chen, Liang Xue, Michael A. Brower, Marina Koledintseva
A Novel Tdr-Based Coaxial Cable Sensor For Crack/Strain Sensing In Reinforced Concrete Structures, Shishuang Sun, David Pommerenke, James L. Drewniak, Genda Chen, Liang Xue, Michael A. Brower, Marina Koledintseva
Electrical and Computer Engineering Faculty Research & Creative Works
Novel coaxial cable sensors that feature high sensitivity and high spatial resolution are developed for health monitoring of concrete structures using a time-domain reflectometry (TDR). The new sensor was designed based on the topology change of its outer conductor, which was fabricated with tightly wrapped commercial tin-plated steel spiral covered with solder. The cracks that developed within concrete structures will lead to out-of-contact of local steel spirals. This topology change results in a large impedance discontinuity that can be measured with a TDR. A simplified equivalent transmission line model and numerical full-wave simulations using finite-difference time-domain techniques were used to …
Hardware Implementation Of A Mamdani Fuzzy Logic Controller For A Static Compensator In A Multimachine Power System, Salman Mohagheghi, Ganesh K. Venayagamoorthy, Satish Rajagopalan, Ronald G. Harley
Hardware Implementation Of A Mamdani Fuzzy Logic Controller For A Static Compensator In A Multimachine Power System, Salman Mohagheghi, Ganesh K. Venayagamoorthy, Satish Rajagopalan, Ronald G. Harley
Electrical and Computer Engineering Faculty Research & Creative Works
A Mamdani-type fuzzy logic controller is designed and implemented in hardware for controlling a static compensator (STATCOM), which is connected to a ten-bus multimachine power system. Such a controller does not need any mathematical model of the plant to be controlled and can efficiently provide control signals for the STATCOM over a wide range of operating conditions of the power system and during different disturbances. The proposed controller is implemented using the M67 digital signal processor board and is interfaced to the multimachine power system simulated on a real-time digital simulator. Experimental results are provided, showing that the proposed Mamdani …
Rfid-Based Smart Freezer, Ahmet Soylemezoglu, Maciej Jan Zawodniok, Jagannathan Sarangapani
Rfid-Based Smart Freezer, Ahmet Soylemezoglu, Maciej Jan Zawodniok, Jagannathan Sarangapani
Electrical and Computer Engineering Faculty Research & Creative Works
This paper presents a novel radio-frequency identification (RFID)-based smart freezer using a new inventory-management scheme for extremely low temperature environments. The proposed solution utilizes backpressure inventory control, systematic selection of antenna configuration, and antenna power control. The proposed distributed-inventory-control (DIC) scheme dictates the amount of items transferred through the supply chain. when a high item visibility is ensured, the control scheme maintains the desired level of inventory at each supply-chain echelon. The performance of the DIC scheme is guaranteed using a Lyapunov-based analysis. The proposed RFID antenna-configuration design methodology coupled with locally asymptotically stable distributed power control ensures a 99% …
Economic Dispatch Of A Differential Evolution Based Generator Maintenance Scheduling Of A Power System, Yusuf Yare, Ganesh K. Venayagamoorthy, Ahmed Yousuf Saber
Economic Dispatch Of A Differential Evolution Based Generator Maintenance Scheduling Of A Power System, Yusuf Yare, Ganesh K. Venayagamoorthy, Ahmed Yousuf Saber
Electrical and Computer Engineering Faculty Research & Creative Works
This paper presents generator maintenance scheduling (GMS) and economic dispatch (ED) of the Indonesian power system based on minimization of an economic cost function for the economical and reliable operation of a power system, while satisfying crew/manpower, maintenance window, load demand, generation limits and spinning reserve constraints. Differential evolution (DE), an evolutionary computation technique and an optimization algorithm that utilizes the differential information to guide its further search, is known to effectively solve large scale optimization problems and has been widely applied in power system. In this paper, the DE approach is proposed for solving the GMS problem and the …
Optical Fiber Harsh Environment Sensors, Hai Xiao, Tao Wei, Xinwei Lan, Yinan Zhang
Optical Fiber Harsh Environment Sensors, Hai Xiao, Tao Wei, Xinwei Lan, Yinan Zhang
Electrical and Computer Engineering Faculty Research & Creative Works
Various optical fiber harsh environment sensors were reported, including the miniaturized inline Fabry-Perot interferometer sensor by femtosecond laser micromachining, the long period fiber grating sensor and the inline core-cladding mode interferometer by CO2 laser irradiations.
Optimization Of Vehicle-To-Grid Scheduling In Constrained Parking Lots, Ahmed Yousuf Saber, Ganesh K. Venayagamoorthy
Optimization Of Vehicle-To-Grid Scheduling In Constrained Parking Lots, Ahmed Yousuf Saber, Ganesh K. Venayagamoorthy
Electrical and Computer Engineering Faculty Research & Creative Works
An automatic Vehicle-to-Grid (V2G) technology can contribute to the utility grid. V2G technology has drawn great interest in the recent years. Success of the sophisticated automatic V2G research depends on efficient scheduling of gridable vehicles in constrained parking lots. Parking lots have constraints of space and current limits for V2G. However, V2G can reduce dependencies on small expensive units in the existing power systems as energy storage that can decrease running costs. It can efficiently manage load fluctuation, peak load; however, it increases spinning reserves and reliability. As number of gridable vehicles in V2G is much higher than small units …
Near-Field Millimeter-Wave Imaging Of Exposed And Covered Fatigue Cracks, Sergey Kharkovsky, Mohammad Tayeb Ahmad Ghasr, R. Zoughi
Near-Field Millimeter-Wave Imaging Of Exposed And Covered Fatigue Cracks, Sergey Kharkovsky, Mohammad Tayeb Ahmad Ghasr, R. Zoughi
Electrical and Computer Engineering Faculty Research & Creative Works
In this paper, the efficacy of near-field millimeter-wave nondestructive techniques, using open-ended flange-mounted rectangular waveguide probes, for extracting information of 3-D crack area deformation (i.e., in-plane and out-of-plane deformation) is demonstrated. It is shown that this information can be obtained from indications of unique interference patterns that are generated between the probe and the metal surface during the raster scan of a surface-breaking exposed and covered fatigue crack using a phase-sensitive reflectometer.
Methodology For Thermal Modeling Of On-Chip Interconnects Based On Electromagnetic Simulation Tools, Lijun Jiang, H. Smith, A. Deutsch, K. Chandra, B. J. Rubin, J. Gill, S. K. Kolluri
Methodology For Thermal Modeling Of On-Chip Interconnects Based On Electromagnetic Simulation Tools, Lijun Jiang, H. Smith, A. Deutsch, K. Chandra, B. J. Rubin, J. Gill, S. K. Kolluri
Electrical and Computer Engineering Faculty Research & Creative Works
A method and apparatus for thermal modeling of on-chip interconnects using electromagnetic tools to determine a temperature profile across the interconnect structure and the temperature at each node of an equivalent thermal circuit derived from an electrical model.
Double-Layer Integral Using Static Green’S Function And Rectangular Basis, Lijun Jiang, J. D. Morsey
Double-Layer Integral Using Static Green’S Function And Rectangular Basis, Lijun Jiang, J. D. Morsey
Electrical and Computer Engineering Faculty Research & Creative Works
The present invention a new closed-form double-layer integral for a rectangular basis. It is valid for both self-integrals and non-self-integrals. In general, the approach of the present invention contains only six (6) terms and is much simpler than indirect closed-form results, which has 24 terms.
Comparison Of Feedforward And Feedback Neural Network Architectures For Short Term Wind Speed Prediction, Ganesh K. Venayagamoorthy, Richard L. Welch, Stephen M. Ruffing
Comparison Of Feedforward And Feedback Neural Network Architectures For Short Term Wind Speed Prediction, Ganesh K. Venayagamoorthy, Richard L. Welch, Stephen M. Ruffing
Electrical and Computer Engineering Faculty Research & Creative Works
This paper compares three types of neural networks trained using particle swarm optimization (PSO) for use in the short term prediction of wind speed. The three types of neural networks compared are the multi-layer perceptron (MLP) neural network, Elman recurrent neural network, and simultaneous recurrent neural network (SRN). Each network is trained and tested using meteorological data of one week measured at the National Renewable Energy Laboratory National Wind Technology Center near Boulder, CO. Results show that while the recurrent neural networks outperform the MLP in the best and average case with a lower overall mean squared error, the MLP …
Harmonic Identification Using An Echo State Network For Adaptive Control Of An Active Filter In An Electric Ship, Jing Dai, Ganesh K. Venayagamoorthy, Ronald G. Harley
Harmonic Identification Using An Echo State Network For Adaptive Control Of An Active Filter In An Electric Ship, Jing Dai, Ganesh K. Venayagamoorthy, Ronald G. Harley
Electrical and Computer Engineering Faculty Research & Creative Works
A shunt active filter is a power electronic device used in a power system to decrease ldquoharmonic current pollutionrdquo caused by nonlinear loads. The Echo State Network (ESN) has been widely used as an effective system identifier with much faster training speed than the other Recurrent Neural Networks (RNNs). However, only a few attempts have been made to use an ESN as a system controller. As the first attempt to use an ESN in indirect neurocontrol, this paper proposes an indirect adaptive neurocontrol scheme using two ESNs to control a shunt active filter in a multiple-reference frame. As the first …
Transmit Precoding For Mimo Systems With Partial Csi And Discrete-Constellation Inputs, Chengshan Xiao, Y. Rosa Zheng
Transmit Precoding For Mimo Systems With Partial Csi And Discrete-Constellation Inputs, Chengshan Xiao, Y. Rosa Zheng
Electrical and Computer Engineering Faculty Research & Creative Works
In this paper, we consider the transmit linear precoding problem for MIMO systems with discrete-constellation inputs. We assume that the receiver has perfect channel state information (CSI) and the transmitter only has partial CSI, namely, the channel covariance information. We first consider MIMO systems over frequency-flat fading channels. We design the optimal linear precoder based on direct maximization of mutual information over the MIMO channels with discrete-constellation inputs. It turns out that the optimal linear precoder is a non-diagonal non-unitary matrix. Then, we consider MIMO systems over frequency selective fading channels via extending our method to MIMO-OFDM systems. To keep …
Effects Of Learning Rate On The Performance Of The Population Based Incremental Learning Algorithm, Ganesh K. Venayagamoorthy, K. A. Folly
Effects Of Learning Rate On The Performance Of The Population Based Incremental Learning Algorithm, Ganesh K. Venayagamoorthy, K. A. Folly
Electrical and Computer Engineering Faculty Research & Creative Works
The effect of learning rate (LR) on the performance of a newly introduced evolutionary algorithm called population-based incremental learning (PBIL) is investigated in this paper. PBIL is a technique that combines a simple genetic algorithm (GA) with competitive learning (CL). Although CL is often studied in the context of artificial neural networks (ANNs), it plays a vital role in PBIL in that the idea of creating a prototype vector in learning vector quantization (LVQ) is central to PBIL. In PBIL, the crossover operator of GAs is abstracted away and the role of population is redefined. PBIL maintains a real-valued probability …
A Pso With Quantum Infusion Algorithm For Training Simultaneous Recurrent Neural Networks, Bipul Luitel, Ganesh K. Venayagamoorthy
A Pso With Quantum Infusion Algorithm For Training Simultaneous Recurrent Neural Networks, Bipul Luitel, Ganesh K. Venayagamoorthy
Electrical and Computer Engineering Faculty Research & Creative Works
Simultaneous recurrent neural network (SRN) is one of the most powerful neural network architectures well suited for estimation and control of complex time varying nonlinear dynamic systems. SRN training is a difficult problem especially if multiple inputs and multiple outputs (MIMO) are involved. Particle swarm optimization with quantum infusion (PSO-QI) is introduced in this paper for training such SRNs. In order to illustrate the capability of the PSO-QI training algorithm, a wide area monitor (WAM) for a power system is developed using a multiple inputs multiple outputs Elman SRN. The SRN estimates speed deviations of four generators in a multimachine …
Learning Nonlinear Functions With Mlps And Srns, R. Cleaver, Ganesh K. Venayagamoorthy
Learning Nonlinear Functions With Mlps And Srns, R. Cleaver, Ganesh K. Venayagamoorthy
Electrical and Computer Engineering Faculty Research & Creative Works
In this paper, nonlinear functions generated by randomly initialized multilayer perceptrons (MLPs) and simultaneous recurrent neural networks (SRNs) are learned by MLPs and SRNs. Training SRNs is a challenging task and a new learning algorithm - DEPSO is introduced. DEPSO is a standard particle swarm optimization (PSO) algorithm with the addition of a differential evolution step to aid in swarm convergence. The results from DEPSO are compared with the standard backpropagation (BP) and PSO algorithms. It is further verified that functions generated by SRNs are harder to learn than those generated by MLPs but DEPSO provides better learning capabilities for …
Novel Near-Field Millimeter-Wave Differential Probe Using A Loaded Modulated Aperture, Mohamed A. Abou-Khousa, Sergey Kharkovsky, R. Zoughi
Novel Near-Field Millimeter-Wave Differential Probe Using A Loaded Modulated Aperture, Mohamed A. Abou-Khousa, Sergey Kharkovsky, R. Zoughi
Electrical and Computer Engineering Faculty Research & Creative Works
Near-field millimeter-wave techniques have effectively been used for nondestructive testing (NDT) and imaging applications for over a decade. The interaction of the fields and a structure under test (SUT) in the near field of a probe is more complex than that of the far-field interaction. In the near field, the distance between the probe and the SUT, which is referred to as the standoff distance, is an important measurement parameter, and when optimally chosen, it can significantly improve detection sensitivity. However, undesired changes in this parameter can adversely influence the detection outcome to the extent that a target may be …