Filters








1,671 Hits in 5.7 sec

Adaptive inverse control of linear and nonlinear systems using dynamic neural networks

G.L. Plett
2003 IEEE Transactions on Neural Networks  
Second, the dynamic response of the system is controlled using an adaptive feedforward controller.  ...  No direct feedback is used, except that the system output is monitored and used by an adaptive algorithm to adjust the parameters of the controller.  ...  Structure of a Dynamic Neural Network An adaptive filter has an input , an output , and a "special input" called the desired response.  ... 
doi:10.1109/tnn.2003.809412 pmid:18238019 fatcat:cmjjz67ykrg5hev25quhuokuvq

FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling

A. D. Back, A. C. Tsoi
1991 Neural Computation  
In one way or the other, all these approaches attempt to incorporate some kind of contextual information (in our case, the dynamic nature of the problem is the context required) in a neural network structure  ...  Note that this type of network is still globally feedforward in nature, in that it has a global feedforward structure, with possibly local recurrent features (for IIR synapses).  ... 
doi:10.1162/neco.1991.3.3.375 fatcat:fg24q7yurvc3lhtj5hpn6emnxe

Adaptive neural control for space structure vibration suppression

Larry Davis, David Hyland, Gary Yen, Alok Das
1999 Smart materials and structures (Print)  
The adaptive neural control (ANC) program is part of an effort to develop neural network based controllers capable of self-optimization, on-line adaptation and autonomous fault detection and control recovery  ...  The first, basic phase focused on the development of efficient and completely autonomous neural network feedforward control for the case of broadband disturbances.  ...  The work reported here is part of an effort to analytically design and experimentally validate an innovative adaptive controllers based on neural network technology that is capable of self-optimization  ... 
doi:10.1088/0964-1726/8/6/305 fatcat:i7iyogynm5dttbyv7xitqqonom

Data-based construction of feedback-corrected nonlinear prediction model using feedback neural networks

Yangdong Pan, Su W Sung, Jay H Lee
2001 Control Engineering Practice  
The recurrent feedback neural network structure takes the form of a nonlinear state estimator, which can compactly represent a multivariable dynamic system with stochastic inputs.  ...  A dynamic learning algorithm for training the recurrent neural network has been developed.  ...  Fig. 2 . 2 The neural network structure representing an EKF studied by Suykens et al. (1995) . Fig. 4 . 4 Creating the nonlinear state estimator by two feedforward neural networks.  ... 
doi:10.1016/s0967-0661(01)00050-8 fatcat:t5di7wxebngrbkaioaz4aobmja

Neurocomputing in Civil Infrastructure

Juan P. Amezquita-Sanchez, Martin Valtierra-Rodriguez, Mais Aldwaik, Hojjat Adeli
2016 Scientia Iranica. International Journal of Science and Technology  
This article presents a review of the recent applications of Arti cial Neural Networks (ANN) for civil infrastructure including structural system identi cation, structural health monitoring, structural  ...  The most common ANN used in structural engineering is the backpropagation neural network followed by recurrent neural networks and radial basis function neural networks.  ...  Wang and Adeli [73] presented an adaptive control algorithm for nonlinear vibration control of large structures subjected to dynamic loading.  ... 
doi:10.24200/sci.2016.2301 fatcat:f35gtppgofaojkbertgsowsi24

Vibration control of structures with interferometric sensor non-linearity

Do-Hyung Kim, Jae-Hung Han, Dae-Hyun Kim, In Lee
2003 Smart materials and structures (Print)  
Experimental studies on vibration control of a composite beam with a piezoelectric actuator and an extrinsic Fabry-Perot interferometer (EFPI) have been performed using a neural network controller.  ...  Because of their interferometric characteristics, EFPI sensors show non-linearity as dynamic amplitude increases.  ...  Acknowledgment The present study has been supported by a grant from the National Research Laboratory Program of the Ministry of Science and Technology, Korea.  ... 
doi:10.1088/0964-1726/13/1/011 fatcat:64k5hsiuabczrepdtuisggexdu

An Introduction to the Echo State Network and its Applications in Power System

Jing Dai, Ganesh K. Venayagamoorthy, Ronald G. Harley
2009 2009 15th International Conference on Intelligent System Applications to Power Systems  
Echo State Network (ESN) is a new type of Recurrent Neural Network (RNN) proposed in recent years.  ...  area monitoring, intelligent control of an Active Power Filter (APF), overhead conductor thermal dynamics identification, wind speed or water inflow forecasting, etc.  ...  Recurrent neural networks (RNNs) have advantages over feedforward neural networks in terms of modeling dynamic systems with their dynamic memory and time embedding capabilities; however, the application  ... 
doi:10.1109/isap.2009.5352913 fatcat:l2beszijgnaj5awfuodb4nwday

State-of-the-art in control engineering

Štefan Kozák
2014 Journal of Electrical Systems and Information Technology  
Main ideas covered in this paper are motivated namely by the development of new advanced control engineering methods (predictive, hybrid predictive, optimal, adaptive, robust, fuzzy logic, and neural network  ...  Present trends in the complex process control design demand an increasing degree of integration of numerical mathematics, control engineering methods, new control structures based of distribution, embedded  ...  Acknowledgment The work on this paper was supported by the Scientific Grant Agency of the Ministry of Education, Science and Sports of the Slovak Republic under grant No 1/0973/14, and by the Slovak Research  ... 
doi:10.1016/j.jesit.2014.03.002 fatcat:hxcl5r2325eljcguo54p5lj53i

ARTIFICIAL NEURAL NETWORK AND ITS APPLICATIONS IN THE ENERGY SECTOR – AN OVERVIEW

Damilola Elizabeth Babatunde, Ambrose Anozie, James Omoleye
2020 International Journal of Energy Economics and Policy  
This article provides an overview of AI, chronological blueprints of the emergence of artificial neural networks (ANNs) and some of its applications in the energy sector.  ...  problems even in the areas of modeling, control, and optimization, to mention a few.  ...  The authors acknowledge and appreciate the financial support received from the management of Covenant University towards the publication of this article.  ... 
doi:10.32479/ijeep.8691 fatcat:xkkqiwjfvbebhhwfl4v5r4nccq

Implementing Real-Time Gain Optimization in a Multi-Agent System Designed for Optimized Multiobjective Power Plant Control

Jason D. Head, Jason R. Gomes, Craig S. Williams, Kwang Y. Lee
2011 IFAC Proceedings Volumes  
, such as training and adapting artificial neural network models, parameter optimization, and system monitoring.  ...  The multi-agent system approach to power plant control provides many benefits in that it allows multiple computationally intensive tasks to be performed in parallel to provide effective real-time control  ...  With the implementation of neural networks into the system, another goal will be to develop the Neural Network agent, as the Neural Network agent is crucial to the self-adaptability of the neural network  ... 
doi:10.3182/20110828-6-it-1002.03737 fatcat:f5hkfesg7fhtdapxdsfwbtvrhy

Model predictive control using neural networks

1995 IEEE Control Systems  
We use a feedforward neural network as the nonlinear prediction model in an extended DMC-algorithm to control the pH-value.  ...  Thus, no a priori information about the dynamics of the plant and no special operating conditions of the plant were needed to design the controller.  ...  The Neural Network and Training Algorithm Topology For the prediction of the behavior of the neutralization reactor, we chose a feedforward network with sigmoid activation functions.  ... 
doi:10.1109/37.466261 fatcat:vpxyowi2evftrd2cbi2jaxptf4

Intelligent distributed simulation and control of power plants

K.Y. Lee, M. Perakis, D.R. Sevcik, N.I. Santoso, G.K. Lauslerer, T. Samad
2000 IEEE transactions on energy conversion  
This paper presents summaries of five research and development activities in intelligent distributed simulation and control of power plants which were presented in a panel session of the same name at the  ...  Each of the panelists discussed methods of how they have incorporated intelligent systems techniques into their research and development efforts in power plant control.  ...  One area is the utilization of diagonal recurrent neural networks (DRNN) for dynamic systems control [9] .  ... 
doi:10.1109/60.849126 fatcat:iraye4y37bdxnaih32owa77k3m

Validation of Infinite Impulse Response Multilayer Perceptron for Modelling Nuclear Dynamics

F. Cadini, E. Zio, N. Pedroni
2008 Science and Technology of Nuclear Installations  
In this paper, the nonlinear modeling capabilities of an infinite impulse response multilayer perceptron (IIR-MLP) for nuclear dynamics are considered in comparison to static modeling by a finite impulse  ...  Artificial neural networks are powerful algorithms for constructing nonlinear empirical models from operational data.  ...  As a fact, artificial neural networks are being used with increasing frequency as an alternative to traditional models in a variety of engineering applications including monitoring, prediction, diagnostics  ... 
doi:10.1155/2008/681890 fatcat:dbkqgqegrjd6jpwqooxme53vc4

Neural network approach for predicting drum pressure and level in coal-fired subcritical power plant

Eni Oko, Meihong Wang, Jie Zhang
2015 Fuel  
The model can be used for studying plant dynamics and design of controllers. Dynamic model of the drum-boiler was developed in this study using NARX neural networks.  ...  As a result, data-driven approach based on neural networks is chosen in this study.  ...  Most of the studies so far on application of neural networks in boiler modelling either as stand-alone or as a component of a thermal power plant are based on feedforward neural networks.  ... 
doi:10.1016/j.fuel.2015.01.091 fatcat:kb6ul65u6vfibf72lgr4qif5nu

Multimodal Control by Variable-Structure Neural Network Modeling for Coagulant Dosing in Water Purification Process

Jun Zhang, Da-Yong Luo
2020 Complexity  
In this paper, combined with rule base, through the PCA method, an improved multimodal variable-structure random-vector neural network algorithm (MM-P-VSRVNN) is proposed for coagulant dosing, which is  ...  Stochastic neural network has the characteristics of good global convergence and fast gradient-based learning ability.  ...  Acknowledgments is study was funded by the Natural Science Foundation of Hunan Province (Grant no. 2018JJ3891).  ... 
doi:10.1155/2020/5392417 fatcat:vzb3gqmi5bfzdbgf7yndqsp42m
« Previous Showing results 1 — 15 out of 1,671 results