No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Neural Network Model for Assessing the Physical and Mechanical Properties of a Metal Material Based on Deep Learning
Abstract
The paper investigates the algorithmic stability of learning a deep neural network in problems of recognition of the materials microstructure. It is shown that at 8% of quantitative deviation in the basic test set the algorithm trained network loses stability. This means that with such a quantitative or qualitative deviation in the training or test sets, the results obtained with such trained network can hardly be trusted. Although the results of this study are applicable to the particular case, i.e. problems of recognition of the microstructure using ResNet-152, the authors propose a cheaper method for studying stability based on the analysis of the test, rather than the training set.
... Inspired by visual arts research in bio-agriculture, the joint neural network's ability to learn and express energy resources has been widely used in the field of natural languages, such as the distribution of text and the distribution of hearing [13]. In the native function of CNN, the word vector formed by a sentence is used as a single input, and then the rotation function is performed by multiple rotation kernels matching the size of the word vector to obtain the attributes of several consecutive words. ...
... In Formula (13), H ∈ R (l+L)×2d is the spliced vector, and C � [C 1 , C 2 , · · · , C n ], C ∈ R l×B is the output vector of the convolutional neural network, H t � [h 1 , h 2 , · · · , h L ], H t ∈ R L×2d . e output vector and concat of the two-way GRU is the connecting function. ...
The key sentimental words in the text cannot be paid attention to effectively, and language knowledge such as the text information and the sentimental resources are relied on. Therefore, it is necessary to make full use of this unique sentimental information to achieve the best performance of the model. In order to solve the problems, a method based on the fusion of the convolutional neural network and the bidirectional GRU network text sentiment analysis capsule model to analyze the ideological and political education of public opinion is put forward. In this model, each sentiment category is combined with the attention mechanism to generate feature vectors to construct sentiment capsules. Finally, the text sentiment categories are judged according to the attributes of the capsules. The model is tested on MR, IMDB, SST-5, and the data set of the ideological and political education review. Experimental results show that compared with MC-CNN-LSTM, the readiness rate of the proposed model is improved by 5.1%, 2.8%, 2.8%, and 1.6% on four public Chinese and English data sets, respectively. Compared with LR-Bi-LSTM, NSCL, and multi-Bi-LSTM models, the accuracy of the proposed MC-BiGRU-Capsule model on MR and SST-5 data are 3.2%, 2.4%, and 3.4% higher than that of the LR-Bi-LSTM, NSCL, and multi-Bi-LSTM models, respectively. It also shows a better classification effect on multiclassification data sets. It is concluded that compared with other baseline models, this method has a better classification effect.
Scanning electron microscopy (SEM) was used to examine the polished surface of samples made of basalt-based composite material before and after gamma irradiation. Morphology and local elemental composition changes in binder, filler and boundary of composite components depending on radiation dose were revealed. The samples were irradiated within a dose range of 5 to 15 Mrad. It has been shown that at radiation doses up to 10 Mrad, new intermolecular bonds are formed and the material is strengthened. With large doses of radiation, the destruction of bonds and the formation of a gas phase is observed. This results in softening of the composite. A sufficiently large amount of nitrogen has been detected in the highly irradiated binder. A possible mechanism has been proposed to explain this phenomenon.
The paper considers polymer composite materials based on basalt, carbon and glass fibers. Multilayer carbon nanotubes and gamma irradiation are used to modify these materials. The effect of modification on the strength of materials by determining the tensile strength of the samples is investigated. EDT-10P epoxy resin was used as a binder. The strength properties of the materials by under consideration are compared. An increase in the breaking load by 30% was observed for samples that were modified with nanotubes in relation to unmodified irradiated samples made of UTM49-12K-EP carbon fiber. The hardening of the samples modified by gamma irradiation with a dose of 10 MRad was also recorded at 8%.
The article presents the study results of cryptocurrencies dynamics, which are the most popular at the present time (Bitcoin, Ethereum and Ripple). The paper provides the opinions of various researchers regarding the economic nature of cryptocurrencies. Taking into account that the most significant drawback of modern cryptocurrencies is the high volatility of their market prices, the goal was to find an adequate method for forecasting cryptocurrency rates. Having analyzed an extensive selection of scientific articles on this topic and tested the cryptocurrency market for its information efficiency. The heterogeneous autoregressive model of realized volatility (HAR-RV) was first chosen as a working tool for predicting the rate of cryptocurrencies. To improve the accuracy of the forecast, it was additionally proposed to calculate the Shannon entropy based on the probabilities of a decrease in cryptocurrency market prices. The forecast accuracy by the proposed method exceeded all the most optimistic expectations. This method of calculating the market rate of cryptocurrencies will be useful to investors and speculators when making management decisions.
The inner structure of a material is called microstructure. It stores the genesis of a material and determines all its physical and chemical properties. While microstructural characterization is widely spread and well known, the microstructural classification is mostly done manually by human experts, which gives rise to uncertainties due to subjectivity. Since the microstructure could be a combination of different phases or constituents with complex substructures its automatic classification is very challenging and only a few prior studies exist. Prior works focused on designed and engineered features by experts and classified microstructures separately from the feature extraction step. Recently, Deep Learning methods have shown strong performance in vision applications by learning the features from data together with the classification step. In this work, we propose a Deep Learning method for microstructural classification in the examples of certain microstructural constituents of low carbon steel. This novel method employs pixel-wise segmentation via Fully Convolutional Neural Network (FCNN) accompanied by a max-voting scheme. Our system achieves 93.94% classification accuracy, drastically outperforming the state-of-the-art method of 48.89% accuracy. Beyond the strong performance of our method, this line of research offers a more robust and first of all objective way for the difficult task of steel quality appreciation.
A convolutional neural network (CNN) is proposed to learn multiple useful feature representations for a classification from low level (raw pixels) to high level (object). Convolutional kernels are initialized by the learned filter kernels that come from sparse auto-encoders. Unlike some traditional methods, which divide the feature abstracting and classifier training into two separated processes, a discriminative feature vector and a single multi-class classifier of softmax regression are learned simultaneously during the training process. Based on the learned high-quality feature representation, the classification can be efficiently performed. A real-world case of surface defects on steel sheet, which evaluates the classification performance of the proposed method, is depicted in detail. The experimental results indicate that the proposed method is quite simple, effective and robustness for the classification of surface defects on hot-rolled steel sheet.
We introduce a microstructure informatics dataset focusing on complex, hierarchical structures found in a single Ultrahigh carbon steel under a range of heat treatments. Applying image representations from contemporary computer vision research to these microstructures, we discuss how both supervised and unsupervised machine learning techniques can be used to yield insight into microstructural trends and their relationship to processing conditions. We evaluate and compare keypoint-based and convolutional neural network representations by classifying microstructures according to their primary microconstituent, and by classifying a subset of the microstructures according to the annealing conditions that generated them. Using t-SNE, a nonlinear dimensionality reduction and visualization technique, we demonstrate graphical methods of exploring microstructure and processing datasets, and for understanding and interpreting high-dimensional microstructure representations.
We apply recent advances in machine learning and computer vision to a central problem in materials informatics: The statistical representation of microstructural images. We use activations in a pre-trained convolutional neural network to provide a high-dimensional characterization of a set of synthetic microstructural images. Next, we use manifold learning to obtain a low-dimensional embedding of this statistical characterization. We show that the low-dimensional embedding extracts the parameters used to generate the images. According to a variety of metrics, the convolutional neural network method yields dramatically better embeddings than the analogous method derived from two-point correlations alone.
In this paper, we propose a deep convolutional neural network solution to the analysis of image data for the detection of rail surface defects. The images are obtained from many hours of automated video recordings. This huge amount of data makes it impossible to manually inspect the images and detect rail surface defects. Therefore, automated detection of rail defects can help to save time and costs, and to ensure rail transportation safety. However, one major challenge is that the extraction of suitable features for detection of rail surface defects is a non-trivial and difficult task. Therefore, we propose to use convolutional neural networks as a viable technique for feature learning. Deep convolutional neural networks have recently been applied to a number of similar domains with success. We compare the results of different network architectures characterized by different sizes and activation functions. In this way, we explore the efficiency of the proposed deep convolutional neural network for detection and classification. The experimental results are promising and demonstrate the capability of the proposed approach.
Convolutional neural networks (CNNs) achieved impressive recognition rates in image classification tasks recently. In order to ex-ploit those capabilities, we trained CNNs on a database of photometric stereo images of metal surface defects, i.e. rail defects. Those defects are cavities in the rail surface and are indication for further surface degra-dation right up to rail break. Due to security issues, defects have to be recognized early in order to take countermeasures in time. By means of differently colored light-sources illuminating the rail surfaces from different and constant directions, those cavities are made visible in a photometric dark-field setup. So far, a model-based approach has been used for image classification, which expressed the expected reflection properties of surface defects in contrast to non-defects. In this work, we experimented with classical CNNs trained in pure supervised manner and also explored the impact of regularization methods such as unsuper-vised layer-wise pre-training and training data-set augmentation. The classical CNN already distinctly outperforms the model-based approach. Moreover, regularization methods yet yield further improvements.
We define notions of stability for learning algorithms and derive bounds on their generalization error based on the empirical error and the leave-one-out error. We then study the stability properties of large classes of learning algorithms such as regularization based algorithms. In particular we focus on Hilbert space regularization and Kullback-Liebler regularization. We then apply the results to SVM for regression and classification and to maximum entropy discrimination. 1 Introduction Deriving bounds on the generalization error of a learning system is one of the major issue in statistical learning theory. Many researchers [1, 2, 3, 8, 13] have focused on these bounds by developing worst case analysis. That is, they showed that for all functions in a hypothesis space, the empirical error is close to the generalization error. In this report, we developp a different analysis inspired by [7, 6] where the generalization error is studied with respect to the learning algorithm. The goal ...
The ability of learning networks to generalize can be greatly enhanced by providing constraints from the task domain. This paper demonstrates how such constraints can be integrated into a backpropagation network through the architecture of the network. This approach has been successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service. A single network learns the entire recognition operation, going from the normalized image of the character to the final classification.
The paper investigates the algorithmic stability of learning a deep neural network in problems of recognition of the materials microstructure. It is shown that at 8% of quantitative deviation in the basic test set the algorithm trained network loses stability. This means that with such a quantitative or qualitative deviation in the training or test sets, the results obtained with such trained network can hardly be trusted.
Although the results of this study are applicable to the particular case, i.e. problems of recognition of the microstructure using ResNet-152, the authors propose a cheaper method for studying stability based on the analysis of the test, rather than the training set.KeywordsDeep neural networksMaterial microstructureImage recognitionDeep learningAlgorithmic stability
The paper considers the possibilities of artificial neural networks and deep machine learning in the problem of predicting the physicomechanical properties of functional materials. It is shown that the popular deep neural network VGG with high accuracy solves the problem of hardness classification of metal alloy on the basis of iron. The prospects of building a generative adversarial network that is able to predict the structure of the alloy with predetermined physicomechanical characteristics are discussed.
A new methodology to obtain metallic functional materials with predefined sets of strength properties has been developed. It has been shown that in order to accurately estimate set of material properties at the macro-level, information from the micro-level needs to be taken into account. As a result a two-level estimation model, based on the theory of fuzzy sets, has been proposed. To demonstrate the developed methodology, a reinforcing steel has been analysed. Using microstructural information, derived from an available set of experimentally obtained digital images of material microsections under different heat treatment conditions, macroscopic strength properties of reinforcing steel have been determined.
The technique allows analysis using grain-phase structure of the functional material to evaluate its performance, particularly strength properties. The technique is based on the use of linguistic variable in the process of comprehensive evaluation. An example of estimating the strength properties of steel reinforcement, subject to special heat treatment to obtain the desired grain-phase structure.
We present a Max-Pooling Convolutional Neural Network approach for supervised steel defect classification. On a classification task with 7 defects, collected from a real production line, an error rate of 7% is obtained. Compared to SVM classifiers trained on commonly used feature descriptors our best net performs at least two times better. Not only we do obtain much better results, but the proposed method also works directly on raw pixel intensities of detected and segmented steel defects, avoiding further time consuming and hard to optimize ad-hoc preprocessing.
We present a novel way of obtaining PAC-style bounds on the generalization error of learning algorithms, explicitly using their stability properties. A stable learner is one for which the learned solution does not change much with small changes in the training set. The bounds we obtain do not depend on any measure of the complexity of the hypothesis space (e.g. VC dimension) but rather depend on how the learning algorithm searches this space, and can thus be applied even when the VC dimension is infinite. We demonstrate that regularization networks possess the required stability property and apply our method to obtain new bounds on their generalization performance.
Impact of Dataset Size on Deep Learning Model Skill and Performance Estimates [Digital resource
- Jason Brownlee
Klyuev: Detection and classification metal’s and alloy’s microstructure using deep neural network. Proceeding of 27th International conferencion of computer graphics and machine vision GraphiCon
- G V Aristov
Synho Do (2015) How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?
- Junghwan Cho
- Kyewook Lee
- Ellie Shin
- Garry Choy