|
|
Deep learning methods for the acoustic emission methods to evaluate an onset of plastic straining
Parma, Slavomír ; Kovanda, Martin ; Chlada, Milan ; Štefan, Jan ; Kober, Jan ; Feigenbaum, H. P. ; Plešek, Jiří
Development of phenomenological plasticity models, hardening rules, and plasticity theories relies on experimental data of plastic straining. The experimental data are usually measured as the stress–strain response of the material being loaded and do not provide any clues or information about the local response of\nmaterial. In this paper, we analyze the plastic deformation of the material using the acoustic emission method and current state-of-the-art neural network models such as the InceptionTime architecture.
|
|
|
V7: Summary report NEMENUS for SÚJB
Štefan, Jan ; Joch, Jaroslav ; Převorovský, Zdeněk ; Gabriel, Dušan ; Krofta, Josef ; Chlada, Milan ; Kober, Jan ; Masák, Jan ; Kunz, J. ; Ashhab, B.
This is the final report of project TAČR TK01030108: Innovative methods for nuclear plant safety evaluation based on SHM technologies and related procedures - NEMENUS (NEw MEthods for NUclear Safety). In this report, the most important project results and outputs are presented, as well as a summary of its contributions with respect to long-term technological horizons.
|
|
|
V6: Report on functional sample NEMENUS
Štefan, Jan ; Joch, Jaroslav ; Převorovský, Zdeněk ; Gabriel, Dušan ; Krofta, Josef ; Chlada, Milan ; Kober, Jan ; Masák, Jan ; Materna, A. ; Kovářík, O. ; Čech, J.
This research report is an integral part of mandatory output V6: FUNCTIONAL SPECIMEN of project TAČR TK01030108: Innovative methods for nuclear plant safety evaluation based on SHM technologies and related procedures - NEMENUS (NEw MEthods for NUclear Safety). The report presents full technical description of the elaborated representative functional specimen (the representative SHM model) and the description of a four-year experimental program.
|
|
|
Deep learning methods for acoustic emission evaluation
Kovanda, M. ; Chlada, Milan
The goal of this paper is to show the possibilities of state-of-the-art deep learning methods for ultrasound signals evaluation. Several neural network architectures are applied to\nacoustic emission signals measured during the tensile tests of metallic specimen to determine the beginning of plasticity in the material. Plastic deformation is accompanied by microscopic\nevents such as a slip of atomic plane dislocations which is hardly detectable by other methods. The potential of machine learning is demonstrated on two tensile tests where the material is\nstrained until it collapses. The examined networks proved well to reliably predict the risk of collapse together with changes in the ultrasound emission signals.
|
|
|
Research Report: Representative SHM Model
Převorovský, Zdeněk ; Joch, Jaroslav ; Kober, Jan ; Krofta, Josef ; Chlada, Milan ; Štefan, Jan ; Kunz, J. ; Ashhab, B.
The Research Report is output of the project NEMENUS dealing with methodology development of Structural Health Monitoring (SHM) for nuclear power plant components. SHM incorporates advanced methods for evaluation of structural operating safety. It consists in continuous monitoring of critical structure parts by advanced Nondestructive Testing (NDT) methods enabling assessment of their residual lifetime. The literature search part of this report comprises different aspects of the main problems including history of SHM systems applications at civil and mechanical structures, and also the newest SHM trends in nuclear and non-nuclear industry. The material damage mechanisms in nuclear power plant environment are also discussed in the report. At the report end there is indicated practical realization of the project results and SHM verification on a model structure.
|
|
|
Nonparametric density estimates used for multiple AE source detection
Gális, P. ; Chlada, Milan
Paper deals with the localization of acoustic emission (AE) sources by means of exact geodesic curves on 3D vessels composed of several parametrized surfaces. Precise arrival times of AE events, plugged in DeltaT/DeltaL localization is discussed. Two-dimensional nonparametric (kernel) density estimates are employed to obtain the localization maps on 3-D surfaces and the potential regions of cracks are visibly highlighted. This newly proposed procedure is applied to steam reservoir and other experimental vessels. The results presented are accompanied by thoroughgoing evaluation of their quality and practical usefulness.
|
|
|
Monitoring techniques for special alloys from some medical prostheses.
Savin, A. ; Vizureanu, P. ; Převorovský, Zdeněk ; Steigmann, R. ; Chlada, Milan ; Krofta, Josef ; Baltatu, M.S. ; Craus, M. L. ; Nový, F.
The paper presents complementary methods for noninvasive evaluation of an exotic class of alloys possible to be used in medical prosthetics. The interest in this study is the analysis of Ti alloys with different concentration of Mo and Si, in order to make the elastic modulus and Poisson ratio reach values appropriate with human bones. The both methods, acoustic emission and resonant ultrasound spectroscopy are proposed as complementary methods for nondestructive evaluation of entire sample volume.
|
|
|
Analysis of acoustic emission source location precision for general sensor configurations
Chlada, Milan ; Gális, P. ; Převorovský, Zdeněk
Proper sensor placement is the crucial step and a premise for precise acoustic emission (AE) source location estimate. Using the algorithm for finding the shortest ways in discretely defined bodies it is possible to design three parallel tools how to evaluate problematic areas, namely the location sensitivity, similarity and ambiguity maps, available even for discontinuous or anisotropic bodies. To check the numerical forecast of localization capabilities for given sensor configuration, theoretical results were compared with the data measured on the real steam pressure vessel.
|
|
| |
|
| |
guest ::
