Wyniki wyszukiwania - BazTech

1

Fault diagnosis of machines operating in variable conditions using artificial neural network not requiring training data from a faulty machine

Pawlik Paweł, Kania Konrad, Przysucha Bartosz

Eksploatacja i Niezawodność

|

2023

|

Vol. 25, no. 3

art. no. 168109

EN

The fault diagnosis for maintenance of machines operating in variable conditions requires special dedicated methods. Variable load or temperature conditions affect the vibration signal values. The article presents a new approach to diagnosing rotating machines using an artificial neural network, the training of which does not require data from the damaged machine. This is a new approach not previously found in the literature. Until now, neural networks have been used for machine diagnosis in the form of classifiers, where data from individual faults were required. A new diagnostic parameter rDPNS (Relative Differences Product of Network Statistics) as a function of the machine's shaft order was proposed as a kind of new order spectrum independent of the machine's operating conditions. The presented work analyses the use of the proposed method to diagnose misalignment and unbalance. The results of an experiment carried out in the laboratory demonstrated the effectiveness of the proposed method.

2

Detection of cardiac arrhythmias in body surface potential mapping (BSMP) measurements

Przysucha Bartosz, Rymarczyk Tomasz, Wójcik Dariusz

Przegląd Elektrotechniczny

|

2022

|

R. 98, nr 1

115--118

EN

The multitude of measurement data obtained from BSPM (Body Surface Potential Mapping) requires automatic detection and classification methods to detect disturbances. The article describes the method of classification of heart rate disorders based on the characteristics of signals from sensors. For the purposes of the research, a coefficient was created that allows the classification of cardiac arrhythmias in the BSPM measurements. In addition, BSPM signals were simulated using a system constructed for testing an innovative measuring vest with 102 measuring electrodes.

PL

Artykuł opisuje problem klasyfikacji zaburzeń rytmu serca sygnałów otrzymanych z pomiarów BSPM. W pracy skonstruowano współczynnik mierzący dynamikę sygnału I sprawdzono możliwości klasyfikacji sygnału opartej na podstawie wyliczonego współczynnika. Pomiary na baize których dokonano analizy pochodzą z symulacji wykonanych na zaprojektowanym urządzeniu symulacyjnych powstałym w celu testowania innowacyjnej kamizelki pomiarowej BSPM ze 102 elektrodami.

3

Statistical analysis with Kolmogorov-Smirnov distance for reflections’ directions of arrival and amplitudes for sound field diffuseness estimation

Chojnacki Bartłomiej, Przysucha Bartosz, Kamisiński Tadeusz, Binek Wojciech

Vibrations in Physical Systems

|

2021

|

Vol. 32, nr 1

art. no. 2021101

EN

Many parameters are used for rating the quality of the sound field inside qualified acoustic halls describing the strength, clarity, and definition of the sound. Sound field diffuseness level and spatial impression parameters are used rarely because of the problem in their measurements and interpretation. Previous research on that topic provided some sound field diffuseness coefficients. Some of them are complicated in estimation and measurement. This paper presents a method for the sound field diffuseness level estimation basing on example measurements of the Arthur Rubinstein Philharmonic in Łódź, Poland. New directional parameters are proposed based on the statistical analysis of the sound reflections’ incidence angles and their amplitudes with Kolmogorov-Smirnov distance. The paper contains a discussion on the quality evaluation with the proposed method, including analysing the sound field diffuseness and non-uniform spatial distributions of sound reflections. The usability of the selected parameters and their importance for the spatial impression is discussed. The performed experiments allow setting the direction of future work in the field taken of the study, especially applying the proposed method for extended sound field diffuseness ratings with methods based on different physical principles, including directional, energetic, and time coefficients.

4

Analysis of multi-source data for monitoring and control of intelligent technological systems

Rymarczyk Tomasz, Przysucha Bartosz, Pawlik Paweł

Przegląd Elektrotechniczny

|

2020

|

R. 96, nr 9

95--98

EN

The article presents a part of cyber-physical system for acquiring, processing and controlling from measurement data. The technology was based on, intelligent measurement sensors, internet of Things as a solution for Industry 4.0. The aspect raised in the article concerns data reduction and selection of an appropriate covariant in the modeling optimization of modeling faults by the Cox model for a specific mechanical system.

PL

Artykuł przedstawia część cyber-fizycznego systemu do zbierania, przetwarzania i sterowania przy pomocy informacji pochodzącej z danych pomiarowych. Technologia ta została oparta na inteligentnych czujnikach pomiarowych z użyciem internetu rzeczy jako rozwiązania dla Przemysłu 4.0. Aspekt poruszony w pracy dotyczy redukcji danych i wyboru odpowiedniego kowariantu w optymalizacji modelowania usterek modelem Coxa dla konkretnego układu mechanicznego.