Quality Assessment of the Neural Algorithms on the Example of EIT-UST Hybrid Tomography
The paper presents the results of research on the hybrid industrial tomograph electrical impedance tomography (EIT) and ultrasonic tomography (UST) (EIT-UST), operating on the basis of electrical and ultrasonic data. The emphasis of the research was placed on the algorithmic domain. However, it shou...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/11/3324 |
| _version_ | 1797417047021322240 |
|---|---|
| author | Grzegorz Kłosowski Tomasz Rymarczyk Tomasz Cieplak Konrad Niderla Łukasz Skowron |
| author_facet | Grzegorz Kłosowski Tomasz Rymarczyk Tomasz Cieplak Konrad Niderla Łukasz Skowron |
| author_sort | Grzegorz Kłosowski |
| collection | DOAJ |
| description | The paper presents the results of research on the hybrid industrial tomograph electrical impedance tomography (EIT) and ultrasonic tomography (UST) (EIT-UST), operating on the basis of electrical and ultrasonic data. The emphasis of the research was placed on the algorithmic domain. However, it should be emphasized that all hardware components of the hybrid tomograph, including electronics, sensors and transducers, have been designed and mostly made in the Netrix S.A. laboratory. The test object was a tank filled with water with several dozen percent concentration. As part of the study, the original multiple neural networks system was trained, the characteristic feature of which is the generation of each of the individual pixels of the tomographic image, using an independent artificial neural network (ANN), with the input vector for all ANNs being the same. Despite the same measurement vector, each of the ANNs generates its own independent output value for a given tomogram pixel, because, during training, the networks get their respective weights and biases. During the tests, the results of three tomographic methods were compared: EIT, UST and EIT-UST hybrid. The results confirm that the use of heterogeneous tomographic systems (hybrids) increases the reliability of reconstruction in various measuring cases, which is used to solve quality problems in managing production processes. |
| first_indexed | 2024-03-09T06:13:16Z |
| format | Article |
| id | doaj.art-0086eb3a96e04845aac474f8f2ab90e0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T06:13:16Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0086eb3a96e04845aac474f8f2ab90e02023-12-03T11:55:35ZengMDPI AGSensors1424-82202020-06-012011332410.3390/s20113324Quality Assessment of the Neural Algorithms on the Example of EIT-UST Hybrid TomographyGrzegorz Kłosowski0Tomasz Rymarczyk1Tomasz Cieplak2Konrad Niderla3Łukasz Skowron4Faculty of Management, Lublin University of Technology, 20–618 Lublin, PolandUniversity of Economics and Innovation in Lublin Research & Development Centre Netrix S.A., 20-209 Lublin, PolandFaculty of Management, Lublin University of Technology, 20–618 Lublin, PolandUniversity of Economics and Innovation in Lublin Research & Development Centre Netrix S.A., 20-209 Lublin, PolandFaculty of Management, Lublin University of Technology, 20–618 Lublin, PolandThe paper presents the results of research on the hybrid industrial tomograph electrical impedance tomography (EIT) and ultrasonic tomography (UST) (EIT-UST), operating on the basis of electrical and ultrasonic data. The emphasis of the research was placed on the algorithmic domain. However, it should be emphasized that all hardware components of the hybrid tomograph, including electronics, sensors and transducers, have been designed and mostly made in the Netrix S.A. laboratory. The test object was a tank filled with water with several dozen percent concentration. As part of the study, the original multiple neural networks system was trained, the characteristic feature of which is the generation of each of the individual pixels of the tomographic image, using an independent artificial neural network (ANN), with the input vector for all ANNs being the same. Despite the same measurement vector, each of the ANNs generates its own independent output value for a given tomogram pixel, because, during training, the networks get their respective weights and biases. During the tests, the results of three tomographic methods were compared: EIT, UST and EIT-UST hybrid. The results confirm that the use of heterogeneous tomographic systems (hybrids) increases the reliability of reconstruction in various measuring cases, which is used to solve quality problems in managing production processes.https://www.mdpi.com/1424-8220/20/11/3324industrial tomographymachine learningneural networkscyber-physical systemhybrid systemsproduction process management |
| spellingShingle | Grzegorz Kłosowski Tomasz Rymarczyk Tomasz Cieplak Konrad Niderla Łukasz Skowron Quality Assessment of the Neural Algorithms on the Example of EIT-UST Hybrid Tomography Sensors industrial tomography machine learning neural networks cyber-physical system hybrid systems production process management |
| title | Quality Assessment of the Neural Algorithms on the Example of EIT-UST Hybrid Tomography |
| title_full | Quality Assessment of the Neural Algorithms on the Example of EIT-UST Hybrid Tomography |
| title_fullStr | Quality Assessment of the Neural Algorithms on the Example of EIT-UST Hybrid Tomography |
| title_full_unstemmed | Quality Assessment of the Neural Algorithms on the Example of EIT-UST Hybrid Tomography |
| title_short | Quality Assessment of the Neural Algorithms on the Example of EIT-UST Hybrid Tomography |
| title_sort | quality assessment of the neural algorithms on the example of eit ust hybrid tomography |
| topic | industrial tomography machine learning neural networks cyber-physical system hybrid systems production process management |
| url | https://www.mdpi.com/1424-8220/20/11/3324 |
| work_keys_str_mv | AT grzegorzkłosowski qualityassessmentoftheneuralalgorithmsontheexampleofeitusthybridtomography AT tomaszrymarczyk qualityassessmentoftheneuralalgorithmsontheexampleofeitusthybridtomography AT tomaszcieplak qualityassessmentoftheneuralalgorithmsontheexampleofeitusthybridtomography AT konradniderla qualityassessmentoftheneuralalgorithmsontheexampleofeitusthybridtomography AT łukaszskowron qualityassessmentoftheneuralalgorithmsontheexampleofeitusthybridtomography |