Hysteresis modeling based on the hysteretic chaotic neural network

Abstract

The hysteresis activation function is proposed, and a novel hysteretic chaotic neuron model is constructed by the function. It is shown that the model may exhibit a complex dynamic behavior. On the basis of this neuron model, we propose a novel neural network, which can be applied to hysteresis system modeling. We demonstrate the advantages of the network by experimental results.

Design and security analysis of two robust keyed hash functions based on chaotic neural networks

“…365 (23) ) = 50.73%. Birthday attack is widely exploited for finding any two messages M and M , such that H(M) = H(M ), then the couple (M, M ) is named a collision.…”

“…In 2007, Zhang et al, [19] proposed a novel chaotic keyed hash algorithm using a feed forward-feedback nonlinear filter. Other researchers proposed combined hashing and encryption schemes based on chaotic neural network [20][21][22][23][24][25][26][27][28][29][30][31][32]. Since 2010, there has been a real turning point in building new secure hash algorithms based on chaotic maps and neural network.…”

The Application of Piezoelectric Materials in Smart Structures in China

“…However, neural networks can only approximate one-to-one mapping and multi-to-one mapping, and cannot directly approximate multi-value mapping such as hysteresis nonlinearity (Hagan et al, 1996). Many new mapping methods have been developed for neural networks in order to describe the hysteresis, such as accumulated generation operation of grey theory (Dang and Tan, 2005b), hybrid neural network (Liu et al, 2006b), neural network in three-dimension coordinates (Qu et al, 2005), radial basis function neural networks (Yang and Chang, 2006), Winner model , chaotic neural network (Liu et al, 2006b). Some of these neural network models have been programmed to design controllers for hysteresis compensation.…”

Feedforward Chaotic Neural Network Model for Rotor Rub-Impact Fault Recognition Using Acoustic Emission Method

“…is technology has been demonstrated, and it has beneficial prospects for applications in rubbing fault diagnosis field [17][18][19]. e hysteretic Hopfield neural network (HHNN) is one of the nondestructive testing methods [20][21][22][23][24][25], detects defection property by AE signal, and then depends on the pattern recognition to classify the signal. e hysteretic characteristic can help us to enhance the capacity of memory and steadiness of the original states for the neural network, and chaotic characteristic can reflect some perception phenomena or cognitive process of human.…”