Incipient wheel fault identification in mobile robots using neural networks and nonlinear least squares

2016 ◽  
Vol 231 (3) ◽  
pp. 446-458
Author(s):  
Ngoc-Bach Hoang ◽  
Hee-Jun Kang
Keyword(s):  
Neural Networks ◽  
Mobile Robots ◽  
Least Squares ◽  
Dynamic Model ◽  
Nonlinear Least Squares ◽  
Fault Identification ◽  
Robot Dynamics ◽  
The Neural Network ◽  
Network Output ◽  
Wheel Radius

In this paper, we present a novel method for fault identification in the case of an incipient wheel fault in mobile robots. First, a three-layer neural networks is established to estimate the deviation of the robot dynamics due to the process fault. The estimate of the faulty dynamic model is based on a combination of the nominal dynamic model and the neural network output. Then, by replacing the faulty dynamic model with its estimate value, the primary estimates of the wheel radius appear as the solutions of two quadratic equations. Next, a simple and efficient way to perform these primary estimate selections is proposed in order to eliminate undesired primary estimates. A recursive nonlinear least squares is applied in order to obtain a smooth estimate of the wheel radius. Two computer simulation examples using Matlab/Simulink show that the proposed method is very effective for incipient fault identification in the setting of both left and right wheel faults.

Sensor Dynamic Modeling Based on LS-SVM and NGA

2008 ◽  
Vol 381-382 ◽  
pp. 439-442
Author(s):  
Qi Wang ◽  
Zhi Gang Feng ◽  
K. Shida
Keyword(s):  
Genetic Algorithm ◽  
Neural Networks ◽  
Support Vector Machine ◽  
Least Squares ◽  
Dynamic Model ◽  
Dynamic Modeling ◽  
Support Vector ◽  
Local Minima ◽  
Highly Nonlinear ◽  
Sharing Function

Least squares support vector machine (LS-SVM) combined with niche genetic algorithm (NGA) are proposed for nonlinear sensor dynamic modeling. Compared with neural networks, the LS-SVM can overcome the shortcomings of local minima and over fitting, and has higher generalization performance. The sharing function based niche genetic algorithm is used to select the LS-SVM parameters automatically. The effectiveness and reliability of this method are demonstrated in two examples. The results show that this approach can escape from the blindness of man-made choice of LS-SVM parameters. It is still effective even if the sensor dynamic model is highly nonlinear.

CONTROL STRATEGIES FOR CHAOTIC NEUROMODULES

1996 ◽  
Vol 06 (04) ◽  
pp. 693-703 ◽  
Author(s):  
NICO STOLLENWERK ◽  
FRANK PASEMANN
Keyword(s):  
Least Squares ◽  
Chaotic Dynamics ◽  
Chaotic Systems ◽  
Least Squares Method ◽  
Control Strategies ◽  
Nonlinear Least Squares ◽  
The Neural Network ◽  
One Step ◽  
Nonlinear Least Squares Method ◽  
The One

Different strategies for control of chaotic systems are discussed: The well known Ott-Grebogi-Yorke algorithm and two alternative algorithms based on least-squares minimisation of the one step future deviation. To compare their effectiveness in the neural network context they are applied to a minimal two neuron module with discrete chaotic dynamics. The best method with respect to calculation effort, to neural implementation, and to controlling properties is the nonlinear least squares method. Furthermore, it is observed in simulations that one can stabilise a whole periodic orbit by applying the control signals only to one of its periodic points, which lies in a distinguished region of phase space.

The Effects of Adding Noise During Backpropagation Training on a Generalization Performance

1996 ◽  
Vol 8 (3) ◽  
pp. 643-674 ◽  
Author(s):  
Guozhong An
Keyword(s):  
Neural Networks ◽  
Objective Function ◽  
Feedforward Neural Networks ◽  
Classification Problem ◽  
Weight Changes ◽  
Generalization Performance ◽  
Input Noise ◽  
The Neural Network ◽  
Network Output ◽  
Noise Limit

We study the effects of adding noise to the inputs, outputs, weight connections, and weight changes of multilayer feedforward neural networks during backpropagation training. We rigorously derive and analyze the objective functions that are minimized by the noise-affected training processes. We show that input noise and weight noise encourage the neural-network output to be a smooth function of the input or its weights, respectively. In the weak-noise limit, noise added to the output of the neural networks only changes the objective function by a constant. Hence, it cannot improve generalization. Input noise introduces penalty terms in the objective function that are related to, but distinct from, those found in the regularization approaches. Simulations have been performed on a regression and a classification problem to further substantiate our analysis. Input noise is found to be effective in improving the generalization performance for both problems. However, weight noise is found to be effective in improving the generalization performance only for the classification problem. Other forms of noise have practically no effect on generalization.

scholarly journals Neural Networks-Based Identification and Control of a Large Flexible Antenna

2011 ◽  
Vol 2011 ◽  
pp. 1-8
Author(s):  
Minoru Sasaki ◽  
Takuya Murase ◽  
Yoshihiro Inoue ◽  
Nobuharu Ukita
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Nonlinear Dynamical System ◽  
Inverse Model ◽  
Nonlinear Dynamical ◽  
The Neural Network ◽  
Network Output ◽  
Flexible Antenna ◽  
Angle Encoder ◽  
And Control

This paper presents identification and control of a 10-m antenna via accelerometers and angle encoder data. Artificial neural networks can be used effectively for the identification and control of nonlinear dynamical system such as a large flexible antenna with a friction drive system. Some identification results are shown and compared with the results of conventional prediction error method. And we use a neural network inverse model to control the large flexible antenna. In the neural network inverse model, a neural network is trained, using supervised learning, to develop an inverse model of the antenna. The network input is the process output, and the network output is the corresponding process input. The control results show the validation of the ANN approach for identification and control of the 10-m flexible antenna.

scholarly journals NeurASP: Embracing Neural Networks into Answer Set Programming

2020 ◽  
Author(s):  
Zhun Yang ◽  
Adam Ishay ◽  
Joohyung Lee
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Symbolic Computation ◽  
Answer Set Programming ◽  
Simple Extension ◽  
Symbolic Reasoning ◽  
The Neural Network ◽  
Network Output ◽  
Trained Neural Network ◽  
Answer Set

We present NeurASP, a simple extension of answer set programs by embracing neural networks. By treating the neural network output as the probability distribution over atomic facts in answer set programs, NeurASP provides a simple and effective way to integrate sub-symbolic and symbolic computation. We demonstrate how NeurASP can make use of a pre-trained neural network in symbolic computation and how it can improve the neural network's perception result by applying symbolic reasoning in answer set programming. Also, NeurASP can make use of ASP rules to train a neural network better so that a neural network not only learns from implicit correlations from the data but also from the explicit complex semantic constraints expressed by the rules.

A Method about Load Distribution of Rolling Mills Based on RBF Neural Network

2011 ◽  
Vol 279 ◽  
pp. 418-422
Author(s):  
Dong Dong Liu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Load Distribution ◽  
Rolling Force ◽  
Rbf Neural Network ◽  
Rbf Neural Networks ◽  
Rolling Mills ◽  
The Neural Network ◽  
Network Output

Rolling mills process is too complicated to be described by formulas. RBF neural networks can establish finishing thickness and rolling force models. Traditional models are still useful to the neural network output. Compared with those finishing models which have or do not have traditional models as input, the importance of traditional models in application of neural networks is obvious. For improving the predictive precision, BP and RBF neural networks are established, and the result indicates that the model of load distribution based on RBF neural network is more accurate.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Sign in / Sign up

Export Citation Format

Share Document