scholarly journals Nonlinear Aeroelastic System Identification Based on Neural Network

2018 ◽  
Vol 8 (10) ◽  
pp. 1916
Author(s):  
Bo Zhang ◽  
Jinglong Han ◽  
Haiwei Yun ◽  
Xiaomao Chen
Keyword(s):  
Neural Network ◽  
Time Delay ◽  
System Identification ◽  
Control Surface ◽  
Identification Algorithm ◽  
Aeroelastic System ◽  
Structural Nonlinearity ◽  
Time Marching ◽  
Artificial Neural Network Ann ◽  
Trained Neural Network

This paper focuses on the nonlinear aeroelastic system identification method based on an artificial neural network (ANN) that uses time-delay and feedback elements. A typical two-dimensional wing section with control surface is modelled to illustrate the proposed identification algorithm. The response of the system, which applies a sine-chirp input signal on the control surface, is computed by time-marching-integration. A time-delay recurrent neural network (TDRNN) is employed and trained to predict the pitch angle of the system. The chirp and sine excitation signals are used to verify the identified system. Estimation results of the trained neural network are compared with numerical simulation values. Two types of structural nonlinearity are studied, cubic-spring and friction. The results indicate that the TDRNN can approach the nonlinear aeroelastic system exactly.

Fuzzy control of nonlinear aeroelastic system based on neural network identification

2021 ◽  
pp. 095441002110109
Author(s):  
Bo Zhang ◽  
Jing-Long Han ◽  
Hai-Wei Yun ◽  
Xiao-Mao Chen
Keyword(s):  
Neural Network ◽  
Fuzzy Control ◽  
Control Method ◽  
Free Play ◽  
Control Surface ◽  
Limit Cycle Oscillation ◽  
Identification Algorithm ◽  
Aeroelastic System ◽  
Network Identification ◽  
Cycle Oscillation

This article presents a fuzzy control method for the limit cycle oscillation (LCO) suppression of nonlinear aeroelastic systems based on the neural network identification algorithm. A prototypical 2D wing section with a single control surface at the trailing edge of the main wing, which contains a symmetrical free play nonlinearity in the pitch degree of freedom, is modeled to illustrate the proposed method. A neural network is used to identify the fuzzy control rules from the existing LCO suppression input and output data. A new fuzzy control rate of the nonlinear aeroelastic system is obtained by adjusting the parameters of the fuzzy control surface. Numerical simulations are conducted to verify the effectiveness of the proposed method.

Conjugate Gradient Trained Neural Network for Intelligent Sensing of Manhole Gases to Avoid Human Fatality

2014 ◽  
pp. 257-280
Author(s):  
Paramartha Dutta ◽  
Varun Kumar Ojha
Keyword(s):  
Neural Network ◽  
Conjugate Gradient ◽  
Learning Algorithm ◽  
Real Life ◽  
Nonlinear Problems ◽  
Pipeline System ◽  
Neural Network Learning ◽  
Pattern Recognition Problem ◽  
Artificial Neural Network Ann ◽  
Trained Neural Network

Computational Intelligence offers solution to various real life problems. Artificial Neural Network (ANN) has the capability of solving highly complex and nonlinear problems. The present chapter demonstrates the application of these tools to provide solutions to the manhole gas detection problem. Manhole, the access point across sewer pipeline system, contains various toxic and explosive gases. Hence, predetermination of these gases before accessing manholes is becoming imperative. The problem is treated as a pattern recognition problem. ANN, devised for solving this problem, is trained using a supervised learning algorithm. The conjugate gradient method is used as an alternative of back propagation neural network learning algorithm for training of the ANN. The chapter offers comprehensive performance analysis of the learning algorithm used for the training of ANN followed by discussion on the methods of presenting the system result. The authors discuss different variants of Conjugate Gradient and propose two new variants of it.

A Genetic Algorithm-Artificial Neural Network Method for the Prediction of Longitudinal Dispersion Coefficient in Rivers

2011 ◽  
pp. 358-374
Author(s):  
Jianhua Yang ◽  
Evor L. Hines ◽  
Ian Guymer ◽  
Daciana D. Iliescu ◽  
Mark S. Leeson ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Dispersion Coefficient ◽  
Longitudinal Dispersion ◽  
Longitudinal Dispersion Coefficient ◽  
Artificial Neural ◽  
Input Variables ◽  
Training Examples ◽  
Artificial Neural Network Ann ◽  
Trained Neural Network

In this chapter a novel method, the Genetic Neural Mathematical Method (GNMM), for the prediction of longitudinal dispersion coefficient is presented. This hybrid method utilizes Genetic Algorithms (GAs) to identify variables that are being input into a Multi-Layer Perceptron (MLP) Artificial Neural Network (ANN), which simplifies the neural network structure and makes the training process more efficient. Once input variables are determined, GNMM processes the data using an MLP with the back-propagation algorithm. The MLP is presented with a series of training examples and the internal weights are adjusted in an attempt to model the input/output relationship. GNMM is able to extract regression rules from the trained neural network. The effectiveness of GNMM is demonstrated by means of case study data, which has previously been explored by other authors using various methods. By comparing the results generated by GNMM to those presented in the literature, the effectiveness of this methodology is demonstrated.

Prediction of Surface Roughness and Coefficient of Friction Using Artificial Neural Network in Tribotesting of Bio-Lubricants

2019 ◽  
Vol 895 ◽  
pp. 52-57 ◽  
Author(s):  
Prasanna Vineeth Bharadwaj ◽  
T.P. Jeevan ◽  
P.S. Suvin ◽  
S.R. Jayaram
Keyword(s):  
Neural Network ◽  
Surface Roughness ◽  
Artificial Neural Network ◽  
Coefficient Of Friction ◽  
Ann Model ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Trained Neural Network ◽  
Lubrication Conditions ◽  
Good Agreement

Tribotesting is necessary to understand the behaviour of the material under various operating lubrication conditions. This paper deals with the training of an artificial neural network (ANN) model with Bio-lubricant properties and machining conditions for prediction of surface roughness and coefficient of friction in Tribotesting by Tool chip Tribometer. Experimental results obtained from Tool chip tribometer for tested bio-lubricants are compared with those obtained by ANN prediction. A good agreement in results recommends that a well trained neural network is competent enough to predict the parameters in Tribotesting process.

Sedimentation Load Analysis Using ANN and GA

2011 ◽  
Vol 110-116 ◽  
pp. 2693-2698 ◽  
Author(s):  
Dillip Kumar Ghose ◽  
P.C. Swain ◽  
Sudhansu Sekhar Panda
Keyword(s):  
Neural Network ◽  
Process Parameters ◽  
Water Discharge ◽  
Load Condition ◽  
Optimal Level ◽  
Daily Basis ◽  
Ann Model ◽  
Artificial Neural Network Ann ◽  
Trained Neural Network ◽  
The Given

Artificial Neural Network (ANN) model is used to predict the suspended sediment load for the survey data collected on daily basis in the river Mahanadi. Genetic algorithm has been used to find the optimal level of process parameters such as water discharge and temperature for a minimum sedimentation load condition. Optimal level of process parameters obtained from the GA has been used in a trained neural network to obtain the sedimentation load condition. A comparative analysis is then made between GA and ANN for achieving minimum sedimentation load with the given process parameters.

The Modeling of Earnings Prediction by Time-Delay Neural Network

2012 ◽  
Vol 433-440 ◽  
pp. 907-911 ◽  
Author(s):  
Kao Yi Shen
Keyword(s):  
Neural Network ◽  
Data Structure ◽  
Time Delay ◽  
Investment Decisions ◽  
Complex Data ◽  
Ann Model ◽  
Learning Capability ◽  
Future Earnings ◽  
Earnings Prediction ◽  
Artificial Neural Network Ann

Although the use of earnings prediction in supporting investment decisions has been prevailing in practice, an accounting-based analysis for modeling the key accounting components by time-delay machine learning technique is unexplored. Traditional time-series techniques fail to handle complex data structure, and the fundamental analysis approach cannot model multiple periods’ data effectively. Thus, this study aims to explore the crucial relationships among future earnings and the main historical accounting components, i.e. cash-flow and accrual components. The research method leverages the flexible learning capability of artificial neural network (ANN) with time-delay data structure. The major findings suggested that adding accrual components is helpful for better earnings prediction, and the proposed 5-period time-delay ANN model may capture the future earnings in a positive way. The results of this study may help to support investment decisions and better understanding for the role of accruals in earnings.

Neural Q-Learning Based Mobile Robot Navigation

2012 ◽  
Vol 433-440 ◽  
pp. 721-726
Author(s):  
Soh Chin Yun ◽  
S. Parasuraman ◽  
Velappa Ganapathy ◽  
Halim Kusuma Joe
Keyword(s):  
Neural Network ◽  
Learning Algorithm ◽  
Mobile Robot Navigation ◽  
Matlab Simulation ◽  
Training Process ◽  
Q Learning ◽  
State Action ◽  
Training Samples ◽  
Artificial Neural Network Ann ◽  
Trained Neural Network

This research is focused on the integration of multi-layer Artificial Neural Network (ANN) and Q-Learning to perform online learning control. In the first learning phase, the agent explores the unknown surroundings and gathers state-action information through the unsupervised Q-Learning algorithm. Second training process involves ANN which utilizes the state-action information gathered in the earlier phase of training samples. During final application of the controller, Q-Learning would be used as primary navigating tool whereas the trained Neural Network will be employed when approximation is needed. MATLAB simulation was developed to verify and the algorithm was validated in real-time using Team AmigoBotTM robot. The results obtained from both simulation and real world experiments are discussed.

Sign in / Sign up

Export Citation Format

Share Document