A study of supervised combined neural-network-based ultrasonic method for reconstruction of spatial distribution of material properties

Abstract

This paper examines the performance of the commonly used neural-network-based classifiers for investigating a structural noise in metals as grain size estimation. The biggest problem which aims to identify the object structure grain size based on metal features or the object structure itself. When the structure data is obtained, a proposed feature extraction method is used to extract the feature of the object. Afterwards, the extracted features are used as the inputs for the classifiers. This research studies is focused to use basic ultrasonic sensors to obtain objects structural grain size which are used in neural network. The performance for used neural-network-based classifier is evaluated based on recognition accuracy for individual object. Also, traditional neural networks, namely convolutions and fully connected dense networks are shown as a result of grain size estimation model. To evaluate robustness property of neural networks, the original samples data is mixed for three types of grain sizes. Experimental results show that combined convolutions and fully connected dense neural networks with classifiers outperform the others single neural networks with original samples with high SN data. The Dense neural network as itself demonstrates the best robustness property when the object samples not differ from trained datasets.

A Stopping Criterion for the Training Process of the Specific Signal Generator

“…Unfortunately, such approaches are subjective and possibly misleading. Therefore, Inception Score (IS) was proposed in [22] to quantitatively assess the performance of GANs which is based on the fact that a good model should generate samples for which, when evaluated (7) shows the principle of IS:…”

“…The Deep Neural Networks (DNN), which can be regarded as a special mathematical description. It has an information forward structure, where the data flows forward from the network inputs through many hidden units and eventually to the output blocks [7]. It is widely used to generate different signals by fitting the independent variables and the dependent variables to a certain extent.…”

Deep learning in automated ultrasonic NDE -- developments, axioms and opportunities

“…The estimation of other material properties from ultrasonic data has also been the subject of study. For example, the estimation of the spatial distribution of grain size in metals was investigated in [66]. The authors proposed a DL architecture consisting of a CNN followed by several fully connected layers.…”