Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 9

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
PL
Komputerowe modele ruchu drogowego są powszechnie wykorzystywane do analiz przepustowości i sprawności sieci drogowo-parkingowej. Budowa modeli mikrosymulacyjnych jest procesem długotrwałym i złożonym. Jednym z najbardziej czasochłonnych etapów jest kalibracja modelu. Możliwe jest znaczne przyspieszenie tego procesu poprzez wykorzystanie sztucznych sieci neuronowych do szacowania potencjalnie najkorzystniejszych kombinacji parametrów modelu ruchu. W pracy przedstawiono sposób budowy sieci neuronowych na potrzeby modelowania ruchu na wybranym odcinku drogi oraz zaproponowano procedurę umożliwiającą kalibrację mikrosymulacyjnego modelu ruchu.
EN
Computer traffic models are widely used for analysis of the capacity and efficiency of road network. Construction of traffic models is a long and complex process. One of the most timeconsuming stages of the calibration model, which aim is to reflect real traffic condition. This process can be greatly accelerated by the use of artificial neural networks to generate potentially best combinations of parameters for the traffic model. The paper presents a method of building neural networks for traffic modeling, and proposes a procedure for the calibration process.
PL
W artykule przedstawiono metodę pomiaru amplitudy osiowych oscylacji narzędzi stosowanych w procesach obróbki ze wspomaganiem ultradźwiękowym. Pomiary zrealizowano za pomocą laserowego wibrometru skanującego LDV (ang. Laser Doppler Vibrometer).
EN
The article presents axial oscillations amplitude measurements of tools for ultrasonic assisted machining processes. Laser Doppler Vibrometer (LDV) is applied for these investigations.
PL
W artykule przedstawiono metodykę wyznaczania widma częstotliwości ultradźwiękowych oscylacji narzędzi obróbkowych stosowanych w hybrydowych procesach obróbki ubytkowej. W celu określenia widma częstotliwości zastosowano laserowy wibrometr skanujący LDV (ang. Laser Doppler Vibrometer).
EN
The methodology of ultrasonic oscillation spectrum determination for tools applied in hybrid machining processes is presented. The laser scanning vibrometer is applied in order to determine frequency spectrum.
4
Content available remote Novelty detection based on elastic wave signals measured by different techniques
EN
The paper discusses the results of laboratory experiments i n which three independent measurement techniques were compared: a digital oscilloscope, phased array acquisition system, a laser vibrometer 3D. These techniques take advantage of elastic wave signals actuated and sensed by a surface-mounted piezoelectric transducers as well as non-contact measurements. In these e xperiments two samples of aluminum strips were investigated while the damage was modeled by drilling a hole. The structure responses recorded were then subjected to a procedure of signal processing, and features’ extraction was done by PrincipalComponents Analysis. A pattern database defined was used to train artificial neural networks for the purpose of damage detection.
EN
The paper presents a structure test system developed for monitoring structural health, and discusses the results of laboratory experiments conducted on notched strip specimens made of various materials (aluminium, steel, Plexiglas). The system takes advantage of elastic wave signals actuated and sensed by a surface-mounted piezoelectric transducers. The structure responses recorded are then subjected to a procedure of signal processing and feature’s extraction, which includes digital filters, wavelets decomposition, Principal Components Analysis (PCA), Fast Fourier Transformation (FFT), etc. A pattern database defined was used to train artificial neural networks and to establish a structure diagnosis system. As a consequence, two levels of damage identification problem were performed: novelty detection and damage evaluation. The system’s accuracy and reliability were veri?ed on the basis of experimental data. The results obtained have proved that the system can be used for the analysis of simple as well as complex signals of elastic waves and it can operate as an automatic Structure Health Monitoring system.
6
Content available remote Fale sprężyste w badaniach konstrukcji. Cz.2. Doświadczenia laboratoryjne
EN
The paper presents an idea of elastic waves application in the field of structure test and health monitoring. Laboratory experiments were performed for several laboratory specimens made of various materials. In this paper strips elements and plates were analyzed. The main components of the used equipment and the laboratory setup were discussed. The obtained results of preliminary tests have shown that such the approach can be successfully used for the purpose of diagnosis systems since it provides good indication about damage appearance and predicts its size with reasonably well accuracy.
7
Content available remote Fale sprężyste w badaniach konstrukcji. Cz.1. Przetwarzanie sygnałów
EN
The paper presents an idea of elastic waves application in the field of structure test and health monitoring. Smart technology used for this purpose can lead further to autonomous systems that may operate in real time providing information about the structure state or even remaining operational life. However, the analysis of the elastic waves signals, assuming reflections from structure boundaries, connections, cracks, delaminations, etc., may be rather clear or pretty complex. Due to this fact advance signal processing techniques were used here for a purpose of signal de-noising and features extraction. The proposed system performs two levels of structure diagnosis: novelty detection and damage prediction. The developed procedure of signal processing has been studied for the elastic waves signals measured in various laboratory specimens. It has been proved that the application of those techniques improves the accuracy of the designed diagnosis system. Trained neural networks were able to detect damage and predict its size with reasonably well accuracy.
EN
Examination of structures integrity and failures detection are nowadays of great interest for both civil infrastructure and industry systems. This paper presents Structural Health Monitoring (SHM) technique that was tested on several laboratory models and utilizes elastic wave propagation phenomenon. Furthermore, it describes signals feature extraction procedure by using Principal Component Analysis (PCA). Artificial Neural Networks (ANNs) and statistical learning theory are used to determine and classify structure's damages. The results show that data reduction using PCA, followed by implementation of ANNs patterns recognition, provide a good indication of failure occurrence and they may be used for SHM.
PL
Od wielu lat badania prowadzone na Wydziale Budownictwa i Inżynierii Środowiska Politechniki Rzeszowskiej obejmują nieniszczące określanie stanu konstrukcji inżynierskich. Stosowane metody to m.in. analiza przebiegu czasowego przyśpieszeń wybranych punktów badanej konstrukcji, analiza widma częstotliwościowego oraz analiza przebiegu fali sprężystej w badanej konstrukcji. Natomiast do analizy sygnału wykorzystywana jest analiza modalna, analiza za pomocą sztucznych sieci neuronowych oraz analiza falkowa. Niniejsza praca przedstawia problematykę związaną z obszarem zainteresowań autorów opracowania i obejmuje nieniszczącą analizę stanu konstrukcji inżynierskich bazującą na analizie propagacji fali sprężystej z zastosowaniem sztucznych sieci neuronowych.
EN
Since many years Faculty of Civil and Environmental Engineering of Rzeszow University of Technology is carrying out some research on the non-destructive structure testing. The applied methods include the analysis of the acceleration signals in both time and frequency domains and the analysis of the propagation of elastic waves. Modal analysis or analysis involving artificial neural networks and wavelets are applied in the analysis of measurement signals. This paper presents problems connected with authors' field of interests and includes strip-structures analysis based on the elastic wave perturbations and artificial neural networks.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.