A Hybrid Training Algorithm for Continuum Deep Learning Neuro-Skin Neural Network

In this brief paper, a learning algorithm is developed for Deep Learning NeuroSkin Neural Network to improve their learning properties. Neuroskin is a new type of neural network presented recently by the authors. It is comprised of a cellular membrane which has a neuron attached to each cell. The neuron is the cells nucleus. A neuroskin is modelled using finite elements. Each element of the finite element represents a cell. Each cells neuron has dendritic fibers which connects it to the nodes of the cell. On the other hand, its axon is connected to the nodes of a number of different neurons. The neuroskin is trained to contract upon receiving an input. The learning takes place during updating iterations using sensitivity analysis. It is shown that while the neuroskin cannot present the desirable response, it improves gradually to the desired level.

Computer Vision based Tomography of Structures Using 3D Digital Image Correlation

Internal properties of a sample can be observed by medical imaging tools, such as ultrasound devices, magnetic resonance imaging (MRI) and optical coherence tomography (OCT) which are based on relying on changes in material density or chemical composition [1-21]. As a preliminary investigation, the feasibility to detect interior defects inferred from the discrepancy in elasticity modulus distribution of a three-dimensional heterogeneous sample using only surface full-field measurements and finite element model updating as an inverse optimization algorithm without any assumption about local homogeneities and also the elasticity modulus distribution is investigated. Recently, the authors took advantages of the digital image correlation technique as a full field measurement in constitutive property identification of a full-scale steel component [22-27]. To the extension of previous works, in this brief technical note, the new idea intended at recovering unseen volumetric defect distributions within the interior of three-dimensional heterogeneous space of the structural component using 3D-Digital Image Correlation for structural identification [28-57]. As a proof of concept, the results of this paper illustrate the potential to identify invisible internal defect by the proposed computer vision technique establishes the potential for new opportunities to characterize internal heterogeneous materials for their mechanical property distribution and condition state.

Training of Deep Learning Neuro-Skin Neural Network

In this brief paper, a learning algorithm is developed for Deep Learning Neuro-Skin Neural Network to improve their learning properties. Neuroskin is a new type of neural network presented recently by the authors. It is comprised of a cellular membrane which has a neuron attached to each cell. The neuron is the cells nucleus. A neuroskin is modelled using finite elements. Each element of the finite element represents a cell. Each cells neuron has dendritic fibers which connects it to the nodes of the cell. On the other hand, its axon is connected to the nodes of a number of different neurons. The neuroskin is trained to contract upon receiving an input. The learning takes place during updating iterations using sensitivity analysis. It is shown that while the neuroskin can not present the desirable response, it improves gradually to the desired level.

Universal Hysteresis Identification Using Extended Preisach Neural Network

Hysteresis phenomena have been observed in different branches of physics and engineering sciences. Therefore, several models have been proposed for hysteresis simulation in different fields; however, almost neither of them can be utilized universally. In this paper by inspiring of Preisach Neural Network which was inspired by the Preisach model that basically stemmed from Madelungs rules and using the learning capability of the neural networks, an adaptive universal model for hysteresis is introduced and called Extended Preisach Neural Network Model. It is comprised of input, output and, two hidden layers. The input and output layers contain linear neurons while the first hidden layer incorporates neurons called Deteriorating Stop neurons, which their activation function follows Deteriorating Stop operator. Deteriorating Stop operators can generate non-congruent hysteresis loops. The second hidden layer includes Sigmoidal neurons. Adding the second hidden layer, helps the neural network learn non-Masing and asymmetric hysteresis loops very smoothly. At the input layer, besides input data the rate at which input data changes, is included as well in order to give the model the capability of learning rate-dependent hysteresis loops. Hence, the proposed approach has the capability of the simulation of both rate-independent and rate-dependent hysteresis with either congruent or non-congruent loops as well as symmetric and asymmetric loops. A new hybridized algorithm has been adopted for training the model which is based on a combination of the Genetic Algorithm and the optimization method of sub-gradient with space dilatation. The generality of the proposed model has been evaluated by applying it to various hysteresis from different areas of engineering with different characteristics. The results show that the model is successful in the identification of the considered hystereses.