Ten serwis zostanie wyłączony 2025-02-11.
Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 14

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
Przedstawiono podstawowe problemy związane z monitorowaniem i diagnostyką silników indukcyjnych klasycznymi metodami wykrywania uszkodzeń, w połączeniu z nowymi możliwościami stworzonymi przez sztuczne sieci neuronowe. Omówiono przyczyny powstawania uszkodzeń elektrycznych i mechanicznych w silnikach indukcyjnych klatkowych. Scharakteryzowano podstawowe metody wykrywania uszkodzeń stosowane obecnie w diagnostyce eksploatacyjnej. Szczególną uwagę zwrócono na omówienie metod monitorowania i diagnostyki na podstawie analizy częstotliwościowej sygnałów prądu stojana, strumienia poosiowego oraz drgań mechanicznych. Zaprezentowano metodykę zastosowania sztucznych sieci neuronowych do wykrywania podstawowych uszkodzeń w silnikach indukcyjnych i budowania neuronowych detektorów uszkodzeń, mających za zadanie wspomóc klasyczne metody diagnozowania i zobiektywizować proces wykrywania i oceny uszkodzenia. Szczególną uwagę zwrócono na zastosowanie sieci typu perceptron wielowarstwowy oraz sieci samoorganizujących Kohonena do budowy neurodetektorów uszkodzeń, realizujących funkcje klasyfikatora uszkodzeń. Zbadano neuronowe detektory uszkodzeń wirników klatkowych, zwarć międzyzwojowych w stojanie oraz łożysk tocznych, opracowane na podstawie danych zebranych klasycznymi metodami na rzeczywistym obiekcie. Wykazano przydatność analizy falkowej do wstępnego przetwarzania sygnałów diagnostycznych w celu otrzymania danych przydatnych do trenowania i testowania neuronowych detektorów uszkodzeń. Przedstawiono wstępne wyniki badań laboratoryjnych neuronowych detektorów uszkodzeń wirników i łożysk tocznych, pracujących on-line na rzeczywistej maszynie i zrealizowanych programowo w komputerze PC z kartą kontrolera DSP.
EN
In the monograph, the basic problems connected with the monitoring and diagnostics of induction motors using classical fault detection methods, supported by new possibilities generated by artificial neural networks, have been presented. The main sources of electrical and mechanical faults of the squirrel cage induction motors are described. Basic methods of fault detection used in the industrial diagnostics of induction machines are characterized. The main attention was focused on the monitoring and diagnosis methods based on the frequency analysis of the motor current, the axial flux and mechanical vibration signals. The possibility of applying the neural networks to fault detection in the stator, rotor and bearings of the induction motors is presented. A methodology for the design of neural detectors, supporting the classical diagnostics methods and making fault detection and evaluation process reliable, has been developed. Special attention is focused on the application of multilayer perceptron and Kohonen networks for the design of fault detectors, used as fault classifiers. Various structures of neural detectors of rotor cages, stator inter-turn short-circuits and rolling bearings, trained using experimental data obtained from a real machine, have been tested and evaluated. It has also been proved that wavelet analysis applied to the initial preprocessing of the diagnostic signals, is a useful and powerful tool for collection of the training and testing data for neural fault detectors. The developed neural detectors of the rotor and bearing faults were implemented in the laboratory test bench using a digital signal processor, which performed the data acquisition of the stator current and/or vibration signals, Fast Fourier Transformation of Wavelet Transformation of the diagnostic signals in the real-time operation. Experimental results of laboratory tests for are demonstrated and evaluated.
|
|
tom Nr 77
129-134
EN
The paper deals with the remote monitoring of a converter fed induction motor drive via Ethernet using the Lab VIEW environment. In order to address this challenge a complex solution is proposed concerning both hardware (laboratory set-up design) and software layer (the consumer, distributor and producer's application). Techniques for remote monitoring of a converter fed induction motor drive's operation are discussed. The results of the experimental tests are presented.
|
|
tom Nr 77
135-141
EN
The paper deals with the application of the reconfigurable system i.e. FPGA matrix to the induction motor control. The classical approach based on the microcontroller technique, in which the control algorithms are sequentially executed, has been compared with the FPGA application capable of performing parallel calculations. The algorithms and techniques enabling implementation of SVM vector modulation in FPGA are presented. The coordinates' transformations have conducted by means of the CORDIC algorithm. The discussion of the laboratory tests' results takes advantage of the simple scalar control system. The Xilinx Virtex II by National Instruments was used.
|
|
tom Nr 87
179-184
EN
In this paper possibilities of application the extended Kalman filter algorithm to rotor fault detection of induction motor fed by PWM inverter are presented. The induction motor condition is analyzed using estimated rotor resistance. The motor mathematical model of induction motor with rotor damage are described. The fault level is modeled by a change of a numbers of broken rotor bars. The algorithm of extended Kalman filter are presented. Rotor resistance as a additional electromagnetic state variables are selected. A detailed analysis of simulation and experimental results for induction motor with broken rotor bars in open and closed loop are presented. The simulations showed high accuracy and fast response of extended Kalman filter algorithm. The experimental proved theoretical assumption and demonstrated extended Kalman filter suitability to inverter fed induction motor rotor faults detection.
|
|
tom Nr 87
145-150
EN
This paper deals with the problem of the early stator faults (the short-circuits) detection and localization of the induction motors supplied from the frequency converter. A stator fault detection method based on monitoring of RMS stator current value, the phase shift between the line currents, the spectral analysis of the line current and negative current symmetrical component analysis are presented. Tests were realized for different load torque and supply frequencies, what enabled the evaluating of the usefulness of the proposed analysis in the diagnostics of the stator faults in the converter-fed induction motor drives.
|
|
tom Nr 87
151-156
EN
In this paper problem of the early induction motors stator faults (the short-circuits) detection and localization supplied from the frequency converter are presented. Tests were realized for different load torque and supply frequencies. For the monitoring stator winding condition method based on monitoring the spatial current vector is used. Attention was paid to changes that result in short-circuit a few winding turns in one phase of stator current spatial vector, such as maximum value, hodograph deformation, angular shift and spectral analysis of the stator current spatial vector module. To evaluate changes of current hodograph method based on principal components analysis PCA are used.
|
|
tom Nr 83
189-194
EN
The paper deals with the basic problems of misalignment monitoring for induction motor drive. Methods of misalignment symptom detection based on the frequency analysis of the stator current and mechanical vibration signals are described. Examples of stator current and vibration spectra are demonstrated for alignment drive system as well as in the case of parallel displacement of 0.77 mm. Results of tests have shown that frequency analysis is proper tool for misalignment detection of the drive system. However the high resolution of measurement and diagnostic equipment is required as well as suitable experience of the expert. So recently other solution are searched for, which can minimize the participation of human expert in the drive diagnostics and can make the diagnostic process fully automatic. Methods based on neural network theory are capable to solve this task. In this paper the intelligent detector based on neural networks is developed for misalignment monitoring and detection for induction motor drive. The multilayer perceptron network (MLP) is trained and tested using magnitudes of specific harmonics of stator current and vibration spectra. It is shown that proposed neural detector is very effective in misalignment monitoring for induction motor drives.
EN
In this paper possibility of application the extended state observer algorithm to rotor and stator fault detection of induction motor. The induction motor condition is analyzed using estimated rotor or stator resistance. The motor mathematical model and algorithm of extended observer are presented. Rotor and stator resistance as a additional observer element are selected. The simulations showed high accuracy and fast response of extended observer algorithm. The experimental proved theoretical assumption and demonstrated extended state observer suitability to induction motor rotor and stator faults detection.
PL
W artykule przedstawiono analizę wpływu wybranych uszkodzeń sterownika silnika PM BLDC. Przeprowadzono analizę porównawczą wpływu uszkodzeń tranzystorów i czujników położenia wirnika na widma prądów fazowych. Przedstawiono symptomy uszkodzeń specyficznych dla napędu PM BLDC przy wykorzystaniu widma FFT prądu stojana. Zaprezentowano wyniki wybranych badań eksperymentalnych oraz zbiorcze zestawienie zawartości charakterystycznej częstotliwości w widmie prądów fazowych. Omówiono analityczne podstawy tej analizy. Zebrane informacje (symptomy i ich ograniczenia stosowania) mogą zostać wykorzystane w systemach diagnostyki napędów.
EN
In this work an influence of selected faults in PM BLDC motor driver has been presented. An influence of rotor position sensor and transistors faults on the phase currents spectrum has been analyzed. Specific symptoms of the faults in PM BLDC drive has been presented, using the FFT spectrum of the stator current. The results of experimental studies have been summarized in the list of the contents of the characteristic frequencies in the phase currents spectrum. Analytical basis of this analysis has also been discussed. The collected information (symptoms and the limitations of use) could be used in motor drive diagnostic systems.
10
Content available remote Pośrednia metoda pomiaru momentu elektromagnetycznego silnika indukcyjnego
51%
PL
Przedstawiono problemy odtwarzania w czasie rzeczywistym momentu elektromagnetycznego silnika indukcyjnego klatkowego na podstawie pomiaru prądów i napięć fazowych lub napięć indukowanych w dodatkowych cewkach pomiarowych w stojanie, z wykorzystaniem procesora sygnałowego. Porównano wartości momentów odtworzonych i zmierzonych bezpośrednio. Oceniono dokładność proponowanych metod pośredniego pomiaru momentu silnika indukcyjnego.
EN
Problems connected with the real-time reconstruction of the induction motor electromagnetic torque based on measurements of stator voltages and currents or voltage induced in special measurement coils introduced to the stator windings were disccused. The torque values measured directly and reconstructed with help of digital signal processor were compared. The exactness of proposed indirect measurement method of induction motor electromagnetic torque was evaluated.
11
Content available remote Zdalne sterowanie robotem przemysłowym poprzez sieć Internet
51%
PL
W artykule omówiono możliwości wykorzystania sieci Internet do zdalnego sterowania robotami przemysłowymi. Jako obiekt sterowania wykorzystano robota ramieniowego RV2AJ firmy Mitsubishi. Przedstawiono możliwości sterowania tego typu robota poprzez sieć komunikacyjną Internet. Zostało scharakteryzowane oprogramowanie do komunikacji pomiędzy robotem a klientem, umożliwiające zdalne sterowanie przemieszczaniem się ramienia manipulatora w dowolny zadany punkt. Protokół transmisji danych powiązany został z oprogramowaniem do gry w warcaby w taki sposób, że ruchy pionkami wykonywane były przez robota. Zastosowane oprogramowanie umożliwia jednoczesną transmisję obrazów z dwóch zainstalowanych na manipulatorze kamer internetowych.
EN
In the article possibilities of the utilization of the Internet to the remote control industrial robots were presented. Arm robot RV2AJ of the firm Mitsubishi was steering by the Internet. The techniques for this type of robot control via Internet were discussed. The software for communication between the robot and the client, enabling the remote control of the robot arm movement was described. The data transmission protocol was verified in the checkers game, where the pawns relocation was realized by robot. The used software enables the simultaneous transmission of images provided by two internet cameras mounted on the manipulator.
12
51%
PL
Niniejszy artykuł dotyczy zastosowania środowiska LabVIEW oraz sieci Ethernet do realizacji zadania zdalnego monitorowania przekształtnikowych układów napędowych z silnikami indukcyjnymi. Zaproponowano koncepcję realizacji zadania w warstwie sprzętowej (koncepcja stanowiska laboratoryjnego oraz w warstwie programistycznej (podział zadań pomiędzy aplikacją producenta, dystrybutora i konsumenta). Przedstawiono technologie umożliwiające realizację zadania zdalnego monitorowania pracy przekształtnikowego układu napędowego z silnikiem indukcyjnym. Zaprezentowano wyniki badań laboratoryjnych.
EN
The paper deals with the application of the LabView computational environment to remote monitoring of a converter induction motor drive system via Ethernet. Both the software solution (i.e. the task division between the customer's, producer's and distributor's applications) and the hardware solution (i.e. the laboratory setup design) are presented. The techniques for the remote monitoring and the selected aspects concerning their application are discussed. The results of the experimental tests are presented.
EN
In the paper analysis of the sensorless induction motor drive with rotor faults is presented. The rotor flux and speed is reconstructed using the MRAS CC estimator, where the induction motor is used as a reference model. The stator current estimator and current model of the rotor flux are used as adapted models. Most of the speed estimators used in sensorless drives are sensitive to motor parameters changes, especially to the rotor resistance changes. The proposed MRAS CC estimator is very robust to all motor parameter changes, thus it should work properly in the case of faulted rotor. In the paper simulation and experimental results of the sensorless IM drive with broken rotor bars are presented. Range of the stable work of the control system is shown. Characteristic frequency harmonics of the IM state variables connected with broken bars are introduced. The low speed region and the dynamical properties of the sensorless drive with rotor faults are tested.
EN
Diagnostics of electrical machines is complicated process based on such elements as: measurements of chosen signals and parameters of the motor, transformation of the obtained results in order to separate fault symptoms and the fault detector and classifier design. In this paper fault detectors and classifiers based on neural networks with radial activation function are implemented for diagnostics of rotor damages in induction motors. The main stages of the design methodology of the radial basis neural detectors are described. Furthermore, influence of neural networks complexity and parameters of neuronal activation function on quality of data classification is shown. Presented neural detectors are tested with measurement data obtained in laboratory setup contained of converter-fed induction motor and changeable rotors with different degree of damages.
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.