Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 30 of 34
Full-Text Articles in Engineering
Learning Functions Generated By Randomly Initialized Mlps And Srns, R. Cleaver, Ganesh K. Venayagamoorthy
Learning Functions Generated By Randomly Initialized 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) and two benchmark functions are learned by MLPs and SRNs. Training SRNs is a challenging task and a new learning algorithm - PSO-QI is introduced. PSO-QI is a standard particle swarm optimization (PSO) algorithm with the addition of a quantum step utilizing the probability density property of a quantum particle. The results from PSO-QI 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 …
Implementation Of Neuroidentifiers Trained By Pso On A Plc Platform For A Multimachine Power System, Curtis Alan Parrott, Ganesh K. Venayagamoorthy
Implementation Of Neuroidentifiers Trained By Pso On A Plc Platform For A Multimachine Power System, Curtis Alan Parrott, Ganesh K. Venayagamoorthy
Electrical and Computer Engineering Faculty Research & Creative Works
Power systems are nonlinear with fast changing dynamics. In order to design a nonlinear adaptive controller for damping power system oscillations, it becomes necessary to identify the dynamics of the system. This paper demonstrates the implementation of a neural network based system identifier, referred to as a neuroidentifier, on a programmable logic controller (PLC) platform. Two separate neuroidentifiers are trained using the particle swarm optimization (PSO) algorithm to identify the dynamics in a two-area four machine power system, one neuroidentifier for Area 1 and the other for Area 2. The power system is simulated in real time on the Real …
Reinforcement Learning Based Dual-Control Methodology For Complex Nonlinear Discrete-Time Systems With Application To Spark Engine Egr Operation, Peter Shih, Brian C. Kaul, Jagannathan Sarangapani, J. A. Drallmeier
Reinforcement Learning Based Dual-Control Methodology For Complex Nonlinear Discrete-Time Systems With Application To Spark Engine Egr Operation, Peter Shih, Brian C. Kaul, Jagannathan Sarangapani, J. A. Drallmeier
Electrical and Computer Engineering Faculty Research & Creative Works
A novel reinforcement-learning-based dual-control methodology adaptive neural network (NN) controller is developed to deliver a desired tracking performance for a class of complex feedback nonlinear discrete-time systems, which consists of a second-order nonlinear discrete-time system in nonstrict feedback form and an affine nonlinear discrete-time system, in the presence of bounded and unknown disturbances. For example, the exhaust gas recirculation (EGR) operation of a spark ignition (SI) engine is modeled by using such a complex nonlinear discrete-time system. A dual-controller approach is undertaken where primary adaptive critic NN controller is designed for the nonstrict feedback nonlinear discrete-time system whereas the secondary …
Applications Of Diffusion Maps In Gene Expression Data-Based Cancer Diagnosis Analysis, Rui Xu, Donald C. Wunsch, Steven Damelin
Applications Of Diffusion Maps In Gene Expression Data-Based Cancer Diagnosis Analysis, Rui Xu, Donald C. Wunsch, Steven Damelin
Electrical and Computer Engineering Faculty Research & Creative Works
Early detection of a tumor's site of origin is particularly important for cancer diagnosis and treatment. The employment of gene expression profiles for different cancer types or subtypes has already shown significant advantages over traditional cancer classification methods. One of the major problems in cancer type recognition-oriented gene expression data analysis is the overwhelming number of measures of gene expression levels versus the small number of samples, which causes the curse of dimension issue. Here, we use diffusion maps, which interpret the eigenfunctions of Markov matrices as a system of coordinates on the original data set in order to obtain …
Online Reinforcement Learning-Based Neural Network Controller Design For Affine Nonlinear Discrete-Time Systems, Qinmin Yang, Jagannathan Sarangapani
Online Reinforcement Learning-Based Neural Network Controller Design For Affine Nonlinear Discrete-Time Systems, Qinmin Yang, Jagannathan Sarangapani
Electrical and Computer Engineering Faculty Research & Creative Works
In this paper, a novel reinforcement learning neural network (NN)-based controller, referred to adaptive critic controller, is proposed for general multi-input and multi- output affine unknown nonlinear discrete-time systems in the presence of bounded disturbances. Adaptive critic designs consist of two entities, an action network that produces optimal solution and a critic that evaluates the performance of the action network. The critic is termed adaptive as it adapts itself to output the optimal cost-to-go function and the action network is adapted simultaneously based on the information from the critic. In our online learning method, one NN is designated as the …
Reinforcement Learning Based Output-Feedback Control Of Nonlinear Nonstrict Feedback Discrete-Time Systems With Application To Engines, Peter Shih, Jonathan B. Vance, Brian C. Kaul, Jagannathan Sarangapani, J. A. Drallmeier
Reinforcement Learning Based Output-Feedback Control Of Nonlinear Nonstrict Feedback Discrete-Time Systems With Application To Engines, Peter Shih, Jonathan B. Vance, 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, also referred as the adaptive-critic NN controller, is developed to track a desired trajectory for a class of complex nonlinear discrete-time systems in the presence of bounded and unknown disturbances. The controller includes an observer for estimating states and the outputs, critic, and two action NNs for generating virtual, and actual control inputs. The critic approximates certain strategic utility function and the action NNs are used to minimize both the strategic utility function and their outputs. All NN weights adapt online towards minimization of a performance index, utilizing gradient-descent based rule. …
Online Reinforcement Learning Neural Network Controller Design For Nanomanipulation, Qinmin Yang, Jagannathan Sarangapani
Online Reinforcement Learning Neural Network Controller Design For Nanomanipulation, Qinmin Yang, Jagannathan Sarangapani
Electrical and Computer Engineering Faculty Research & Creative Works
In this paper, a novel reinforcement learning neural network (NN)-based controller, referred to adaptive critic controller, is proposed for affine nonlinear discrete-time systems with applications to nanomanipulation. In the online NN reinforcement learning method, one NN is designated as the critic NN, which approximates the long-term cost function by assuming that the states of the nonlinear systems is available for measurement. An action NN is employed to derive an optimal control signal to track a desired system trajectory while minimizing the cost function. Online updating weight tuning schemes for these two NNs are also derived. By using the Lyapunov approach, …
Gene Expression Data For Dlbcl Cancer Survival Prediction With A Combination Of Machine Learning Technologies, Rui Xu, Xindi Cai, Donald C. Wunsch
Gene Expression Data For Dlbcl Cancer Survival Prediction With A Combination Of Machine Learning Technologies, Rui Xu, Xindi Cai, Donald C. Wunsch
Electrical and Computer Engineering Faculty Research & Creative Works
Gene expression profiles have become an important and promising way for cancer prognosis and treatment. In addition to their application in cancer class prediction and discovery, gene expression data can be used for the prediction of patient survival. Here, we use particle swarm optimization (PSO) to address one of the major challenges in gene expression data analysis, the curse of dimensionality, in order to discriminate high risk patients from low risk patients. A discrete binary version of PSO is used for gene selection and dimensionality reduction, and a probabilistic neural network (PNN) is implemented as the classifier. The experimental results …
Neural Network-Based Output Feedback Controller For Lean Operation Of Spark Ignition Engines, Brian C. Kaul, Jagannathan Sarangapani, J. A. Drallmeier, Jonathan B. Vance, Pingan He
Neural Network-Based Output Feedback Controller For Lean Operation Of Spark Ignition Engines, Brian C. Kaul, Jagannathan Sarangapani, J. A. Drallmeier, Jonathan B. Vance, Pingan He
Electrical and Computer Engineering Faculty Research & Creative Works
Spark ignition (SI) engines running at very lean conditions demonstrate significant nonlinear behavior by exhibiting cycle-to-cycle dispersion of heat release even though such operation can significantly reduce NOx emissions and improve fuel efficiency by as much as 5-10%. A suite of neural network (NN) controller without and with reinforcement learning employing output feedback has shown ability to reduce the nonlinear cyclic dispersion observed under lean operating conditions. The neural network controllers consists of three NN: a) A NN observer to estimate the states of the engine such as total fuel and air; b) a second NN for generating virtual input; …
Negative Reinforcement And Backtrack-Points For Recurrent Neural Networks For Cost-Based Abduction, Donald C. Wunsch, Ashraf M. Abdelbar, M. A. El-Hemaly, Emad A. M. Andrews
Negative Reinforcement And Backtrack-Points For Recurrent Neural Networks For Cost-Based Abduction, Donald C. Wunsch, Ashraf M. Abdelbar, M. A. El-Hemaly, Emad A. M. Andrews
Electrical and Computer Engineering Faculty Research & Creative Works
Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CKA) is an AI formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost proof are taken as the best explanation for the given evidence. In this paper, we introduce two techniques for improving the performance of high order recurrent …
Neural Networks Based Non-Uniform Scalar Quantizer Design With Particle Swarm Optimization, Wenwei Zha, Ganesh K. Venayagamoorthy
Neural Networks Based Non-Uniform Scalar Quantizer Design With Particle Swarm Optimization, Wenwei Zha, Ganesh K. Venayagamoorthy
Electrical and Computer Engineering Faculty Research & Creative Works
Quantization is a crucial link in the process of digital speech communication. Non-uniform quantizer such as the logarithm quantizers are commonly used in practice. In this paper, a companding non-uniform quantizer is designed using two neural networks to perform the nonlinear transformation. Particle swarm optimization is applied to find the weights of neural networks such that the signal to noise ratio (SNR) is maximized. Simulation results on different speech samples are presented and the proposed quantizer design is compared with the logarithm quantizer for bit rates ranging from 3 to 8.
Mlp/Rbf Neural-Networks-Based Online Global Model Identification Of Synchronous Generator, Jung-Wook Park, Ganesh K. Venayagamoorthy, Ronald G. Harley
Mlp/Rbf Neural-Networks-Based Online Global Model Identification Of Synchronous Generator, Jung-Wook Park, Ganesh K. Venayagamoorthy, Ronald G. Harley
Electrical and Computer Engineering Faculty Research & Creative Works
This paper compares the performances of a multilayer perceptron neural network (MLPN) and a radial basis function neural network (RBFN) for online identification of the nonlinear dynamics of a synchronous generator in a power system. The computational requirement to process the data during the online training, local convergence, and online global convergence properties are investigated by time-domain simulations. The performances of the identifiers as a global model, which are trained at different stable operating conditions, are compared using the actual signals as well as the deviation signals for the inputs of the identifiers. Such an online-trained identifier with fixed optimal …
Time Series Prediction With Recurrent Neural Networks Using A Hybrid Pso-Ea Algorithm, Nian Zhang, Ganesh K. Venayagamoorthy, Donald C. Wunsch, Xindi Cai
Time Series Prediction With Recurrent Neural Networks Using A Hybrid Pso-Ea Algorithm, Nian Zhang, Ganesh K. Venayagamoorthy, Donald C. Wunsch, Xindi Cai
Electrical and Computer Engineering Faculty Research & Creative Works
To predict the 100 missing values from the time series consisting of 5000 data given for the IJCNN 2004 time series prediction competition, we applied an architecture which automates the design of recurrent neural networks using a new evolutionary learning algorithm. This new evolutionary learning algorithm is based on a hybrid of particle swarm optimization (PSO) and evolutionary algorithm (EA). By combining the searching abilities of these two global optimization methods, the evolution of individuals is no longer restricted to be in the same generation, and better performed individuals may produce offspring to replace those with poor performance. The novel …
Query-Based Learning For Aerospace Applications, Donald C. Wunsch, Emad W. Saad, J. J. Choi, J. L. Vian
Query-Based Learning For Aerospace Applications, Donald C. Wunsch, Emad W. Saad, J. J. Choi, J. L. Vian
Electrical and Computer Engineering Faculty Research & Creative Works
Models of real-world applications often include a large number of parameters with a wide dynamic range, which contributes to the difficulties of neural network training. Creating the training data set for such applications becomes costly, if not impossible. In order to overcome the challenge, one can employ an active learning technique known as query-based learning (QBL) to add performance-critical data to the training set during the learning phase, thereby efficiently improving the overall learning/generalization. The performance-critical data can be obtained using an inverse mapping called network inversion (discrete network inversion and continuous network inversion) followed by oracle query. This paper …
A Heuristic Dynamic Programming Based Power System Stabilizer For A Turbogenerator In A Single Machine Power System, Wenxin Liu, Ganesh K. Venayagamoorthy, Donald C. Wunsch
A Heuristic Dynamic Programming Based Power System Stabilizer For A Turbogenerator In A Single Machine Power System, Wenxin Liu, Ganesh K. Venayagamoorthy, Donald C. Wunsch
Electrical and Computer Engineering Faculty Research & Creative Works
Power system stabilizers (PSS) are used to generate supplementary control signals for the excitation system in order to damp the low frequency power system oscillations. To overcome the drawbacks of conventional PSS (CPSS), numerous techniques have been proposed in the literature. Based on the analysis of existing techniques, a novel design of power system stabilizer (PSS) based on heuristic dynamic programming (HDP) is proposed in this paper. HDP combining the concepts of dynamic programming and reinforcement learning is used in the design of a nonlinear optimal power system stabilizer. The proposed HDP based PSS is evaluated against the conventional power …
Adaptive Critic Design Based Neurocontroller For A Statcom Connected To A Power System, Salman Mohagheghi, Jung-Wook Park, Ganesh K. Venayagamoorthy, Ronald G. Harley
Adaptive Critic Design Based Neurocontroller For A Statcom Connected To A Power System, Salman Mohagheghi, Jung-Wook Park, Ganesh K. Venayagamoorthy, Ronald G. Harley
Electrical and Computer Engineering Faculty Research & Creative Works
A novel nonlinear optimal neurocontroller for a static compensator (STATCOM) connected to a power system using artificial neural networks is presented in this paper. The heuristic dynamic programming (HDP), a member of the adaptive critic designs (ACDs) family, is used for the design of the STATCOM neurocontroller. This neurocontroller provides nonlinear optimal control with better performance compared to the conventional PI controllers.
Adaptive Critic Designs And Their Implementations On Different Neural Network Architectures, Jung-Wook Park, Ganesh K. Venayagamoorthy, Ronald G. Harley
Adaptive Critic Designs And Their Implementations On Different Neural Network Architectures, Jung-Wook Park, Ganesh K. Venayagamoorthy, Ronald G. Harley
Electrical and Computer Engineering Faculty Research & Creative Works
The design of nonlinear optimal neurocontrollers based on the Adaptive Critic Designs (ACDs) family of algorithms has recently attracted interest. This paper presents a summary of these algorithms, and compares their performance when implemented on two different types of artificial neural networks, namely the multilayer perceptron neural network (MLPNN) and the radial basis function neural network (RBFNN). As an example for the application of the ACDs, the control of synchronous generator on an electric power grid is considered and results are presented to compare the different ACD family members and their implementations on different neural network architectures.
Two Separate Continually Online-Trained Neurocontrollers For Excitation And Turbine Control Of A Turbogenerator, Ganesh K. Venayagamoorthy, Ronald G. Harley
Two Separate Continually Online-Trained Neurocontrollers For Excitation And Turbine Control Of A Turbogenerator, Ganesh K. Venayagamoorthy, Ronald G. Harley
Electrical and Computer Engineering Faculty Research & Creative Works
This paper presents the design of two separate continually online trained (COT) neurocontrollers for excitation and turbine control of a turbogenerator connected to the infinite bus through a transmission line. These neurocontrollers augment/replace the conventional automatic voltage regulator and the turbine governor of a generator. A third COT artificial neural network is used to identify the complex nonlinear dynamics of the power system. Results are presented to show that the two COT neurocontrollers can control turbogenerators under steady-state as well as transient conditions and, thus, allow turbogenerators to operate more closely to their steady-state stability limits
Adaptive Critic-Based Neural Network Controller For Uncertain Nonlinear Systems With Unknown Deadzones, Pingan He, Jagannathan Sarangapani, S. N. Balakrishnan
Adaptive Critic-Based Neural Network Controller For Uncertain Nonlinear Systems With Unknown Deadzones, Pingan He, Jagannathan Sarangapani, S. N. Balakrishnan
Electrical and Computer Engineering Faculty Research & Creative Works
A multilayer neural network (NN) controller in discrete-time is designed to deliver a desired tracking performance for a class of nonlinear systems with input deadzones. This multilayer NN controller has an adaptive critic NN architecture with two NNs for compensating the deadzone nonlinearity and a third NN for approximating the dynamics of the nonlinear system. A reinforcement learning scheme in discrete-time is proposed for the adaptive critic NN deadzone compensator, where the learning is performed based on a certain performance measure, which is supplied from a critic. The adaptive generating NN rejects the errors induced by the deadzone whereas a …
Experimental Studies With Continually Online Trained Artificial Neural Network Identifiers For Multiple Turbogenerators On The Electric Power Grid, Ganesh K. Venayagamoorthy, Donald C. Wunsch, Ronald G. Harley
Experimental Studies With Continually Online Trained Artificial Neural Network Identifiers For Multiple Turbogenerators On The Electric Power Grid, Ganesh K. Venayagamoorthy, Donald C. Wunsch, Ronald G. Harley
Electrical and Computer Engineering Faculty Research & Creative Works
The increasing complexity of a modern power grid highlights the need for advanced system identification techniques for effective control of power systems. This paper provides a new method for nonlinear identification of turbogenerators in a 3-machine 6-bus power system using online trained feedforward neural networks. Each turbogenerator in the power system is equipped with a neuro-identifier, which is able to identify its particular turbogenerator and the rest of the network to which it is connected from moment to moment, based on only local measurements. Each neuro-identifier can then be used in the design of a nonlinear neurocontroller for each turbogenerator …
Excitation And Turbine Neurocontrol With Derivative Adaptive Critics Of Multiple Generators On The Power Grid, Ganesh K. Venayagamoorthy, Donald C. Wunsch, Ronald G. Harley
Excitation And Turbine Neurocontrol With Derivative Adaptive Critics Of Multiple Generators On The Power Grid, Ganesh K. Venayagamoorthy, Donald C. Wunsch, Ronald G. Harley
Electrical and Computer Engineering Faculty Research & Creative Works
Based on derivative adaptive critics, neurocontrollers for excitation and turbine control of multiple generators on the electric power grid are presented. The feedback variables are completely based on local measurements. Simulations on a three-machine power system demonstrate that the neurocontrollers are much more effective than conventional PID controllers, the automatic voltage regulators and the governors, for improving the dynamic performance and stability under small and large disturbances
A Committee Of Neural Networks For Automatic Speaker Recognition (Asr) Systems, Viresh Moonasar, Ganesh K. Venayagamoorthy
A Committee Of Neural Networks For Automatic Speaker Recognition (Asr) Systems, Viresh Moonasar, Ganesh K. Venayagamoorthy
Electrical and Computer Engineering Faculty Research & Creative Works
This paper describes how the results of speaker verification systems can be improved and made robust with the use of a committee of neural networks for pattern recognition rather than the conventional single-network decision system. It illustrates the use of a supervised learning vector quantization neural network as the pattern classifier. Linear predictive coding and cepstral signal processing techniques are utilized to form hybrid feature parameter vectors to combat the effect of decreased recognition success with increased group size (number of speakers to be recognized)
A Parallel Computer-Go Player, Using Hdp Method, Donald C. Wunsch, Xindi Cai
A Parallel Computer-Go Player, Using Hdp Method, Donald C. Wunsch, Xindi Cai
Electrical and Computer Engineering Faculty Research & Creative Works
The game of Go has simple rules to learn but requires complex strategies to play well, and, the conventional tree search algorithm for computer games is not suited for Go program. Thus, the game of Go is an ideal problem domain for machine learning algorithms. This paper examines the performance of a 19x19 computer Go player, using heuristic dynamic programming (HDP) and parallel alpha-beta search. The neural network based Go player learns good Go evaluation functions and wins about 30% of the games in a test series on 19x19 board
Two Separate Continually Online Trained Neurocontrollers For Excitation And Turbine Control Of A Turbogenerator, Ganesh K. Venayagamoorthy, Ronald G. Harley
Two Separate Continually Online Trained Neurocontrollers For Excitation And Turbine Control Of A Turbogenerator, Ganesh K. Venayagamoorthy, Ronald G. Harley
Electrical and Computer Engineering Faculty Research & Creative Works
This paper presents the design of two separate continually online trained (GOT) artificial neural network (ANN) controllers for excitation and turbine control of a turbogenerator connected to the infinite bus through a transmission line. These neurocontrollers augment/replace the conventional automatic voltage regulator and the turbine governor of a generator. A third COT ANN is used to identify the complex nonlinear dynamics of the power system. Results are presented to show that the two COT ANN controllers can control turbogenerators under steady state as well as transient conditions and thus allow turbogenerators to operate more closely to their steady state stability …
Efficient Training Techniques For Classification With Vast Input Space, Donald C. Wunsch, Emad W. Saad, J. J. Choi, J. L. Vian
Efficient Training Techniques For Classification With Vast Input Space, Donald C. Wunsch, Emad W. Saad, J. J. Choi, J. L. Vian
Electrical and Computer Engineering Faculty Research & Creative Works
Strategies to efficiently train a neural network for an aerospace problem with a large multidimensional input space are developed and demonstrated. The neural network provides classification for over 100,000,000 data points. A query-based strategy is used that initiates training using a small input set, and then augments the set in multiple stages to include important data around the network decision boundary. Neural network inversion and oracle query are used to generate the additional data, jitter is added to the query data to improve the results, and an extended Kalman filter algorithm is used for training. A causality index is discussed …
Fed-Batch Dynamic Optimization Using Generalized Dual Heuristic Programming, Donald C. Wunsch, M. S. Iyer
Fed-Batch Dynamic Optimization Using Generalized Dual Heuristic Programming, Donald C. Wunsch, M. S. Iyer
Electrical and Computer Engineering Faculty Research & Creative Works
Traditionally fed-batch biochemical process optimization and control uses complicated theoretical off-line optimizers, with no online model adaptation or re-optimization. This study demonstrates the applicability, effectiveness, and economic potential of a simple phenomenological model for modeling, and an adaptive critic design, generalized dual heuristic programming, for online re-optimization and control of an aerobic fed-batch fermentor. The results are compared with those obtained using a heuristic random optimizer
A Continually Online Trained Artificial Neural Network Identifier For A Turbogenerator, Ganesh K. Venayagamoorthy, Ronald G. Harley
A Continually Online Trained Artificial Neural Network Identifier For A Turbogenerator, Ganesh K. Venayagamoorthy, Ronald G. Harley
Electrical and Computer Engineering Faculty Research & Creative Works
The increasing complexity of modern power systems highlights the need for advanced modelling techniques for effective control of power systems. This paper presents results of simulation and practical studies carried out on identifying the dynamics of a single turbogenerator connected to an infinite bus through a short transmission line, using a continually online trained (COT) artificial neural network (ANN).
A Robust Artificial Neural Network Controller For A Turbogenerator When Line Configuration Changes, Ganesh K. Venayagamoorthy, Ronald G. Harley
A Robust Artificial Neural Network Controller For A Turbogenerator When Line Configuration Changes, Ganesh K. Venayagamoorthy, Ronald G. Harley
Electrical and Computer Engineering Faculty Research & Creative Works
This paper presents the design of a robust controller for a turbogenerator. The robust controller is an artificial neural network (ANN) that is trained offline on a family of ANN models of the turbogenerator. This ANN controller augments/replaces the traditional automatic voltage controller (AVR) and the turbine governor of the generator. Simulation results are presented to show that the ANN controller is robust when the transmission line configuration changes.
Comparative Study Of Stock Trend Prediction Using Time Delay, Recurrent And Probabilistic Neural Networks, Donald C. Wunsch, Emad W. Saad, Danil V. Prokhorov
Comparative Study Of Stock Trend Prediction Using Time Delay, Recurrent And Probabilistic Neural Networks, Donald C. Wunsch, Emad W. Saad, Danil V. Prokhorov
Electrical and Computer Engineering Faculty Research & Creative Works
Three networks are compared for low false alarm stock trend predictions. Short-term trends, particularly attractive for neural network analysis, can be used profitably in scenarios such as option trading, but only with significant risk. Therefore, we focus on limiting false alarms, which improves the risk/reward ratio by preventing losses. To predict stock trends, we exploit time delay, recurrent, and probabilistic neural networks (TDNN, RNN, and PNN, respectively), utilizing conjugate gradient and multistream extended Kalman filter training for TDNN and RNN. We also discuss different predictability analysis techniques and perform an analysis of predictability based on a history of daily closing …
A Practical Continually Online Trained Artificial Neural Network Controller For A Turbogenerator, Ganesh K. Venayagamoorthy, Ronald G. Harley
A Practical Continually Online Trained Artificial Neural Network Controller For A Turbogenerator, Ganesh K. Venayagamoorthy, Ronald G. Harley
Electrical and Computer Engineering Faculty Research & Creative Works
This paper reports on the simulation and practical studies carried out on a single turbogenerator connected to an infinite bus through a short transmission line, with a continually online trained (COT) artificial neural network (ANN) controller to identify the turbogenerator, and another COT ANN to control the turbogenerator. This identifier/controller augments/replaces the automatic voltage regulator and the turbine governor. Results are presented to show that this COT ANN identifier/controller has the potential to allow turbogenerators to operate more closely to their steady-state stability limits and nevertheless “ride through” severe transient disturbances such as three phase faults. This allows greater usage …