Tracking Control of a Nonholonomic Mobile Robot Using Neural Network

The goal of this chapter is to enable a nonholonomic mobile robot to track a specified trajectory with minimum tracking error. Towards that end, an adaptive P controller is designed whose gain parameters are tuned by using two feed-forward neural networks. Back-propagation algorithm is chosen for online learning process and posture-tracking errors are considered as error values for adjusting weights of neural networks. The tracking performance of the controller is illustrated for different trajectories with computer simulation using Matlab/Simulink. In addition, open-loop response of an experimental mobile robot is investigated for these different trajectories. Finally, the performance of the proposed controller is compared to a standard PID controller. The simulation results show that “adaptive P controller using neural networks” has superior tracking performance at adapting large disturbances for the mobile robot.

Download Full-text

Hybrid algorithm for training feed-forward neural networks using PSO-information gain with back propagation algorithm

2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology ◽

10.1109/ecticon.2012.6254157 ◽

2012 ◽

Cited By ~ 3

Author(s):

Tanyawat Sanguanchue ◽

Kietikul Jearanaitanakij

Keyword(s):

Neural Networks ◽

Hybrid Algorithm ◽

Information Gain ◽

Back Propagation ◽

Back Propagation Algorithm ◽

Feed Forward ◽

Propagation Algorithm ◽

Feed Forward Neural Networks

Download Full-text

Multidimensional wavelet neural networks Based on polynomial powers of sigmoid

DAT Journal ◽

10.29147/2526-1789.dat.2016v1i2p106-123 ◽

2016 ◽

Vol 1 (2) ◽

pp. 106-123

Author(s):

João Fernando Marar ◽

Aron Bordin

Keyword(s):

Neural Network ◽

Neural Networks ◽

Back Propagation ◽

Activation Function ◽

Wavelet Neural Network ◽

Back Propagation Algorithm ◽

Wavelet Neural Networks ◽

Low Dimensionality ◽

Feed Forward Neural Networks ◽

Sigmoid Functions

Wavelet functions have been used as the activation function in feed forward neural networks. An abundance of R&D has been produced on wavelet neural network area. Some successful algorithms and applications in wavelet neural network have been developed and reported in the literature. However, most of the aforementioned reports impose many restrictions in the classical back propagation algorithm, such as low dimensionality, tensor product of wavelets, parameters initialization, and, in general, the output is one dimensional, etc. In order to remove some of these restrictions, a family of polynomial wavelets generated from powers of sigmoid functions is presented. We described how a multidimensional wavelet neural networks based on these functions can be constructed, trained and applied in pattern recognition tasks. As examples of applications for the method proposed a framework for face verfication is presented.

Download Full-text

On Training Of Feed Forward Neural Networks

Baghdad Science Journal ◽

10.21123/bsj.4.1.158-164 ◽

2007 ◽

Vol 4 (1) ◽

pp. 158-164

Author(s):

Baghdad Science Journal

Keyword(s):

Neural Networks ◽

Back Propagation ◽

Training Algorithms ◽

Back Propagation Algorithm ◽

Performance Function ◽

Feed Forward ◽

Global Properties ◽

Propagation Algorithm ◽

Feed Forward Neural Networks ◽

And Storage

In this paper we describe several different training algorithms for feed forward neural networks(FFNN). In all of these algorithms we use the gradient of the performance function, energy function, to determine how to adjust the weights such that the performance function is minimized, where the back propagation algorithm has been used to increase the speed of training. The above algorithms have a variety of different computation and thus different type of form of search direction and storage requirements, however non of the above algorithms has a global properties which suited to all problems.

Download Full-text

Detection of Propagating Cracks in Rotors Using Neural Networks

Piping and Component Analysis and Diagnosis ◽

10.1115/pvp2002-1518 ◽

2002 ◽

Cited By ~ 1

Author(s):

S. A. Adewusi ◽

B. O. Al-Bedoor

Keyword(s):

Neural Networks ◽

Back Propagation ◽

Back Propagation Algorithm ◽

Feed Forward Neural Network ◽

Vibration Signals ◽

Feed Forward ◽

Vibration Data ◽

Propagating Crack ◽

Input Layer ◽

Feed Forward Neural Networks

This paper presents the application of neural networks for rotor cracks detection. The basic working principles of neural networks are presented. Experimental vibration signals of rotors with and without a propagating crack were used to train the Multi-layer Feed-forward Neural Networks using back-propagation algorithm. The trained neural networks were tested with other set of vibration data. A simple two-layer feed-forward neural network with two neurons in the input layer and one neuron in the output layer trained with the signals of a cracked rotor and a normal rotor without a crack was found to be satisfactory in detecting a propagating crack. Trained three-layer networks were able to detect both the propagating and non-propagating cracks. The FFT of the vibration signals showing variation in amplitude of the harmonics as time progresses are also presented for comparison.

Download Full-text

Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops

Nature Communications ◽

10.1038/s41467-021-25427-4 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Florian Stelzer ◽

André Röhm ◽

Raul Vicente ◽

Ingo Fischer ◽

Serhiy Yanchuk

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Neural Network ◽

Single Neuron ◽

Deep Neural Networks ◽

Back Propagation ◽

Local Network ◽

Multiple Time ◽

Learning Tools ◽

Back Propagation Algorithm

AbstractDeep neural networks are among the most widely applied machine learning tools showing outstanding performance in a broad range of tasks. We present a method for folding a deep neural network of arbitrary size into a single neuron with multiple time-delayed feedback loops. This single-neuron deep neural network comprises only a single nonlinearity and appropriately adjusted modulations of the feedback signals. The network states emerge in time as a temporal unfolding of the neuron’s dynamics. By adjusting the feedback-modulation within the loops, we adapt the network’s connection weights. These connection weights are determined via a back-propagation algorithm, where both the delay-induced and local network connections must be taken into account. Our approach can fully represent standard Deep Neural Networks (DNN), encompasses sparse DNNs, and extends the DNN concept toward dynamical systems implementations. The new method, which we call Folded-in-time DNN (Fit-DNN), exhibits promising performance in a set of benchmark tasks.

Download Full-text

Rainfall Prediction by Artificial Neural Networks Trained using Different Climate Variables

10.21203/rs.3.rs-569733/v1 ◽

2021 ◽

Author(s):

Mateus Alexandre da Silva ◽

Marina Neves Merlo ◽

Michael Silveira Thebaldi ◽

Danton Diego Ferreira ◽

Felipe Schwerz ◽

...

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Input Data ◽

Back Propagation ◽

Metropolitan Region ◽

Climate Variables ◽

Back Propagation Algorithm ◽

Rainfall Prediction ◽

Artificial Neural ◽

Belo Horizonte

Abstract Predicting rainfall can prevent and mitigate damages caused by its deficit or excess, besides providing necessary tools for adequate planning for the use of water. This research aimed to predict the monthly rainfall, one month in advance, in four municipalities in the metropolitan region of Belo Horizonte, using artificial neural networks (ANN) trained with different climate variables, and to indicate the suitability of such variables as inputs to these models. The models were developed through the MATLAB® software version R2011a, using the NNTOOL toolbox. The ANN’s were trained by the multilayer perceptron architecture and the Feedforward and Back propagation algorithm, using two combinations of input data were used, with 2 and 6 variables, and one combination of input data with 3 of the 6 variables most correlated to observed rainfall from 1970 to 1999, to predict the rainfall from 2000 to 2009. The most correlated variables to the rainfall of the following month are the sequential number corresponding to the month, total rainfall and average compensated temperature, and the best performance was obtained with these variables. Furthermore, it was concluded that the performance of the models was satisfactory; however, they presented limitations for predicting months with high rainfall.

Download Full-text