RESUMO
Robust and reliable diagnostic methods are desired in various types of industries. This article presents a novel approach to object detection in industrial or general ultrasound tomography. The key idea is to analyze the time-dependent ultrasonic signal recorded by three independent transducers of an experimental system. It focuses on finding common or related characteristics of these signals using custom-designed deep neural network models. In principle, models use convolution layers to extract common features of signals, which are passed to dense layers responsible for predicting the number of objects or their locations and sizes. Predicting the number and properties of objects are characterized by a high value of the coefficient of determination R2 = 99.8% and R2 = 98.4%, respectively. The proposed solution can result in a reliable and low-cost method of object detection for various industry sectors.
Assuntos
Aprendizado de Máquina , Redes Neurais de Computação , Ultrassonografia , TomografiaRESUMO
This paper presents a field emitter in the form of a silicon tip covered with a layer of carbon nanotubes. The emitted beam is focused with a set of two electrostatic lenses and - which is novelty in such structures - with a magnetic field. The presented approach gave very promising results. The field emitter was able to provide a high emission current (about 50 µA) and a beam with a small and homogeneous spot. Such electron sources are necessary components of many miniature MEMS and nanoelectronics devices. The presented source is dedicated especially for the use in currently developed MEMS X-ray sources and MEMS electron microscopes.