Rubens M. B. da S. Lima, Hugo B. S. Araujo, Cleonilson P. de Souza
Signal sampling is a fundamental process of data acquisition systems and several studies have emerged regarding sampling methods following on Nyquist Theorem. Compressive Sensing (CS) proposes sampling of sparse signals with sub-Nyquist sampling rates. In short, CS is composed of a sampling/compress stage and a reconstruction stage. Some algorithms are used where this last. One of these is the Orthogonal Matching Pursuit (OMP) where 2D Discrete Cosine Transform (2D-DCT) can be used. This work compared the application of 2D-DCT transform and CS theory on images as either a whole or split in...
TC10 Conference 2022
· TC10
· 2022
· 10.21014/tc10-2022.012
· Download
Marco Carratù, Vincenzo Gallo, Antonio Pietrosanto, Paolo Sommella
The increasing development of neural networks for classification and prediction of temporal sequences has opened the way for a new development of mathematical models for soft sensor design. In particular, Long Short-Term Memory (LSTM) networks have greatly improved execution time and reduced error in both single-step and multi-step prediction. In this context, it is therefore possible to improve on the current concept of Instrument Fault Detection and Isolation (IFDI), reducing costs and footprint by not using physical redundancies of sensitive elements but by employing virtual sensors...
TC10 Conference 2022
· TC10
· 2022
· 10.21014/tc10-2022.011
· Download
Marco Carratù, Marcantonio Catelani, Lorenzo Ciani, Gabriele Patrizi, Antonio Pietrosanto, Paolo Sommella
In many different technological and industrial fields microelectronic device reliability is rising up as a fundamental aspect to consider during the design of diagnostic, optimization and control systems. Unexpected failures in diagnostic and control units could lead to a severe impact on the entire system/plant availability. Thus, reliability analysis must be carried out during the early phase of the design. MEMS (Micro-Electro-Mechanical Systems) based Inertial Measurement Units are widespread in diagnostic units to monitor acceleration, position and angular velocity of machinery. However,...
TC10 Conference 2022
· TC10
· 2022
· 10.21014/tc10-2022.010
· Download
Doris Schadler, Michael Wohlthan, Andreas Wimmer
In the case of test beds for research engines, fault detection methods that use models based on historical data face a particular challenge. Due to the experimental design of the test bed, offline training of statistical models with a data set containing all possible variations is simply not possible. The methods must adapt to the current data situation directly on-site. But this involves risks. First, computational time and memory requirements can become extremely large with high data volumes. Second, the data may be faulty and thus negatively affecting the models. To avoid both, a...
TC10 Conference 2022
· TC10
· 2022
· 10.21014/tc10-2022.009
· Download
Yukio Hiranaka, Koichi Tsujino, Hidenori Katsumura, Maho Mori
It is generally difficult to estimate the degree of deterioration of forging dies, but it is necessary to prevent a large number of defective products. In this study, we propose a deterioration score in cold lateral forging using acoustic emission (AE) signals. From the analysis of the measured data, the transition of the signal from the initial state to the deteriorated state can be observed, and the transition can be numerically evaluated. In the evaluation, variational auto-encoder (VAE) is used for learning the initial distribution, and the deterioration score is calculated by the degree...
TC10 Conference 2022
· TC10
· 2022
· 10.21014/tc10-2022.008
· Download
Chao-Ching Ho, Wei-Ming Su, Sankarsan Mohanty
This Study aims at the surface defects of aluminum gaskets as the detection targets. The types of defects are yellow spots, incomplete grinding and bump damages. The detection method will select image processing or deep learning according to the characteristics of the defects. The characteristic of yellow spots has many variables of random shapes and different shades of color, it is difficult to use image processing to detect defects, therefore, this Study selects deep learning as the detection method of yellow spot and the detection network architecture is a modified architecture based on...
TC10 Conference 2022
· TC10
· 2022
· 10.21014/tc10-2022.007
· Download
Dariusz Zieliński, Damian Grzechca
Communication lines play very important role in railway industry. They enable to exchange data between signalling devices such as wheel detectors, evaluators, signals etc. All of them make it possible to manage rail traffic in a safe and efficient way. Availability which depends on robustness of the communication lines is one of the most important features of the system during its use. In this paper the verification of a surge protection module is presented at two stages, i.e. when the voltage has reached the threshold for a gas discharge tube (GDT) and when it is too low. These two cases...
TC10 Conference 2022
· TC10
· 2022
· 10.21014/tc10-2022.006
· Download
Viola Gallina, Zsolt János Viharos, Gabor Nick, Maik Frye, Andreas Kluth, Adam Szaller, Robert H. Schmitt
The first factory of the year prize was granted more than 60 years ago in the USA. Since then, a considerable number of countries joined this way and several best factory assessment methods and awards have been developed on national, regional, and international levels. These competitions give the possibility for benchmarking the companies. However, in the era of industry 4.0 maturity models have emerged for evaluating individual enterprises' readiness. These models support the companies in the individual strategy development. But the companies are always interested in their results and...
TC10 Conference 2022
· TC10
· 2022
· 10.21014/tc10-2022.005
· Download
Gabriele Patrizi, Alessandro Bartolini, Lorenzo Ciani, Marcantonio Catelani
Nowadays, the use of big data analysis and IoT (Internet of Things) technologies is growing tremendously within companies and organizations in several different application fields. In this scenario, smart farming refers to monitoring of environmental conditions and soil parameter to improve farm productivity, to optimize soil conservation, to save water and to limit plant diseases. During the design of such innovative IoT technologies it is fundamental to carry out a reliability and failure analysis of the device. This could allow to introduce adequate diagnostic solutions to improve the...
TC10 Conference 2022
· TC10
· 2022
· 10.21014/tc10-2022.004
· Download
Paul-Alexander Vogel, Anh Tuan Vu, Hendrik Mende, Shrey Gulati, Tim Grunwald, Robert H. Schmitt, Thomas Bergs
Thin glass is applied in numerous applications, appearing as three-dimensional smartphone covers, displays, and in thin batteries. Nonisothermal glass molding has been developed as a hot forming technology that enables to fulfil demands of high quality yet low-cost production. However, finding optimal parameters to a new product variant or glass material is highly demanding. Accordingly, manufacturers are striving for efficient and agile solutions that enable quick adaptations to the process. In this work, we demonstrate that machine learning (ML) can be utilized as a robust and reliable...
TC10 Conference 2022
· TC10
· 2022
· 10.21014/tc10-2022.003
· Download