Recursive Backpropagation Research Articles

Model Predictive Control of Nonlinear System Based on GA-RBP Neural Network and Improved Gradient Descent Method

A model predictive control (MPC) method based on recursive backpropagation (RBP) neural network and genetic algorithm (GA) is proposed for a class of nonlinear systems with time delays and uncertainties. In the offline modeling stage, a multistep-ahead predictor with GA-RBP neural network is designed, where GA-BP neural network is used as a one-step prediction model and GA is employed to train the initial weights and bias of the BP neural network. The incorporation of GA into RBP can reduce the possibility of the BP neural network falling into a local optimum instead of reaching global optimization. In the online optimizing stage, a multistep-ahead GA-RBP neural network predictor and an improved gradient descent method (IGDM) are proposed to efficiently solve the online optimization problem of nonlinear MPC by minimizing a modified quadratic criterion. The designed MPC strategy can avoid information loss while linearizing the controlled system and computing the Hessian matrix and its inverse matrix. Experimental results show that the proposed approach can reduce the computational burden and improve the performance of MPC (i.e., the maximum overshoots, calculation time, rise time, and RMSE tracking error value) for the solution of nonlinear controlled systems.

Detection and classification of various pest attacks and infection on plants using recursive backpropagation neural network with GA based particle swarm optimization algorithm

<p>Machine learning methodologies are commonly used in the field of<br />precession farming. It prospects greatly in the plant safety measure like<br />disease detection and classification of pest attacks. It highly influences the<br />crop production and management. The venture of our system is to produce<br />healthy plantation. The proposed system involves Enhanced Feature Fractal<br />Texture Analysis, Statistical Feature Selection and Machine Learning<br />methodology for classification. Hence more than ever there is a need for<br />such a tool that combines image processing methodologies and the Neural<br />network concepts and that is supported by huge cloud of structured data<br />which makes the diagnosis and classification part much easier and<br />convenient. The proposed system recognizes and classifies the plant<br />taxonomy and the infection based on the selected statistical features. The<br />neural network concept followed in our proposed system is focused on<br />Artificial Neural Network which uses Recursive Back Propagation Neural<br />network to speed up the training process as well as reduce multiclass<br />problem in the network and optimize the weights on hidden layers of the<br />Network using Genetic Algorithm based Particle Swarm Optimization<br />technique. We have used MATLAB to implement the concept and obtained<br />better accuracy in disease/pest detection and proved to be an efficient<br />method.</p>

Recurrent Neural Adaptive Control of Nonlinear Oscillatory Systems Using a Complex-valued Levenberg-Marquardt Learning Algorithm

Abstract In this work, a Recursive Levenberg-Marquardt learning algorithm in the complex domain is developed and applied in the training of two adaptive control schemes composed by Complex-Valued Recurrent Neural Networks. Furthermore, we apply the identification and both control schemes for a particular case of nonlinear, oscillatory mechanical plant to validate the performance of the adaptive neural controller and the learning algorithm. The comparative simulation results show the better performance of the newly proposed Complex-Valued Recursive Levenberg-Marquardt learning algorithm over the gradient-based recursive Back-propagation one.

MODELLING THE DYNAMICS OF THE LEAD BISMUTH EUTECTIC EXPERIMENTAL ACCELERATOR DRIVEN SYSTEM BY AN INFINITE IMPULSE RESPONSE LOCALLY RECURRENT NEURAL NETWORK

In this paper, an infinite impulse response locally recurrent neural network (IIR-LRNN) is employed for modelling the dynamics of the Lead Bismuth Eutectic eXperimental Accelerator Driven System (LBE-XADS). The network is trained by recursive back-propagation (RBP) and its ability in estimating transients is tested under various conditions. The results demonstrate the robustness of the locally recurrent scheme in the reconstruction of complex nonlinear dynamic relationships.

A VECTOR MATRIX REAL TIME RECURSIVE BACKPROPAGATION ALGORITHM FOR RECURRENT NEURAL NETWORKS THAT APPROXIMATE MULTI-VALUED PERIODIC FUNCTIONS

Unlike feedforward neural networks (FFNN) which can act as universal function approximators, recursive, or recurrent, neural networks can act as universal approximators for multi-valued functions. In this paper, a real time recursive backpropagation (RTRBP) algorithm in a vector matrix form is developed for a two-layer globally recursive neural network that has multiple delays in its feedback path. This algorithm has been evaluated on two GRNNs that approximate both an analytic and nonanalytic periodic multi-valued function that a feedforward neural network is not capable of approximating.

Nuclear reactor dynamics on-line estimation by Locally Recurrent Neural Networks

In this paper, the Causal Recursive Back-Propagation (CRBP) algorithm is employed to train on-line an Infinite Impulse Response–Locally Recurrent Neural Network (IIR–LRNN) for modelling the dynamics of a next-generation nuclear reactor. The results demonstrate the advantages of the on-line training over the batch-mode learning in the reconstruction of complex nonlinear dynamic relationships.

Simulating the dynamics of the neutron flux in a nuclear reactor by locally recurrent neural networks

In this paper, a locally recurrent neural network (LRNN) is employed for approximating the temporal evolution of a nonlinear dynamic system model of a simplified nuclear reactor. To this aim, an infinite impulse response multi-layer perceptron (IIR-MLP) is trained according to a recursive back-propagation (RBP) algorithm. The network nodes contain internal feedback paths and their connections are realized by means of IIR synaptic filters, which provide the LRNN with the necessary system state memory.

On-line learning algorithms for locally recurrent neural networks

This paper focuses on on-line learning procedures for locally recurrent neural networks with emphasis on multilayer perceptron (MLP) with infinite impulse response (IIR) synapses and its variations which include generalized output and activation feedback multilayer networks (MLN's). We propose a new gradient-based procedure called recursive backpropagation (RBP) whose on-line version, causal recursive backpropagation (CRBP), presents some advantages with respect to the other on-line training methods. The new CRBP algorithm includes as particular cases backpropagation (BP), temporal backpropagation (TBP), backpropagation for sequences (BPS), Back-Tsoi algorithm among others, thereby providing a unifying view on gradient calculation techniques for recurrent networks with local feedback. The only learning method that has been proposed for locally recurrent networks with no architectural restriction is the one by Back and Tsoi. The proposed algorithm has better stability and higher speed of convergence with respect to the Back-Tsoi algorithm, which is supported by the theoretical development and confirmed by simulations. The computational complexity of the CRBP is comparable with that of the Back-Tsoi algorithm, e.g., less that a factor of 1.5 for usual architectures and parameter settings. The superior performance of the new algorithm, however, easily justifies this small increase in computational burden. In addition, the general paradigms of truncated BPTT and RTRL are applied to networks with local feedback and compared with the new CRBP method. The simulations show that CRBP exhibits similar performances and the detailed analysis of complexity reveals that CRBP is much simpler and easier to implement, e.g., CRBP is local in space and in time while RTRL is not local in space.

Steepest descent algorithms for neural network controllers and filters

A number of steepest descent algorithms have been developed for adapting discrete-time dynamical systems, including the backpropagation through time and recursive backpropagation algorithms. In this paper, a tutorial on the use of these algorithms for adapting neural network controllers and filters is presented. In order to effectively compare and contrast the algorithms, a unified framework for the algorithms is developed. This framework is based upon a standard representation of a discrete-time dynamical system. Using this framework, the computational and storage requirements of the algorithms are derived. These requirements are used to select the appropriate algorithm for training a neural network controller or filter. Finally, to illustrate the usefulness of the techniques presented in this paper, a neural network control example and a neural network filtering example are presented.

Adaptive Optimal Operation of a Bioreactor Based on a Neural Net Model

This paper presents a novel approach to applying an on-line optimizing control strategy to a continuous fermentation process. The recursive backpropagation neural network (RBPN) identification algorithm with forgetting factor is proposed for the on-line modeling of the process. This technique has been successfully applied for the identification of nonlinear systems. This optimization technique is based on gradient information of the RBPN model. This technique increases the accuracy of the system optimization. Simulation studies of a continuous culture of baker’s yeast were performed to test RBPN model based adaptive optimization approach. The results show that the neural network model describes the nonlinear characteristics of the fermentation process very well. Also, this adaptive optimization strategy was able to keep the process operating at its optimum despite changes in process conditions. Further, a kinetic model is not required for the RBPN optimization approach, that is, the RBPN model can be developed directly from process data. Finally, it appears that this approach is quite general and can be applied to other processes.