A demonstration of using the model reference principle to develop the function-oriented adaptive pulse-coded neural network

SIMULATION ◽  
2019 ◽  
Vol 96 (2) ◽  
pp. 207-219
Author(s):  
B Lungsi Sharma ◽  
Richard B Wells
Keyword(s):  
Neural Network ◽  
Descent Method ◽  
Design Tool ◽  
Steepest Descent Method ◽  
Network Systems ◽  
Model Reference ◽  
Physiological Models ◽  
Psychological Phenomena ◽  
Simple Mapping

How can one design an adaptive pulsed neural network that is based on psycho-phenomenological foundations? In other words, how can one migrate the adaptive capability of a psychologically modeled neural network to a pulsed network? Neural networks that model psychological phenomena are at a larger scale than physiological models. There is a common presumption that pulse-coded neural network analogs to non-pulsing networks can be obtained by a simple mapping and scaling process of some sort. But the actual in vivo environment of pulse-coded neural network systems produces a much more diverse set of firing patterns. Thus, functional mapping from traditional neural network systems to pulse-coded neural network systems is much more challenging than has been presumed. This paper demonstrates that the employment of model reference adaptation as a method for applying scientific reduction is a powerful design tool for the development of a function-oriented adaptive pulse-coded neural network. The performance surface is empirically obtained by comparing the performance of the pulsed network to the non-pulsing network. Based on this surface, the adaptive algorithm is a combination of gain scheduling and steepest-descent method. Therefore, the adaptive property of the pulse-coded neural network is built upon a psycho-physiological foundation.

The Adaptive Ship Motion Control Based on Fuzzy Neural Network

2011 ◽  
Vol 135-136 ◽  
pp. 989-994 ◽  
Author(s):  
Guan Shan Hu ◽  
Hai Rong Xiao
Keyword(s):  
Neural Network ◽  
Adaptive Control ◽  
Motion Control ◽  
Reference Model ◽  
Tracking System ◽  
Good Control ◽  
Ship Motion ◽  
Network Systems ◽  
Model Reference ◽  
Model Reference Adaptive

Given the uncertainty of parameters and the random nature of disturbance, a ship motion, is a complicated control problem. This paper has researched adaptive neural network systems and its application to ship’s motion control. In paper, Ship’s mathematical model is researched. Aimed at ship mathematical motion model, the model reference adaptive auto pilot is first designed based on the analysis of the model reference adaptive control theory. We used fuzzy logic and neural networks to design the feedback controller, used multilayer perceptron neural network to design the reference model and the ship course identification model network. Based on the fuzzy control and neural network, an intelligent adaptive control algorithm was presented in the paper. In consideration of the forces and moments from the environmental disturbance, such as winds, waves, currents, etc., Simulation experiments are carried out by using Matlab’s Simulink toolbox. The simulating result indicates the designed adaptive controller can get a good control performance for ship course tracking system.

RELATIONSHIP BETWEEN A FUZZY LOGIC AND A STEEPEST DESCENT APPROACH TO OPTIMIZE A FEEDFORWARD ARTIFICIAL NEURAL NETWORK CONFIGURATION

1994 ◽  
Vol 05 (04) ◽  
pp. 299-312
Author(s):  
ROBERT N. SHARPE ◽  
MO-YUEN CHOW
Keyword(s):  
Neural Network ◽  
Fuzzy Logic ◽  
Mathematical Models ◽  
Cost Function ◽  
Evaluation Criteria ◽  
Descent Method ◽  
Steepest Descent ◽  
Steepest Descent Method ◽  
Network Configuration ◽  
Training Time

The neural network designer must take into consideration many factors when selecting an appropriate network configuration. The performance of a given network configuration is influenced by many different factors such as: accuracy, training time, sensitivity, and the number of neurons used in the implementation. Using a cost function based on the four criteria mentioned previously, the various network paradigms can be evaluated relative to one another. If the mathematical models of the evaluation criteria as functions of the network configuration are known, then traditional techniques (such as the steepest descent method) could be used to determine the optimal network configuration. The difficulty in selecting an appropriate network configuration is due to the difficulty involved in determining the mathematical models of the evaluation criteria. This difficulty can be avoided by using fuzzy logic techniques to perform the network optimization as opposed to the traditional techniques. Fuzzy logic avoids the need of a detailed mathematical description of the relationship between the network performance and the network configuration, by using heuristic reasoning and linguistic variables. A comparison will be made between the fuzzy logic approach and the steepest descent method for the optimization of the cost function. The fuzzy optimization procedure could be applied to other systems where there is a priori information about their characteristics.

AN Improved RBF Neural Network Model Based on Hybrid Learning Algorithm

2013 ◽  
Vol 718-720 ◽  
pp. 2202-2207
Author(s):  
Zhao Hu Deng ◽  
Yan Qin Zhang
Keyword(s):  
Neural Network ◽  
Traditional Method ◽  
Learning Algorithm ◽  
Rbf Neural Network ◽  
Clustering Algorithms ◽  
Hybrid Learning ◽  
Descent Method ◽  
Learning Ability ◽  
Steepest Descent Method ◽  
Training Samples

When building the radial basis function (RBF) neural network with traditional method, the property of the network is easily influenced by the distribution of training samples. The learning ability and generalization ability are hard to achieve the optimum. In this paper, it presents a new method to solve this problem. In the method it replaced the traditional clustering algorithms with genetic algorithms to optimize the distribution of RBF. At the same time it combined the steepest descent method with GA to solve the binary defect of GA encoding. After experiments the results showed that the constructed neural network has a better architecture and more accuracy than that built with traditional method.

scholarly journals Hessian with Mini-Batches for Electrical Demand Prediction

2020 ◽  
Vol 10 (6) ◽  
pp. 2036 ◽  
Author(s):  
Israel Elias ◽  
José de Jesús Rubio ◽  
David Ricardo Cruz ◽  
Genaro Ochoa ◽  
Juan Francisco Novoa ◽  
...  
Keyword(s):  
Neural Network ◽  
Descent Method ◽  
Steepest Descent ◽  
Steepest Descent Method ◽  
Demand Prediction ◽  
The Neural Network ◽  
Electrical Demand

The steepest descent method is frequently used for neural network tuning. Mini-batches are commonly used to get better tuning of the steepest descent in the neural network. Nevertheless, steepest descent with mini-batches could be delayed in reaching a minimum. The Hessian could be quicker than the steepest descent in reaching a minimum, and it is easier to achieve this goal by using the Hessian with mini-batches. In this article, the Hessian is combined with mini-batches for neural network tuning. The discussed algorithm is applied for electrical demand prediction.

scholarly journals Modified neural network based cascaded control for product composition of reactive distillation

2016 ◽  
Vol 18 (2) ◽  
pp. 111-121 ◽  
Author(s):  
Vandana Sakhre ◽  
Sanjeev Jain ◽  
V. S. Sapkal ◽  
D.P. Agarwal
Keyword(s):  
Neural Network ◽  
Mean Square Error ◽  
Control Strategy ◽  
Reactive Distillation ◽  
Descent Method ◽  
Steepest Descent ◽  
Steepest Descent Method ◽  
Mean Square ◽  
Loop Control ◽  
Single Loop

Abstract In this research work, neural network based single loop and cascaded control strategies, based on Feed Forward Neural Network trained with Back Propagation (FBPNN) algorithm is carried out to control the product composition of reactive distillation. The FBPNN is modified using the steepest descent method. This modification is suggested for optimization of error function. The weights connecting the input and hidden layer, hidden and output layer is optimized using steepest descent method which causes minimization of mean square error and hence improves the response of the system. FBPNN, as the inferential soft sensor is used for composition estimation of reactive distillation using temperature as a secondary process variable. The optimized temperature profile of the reactive distillation is selected as input to the neural network. Reboiler heat duty is selected as a manipulating variable in case of single loop control strategy while the bottom stage temperature T9 is selected as a manipulating variable for cascaded control strategy. It has been observed that modified FBPNN gives minimum mean square error. It has also been observed from the results that cascaded control structure gives improved dynamic response as compared to the single loop control strategy.

ACTIVE HEAT DISSIPATION SYSTEM USING ADAPTIVE RECURRENT WAVELET NEURAL NETWORK CONTROL

2016 ◽  
Vol 40 (4) ◽  
pp. 445-456
Author(s):  
Yung-Lung Lee ◽  
Shou-Jen Hsu ◽  
Yen-Bin Chen
Keyword(s):  
Neural Network ◽  
Pid Control ◽  
Heat Dissipation ◽  
Intelligent System ◽  
Descent Method ◽  
Wavelet Neural Network ◽  
Steepest Descent Method ◽  
Neural Network Controller ◽  
Network Controller ◽  
Voltage Saturation

This paper proposes a novel cooling control system with the intelligent active technique, which is based on the NI-PXI systems structure combined with the heat pipe cooling chips. In order to further solve the controlling problems of nonlinear heat transfer system, the proposed intelligent system involves the PID control, traditional control, and the adaptive recurrent wavelet neural network controller (ARWNNC) control techniques. The traditional control there exists the undesirable control chattering, The PID control the Response of Control cannot be processed immediately and the input voltage saturation phenomenon, the adaptive recurrent wavelet neural network controller, is employed to approximate the ideal controller, while the corresponding parameters are derived by the gradient steepest descent method, thus being provided with the adaptive real-time control ability.

Research of FWP Process Deformation Compensation Forecasting on the Basis of TS-FNN

2011 ◽  
Vol 295-297 ◽  
pp. 2430-2437 ◽  
Author(s):  
Yao Hua Deng ◽  
Gui Xiong Liu ◽  
Qing Fu Liao ◽  
Lei Zeng ◽  
Li Ming Wu
Keyword(s):  
Neural Network ◽  
Rbf Neural Network ◽  
Descent Method ◽  
Steepest Descent Method ◽  
National Standard ◽  
Function Parameter ◽  
Parameter Study ◽  
Network Parameter ◽  
Fuzzy Neural ◽  
Order Of Magnitude

After analyzing the influencing factors of flexible workpiece path(FWP) process deformation, this article proposes the basic conception of process deformation intelligent forecasting and compensation, start from the process modeling method of Takagi-Sugeno fuzzy neural network, to modify the classic FNN model and construct the multiple input/output TS-FNN model for FWP process control; with LMS law and steepest descent method, antecedent network membership function parameter adjustment and descent network parameter study method of TS-FNN model is deduced; finally to carry on comprehensive simulation on TS-FNN model, the result shows the constructed model is better than BP neural network and RBF neural network for an order of magnitude on predication accuracy; in the quilting process of flexible objects, compensated by TS-FNN, the path processing obtains good approaching effect, testing result indicates that the position error scope of quilting is from 0.078 to 0.162(mm), the accuracy is higher than excellence grade of quilting which refers to national standard FZ/T81005-2006.

Sign in / Sign up

Export Citation Format

Share Document