|
| |
|
|
Implementation and practical verification of methods for predictive identification of rolling bearings failures
Bár, Martin ; Havránek, Zdeněk (referee) ; Klusáček, Stanislav (advisor)
The aim of this thesis is to identify and classify rolling bearing failures. The first part of the thesis deals with the diagnosis of bearings using in-house measured data. Faults were introduced into two bearings. The first one was deformed and corroded. In the second bearing, the outer raceway was damaged. Vibration data was collected at regular intervals and processed in MATLAB. The values of the statistical features indicated faults in both bearings. Envelope analysis showed that both bearings had developed a fault on the outer raceway and a gradual fault on the cage. In the second part of this thesis, machine learning methods were used to classify defective bearings using the CWRU data set. The accelerometer data were divided into blocks in two ways. Vibration images were created from these blocks for convolutional neural networks (CNNs). The best prediction accuracy was achieved by 1D convolutional neural network (1DCNN) (99.2 %), followed by neural network (94.6 %) and SVM (94.4 %). Random Forest and SVM are the best methods when the training set is reduced, and among CNNs, MATLAB architecture and 1DCNN are the best. The most noise resistant method is Random Forest and neural network, and among CNNs, 1DCNN is the best. Methods using statistical features perform better than CNNs on extremely noisy data. Convolutional networks do not achieve good accuracy, which is probably due to the conversion of raw accelerometer data into vibration images.
|
|
| |
|
|
Diagnosis of mechanical vibrations in asynchronous motor origin
Dostál, Martin ; Dostál, Lukáš (referee) ; Janda, Marcel (advisor)
Every machine needs to be maintained and controlled, if may work reliably during they service life. Big part of service life of expensive machines are those machines in operation. Vibration diagnostics is type of analysis, that doesn’t need removal of rotation machinery. The vibration, that are created by running machinery, are used as source of information about mode of operation. This master’s thesis contains theoretical analysis of vibration diagnostics and vibration measurements of a particular machine. This thesis contains 3D models of bearings and rotor asynchronous machine, which are created by software Autodesk Inventor 2014. Bearings vibration analysis of this models is performed by software Ansys Workbench.
|
|
|
Implementation and practical verification of methods for predictive identification of rolling bearings failures
Bár, Martin ; Havránek, Zdeněk (referee) ; Klusáček, Stanislav (advisor)
The aim of this thesis is to identify and classify rolling bearing failures. The first part of the thesis deals with the diagnosis of bearings using in-house measured data. Faults were introduced into two bearings. The first one was deformed and corroded. In the second bearing, the outer raceway was damaged. Vibration data was collected at regular intervals and processed in MATLAB. The values of the statistical features indicated faults in both bearings. Envelope analysis showed that both bearings had developed a fault on the outer raceway and a gradual fault on the cage. In the second part of this thesis, machine learning methods were used to classify defective bearings using the CWRU data set. The accelerometer data were divided into blocks in two ways. Vibration images were created from these blocks for convolutional neural networks (CNNs). The best prediction accuracy was achieved by 1D convolutional neural network (1DCNN) (99.2 %), followed by neural network (94.6 %) and SVM (94.4 %). Random Forest and SVM are the best methods when the training set is reduced, and among CNNs, MATLAB architecture and 1DCNN are the best. The most noise resistant method is Random Forest and neural network, and among CNNs, 1DCNN is the best. Methods using statistical features perform better than CNNs on extremely noisy data. Convolutional networks do not achieve good accuracy, which is probably due to the conversion of raw accelerometer data into vibration images.
|
|
|
Bearings for space
Vavřík, Petr ; Nečas, David (referee) ; Košťál, David (advisor)
Currently, space satellites in orbit are required to operate reliably for more than 10 years. This places high demands on the satellite's tribological systems, which must function properly in the hostile space environment for this period. This bachelor thesis deals with the description of suitable bearings and their lubrication for space applications. Lubrication regimes are described at the outset. Then, space factors affecting the proper operation of tribological systems are summarized. The largest part is devoted to the description of the most used bearings and lubricants. The thesis concludes with the design of suitable bearings and their lubrication for the satellite reaction wheel.
|
|
|
Design of apparatus for testing of bearings
Sovadina, František ; Šperka, Petr (referee) ; Svoboda, Petr (advisor)
In this bachelor thesis an analysis of used test devices for durability of the rolling bearing was performed. This analysis then serves as an inspiration for the reconstruction of the existing bearing test facility at FME BUT. Three conceptual designs have been developed and, after consideration of all aspects, drawing documentation for the final variant has been produced. Its design will lead to space saving in the laboratory and easier handling of test equipment in durability tests.
|
|
|
The influence of the frequency converter on the life and damage of bearings
Sukovatý, Adam ; Krejčí, Petr (referee) ; Nahodil, Petr (advisor)
This thesis deals with the effect of frequency inverter on the lifetime of roller bearings. The measurement has been carried out on the frequency inverter and induction motor by Siemens in the Switchgear laboratory of Fakulty of elektrical engineering and communication. Data has been recorded and processed on Adash VA4 Pro analyzer. Methods of measuring RMS values and frequency analysis of vibration and current were used for the analysis. Based on the mutual similarity of frequency spectrum, the presence of the high frequency capacitive current in the bearings has been proven. To prevent this, possible solutions have been presented. In the second part of the experiment an effect of changing pulse width modulation (PWM) on vibration was examined. The goal was to make a basic analysis and to provide background material for further research.
|
|
| |
|
|
Turbocharger Rotors using Rolling Bearings
Šárovec, Marek ; Dlugoš, Jozef (referee) ; Novotný, Pavel (advisor)
The main purpose of this diploma thesis is to design turbocharger rotor using rolling element bearings. The diploma thesis is compiled from two specialized search parts dealing with turbocharger rotor and rolling element bearing computation, respectively. The application of the particular rotor using the multi body system Adams – View is described in the following chapter. In the last chapter, one can find the comparison between rotor using bearing with steal and hybrid ceramic rolling element. Also, there is compariosn between rolling element bearing and journal bearing. In the maximum rotor speed, the decrease of more than 50 % in power loss, due to usage of rolling element bearing, resulted from this comparison.
|
guest ::
