|
|
Predictive maintenance of pneumatic pistons
Voronin, Artyom ; Rajchl, Matej (oponent) ; Brablc, Martin (vedoucí práce)
This thesis deals with creating a simulation model of a double-acting pneumatic piston with a mechanical assembly, including the sensors models, with the following parameter estimation and approximation to the behavior of a demonstration device. Another goal is the demonstration of various Predictive Maintenance approaches on a dataset measured on a demonstration device. Applying signal-based techniques to the measured dataset without using a simulation model and a model-based method that requires the use of a simulation model. The outcome of this work is the verification of the possibility of monitoring the device's condition state, using installed sensors, and evaluating the efficiency of the sensors in terms of accuracy/cost.
|
|
|
Aplikace algoritmů prediktivní údržby na odhad RUL
Dvořák, Jan ; Brablc, Martin (oponent) ; Dobossy, Barnabás (vedoucí práce)
Cílem této práce je seznámit čtenáře s oblastí prediktivní údržby a jejími algoritmy především v rámci její prognostické části. Na datových sadách a provedeném experimentu dojde k určení zbývající životnosti daného systému pomocí vytvořených modelů v souladu s algoritmy popsanými v rešeršní části. Ke zpracování dat a tvorbě modelů bylo využito nástroje MATLAB a jeho dalších aplikací popsaných v práci.
|
|
|
Methods of Technical Prognostics Applicable to Embedded Systems
Krupa, Miroslav ; Ďaďo, Stanislav (oponent) ; Tůma, Jiří (oponent) ; Bejček, Ludvík (vedoucí práce)
The main aim of the thesis is to provide a comprehensive overview of technical prognosis, which is applied in the condition based maintenance, based on continuous device monitoring and remaining useful life estimation, especially in the field of complex equipment and machinery. Nowadays technical prognosis is still evolving discipline with limited number of real applications and is not so well developed as technical diagnostics, which is fairly well mapped and deployed in real systems. Thesis provides an overview of basic methods applicable for prediction of remaining useful life, metrics, which can help to compare the different approaches both in terms of accuracy and in terms of computational/deployment cost. One of the research cores consists of recommendations and guide for selecting the appropriate forecasting method with regard to the prognostic criteria. Second thesis research core provides description and applicability of particle filtering framework suitable for model-based forecasting. Verification of their implementation and comparison is provided. The main research topic of the thesis provides a case study for a very actual Li-Ion battery health monitoring and prognostics with respect to continuous monitoring. The case study demonstrates the prognostic process based on the model and compares the possible approaches for estimating both the runtime and capacity fade. Proposed methodology is verified on real measured data.
|
|
|
Aplikace algoritmů prediktivní údržby na odhad RUL
Dvořák, Jan ; Brablc, Martin (oponent) ; Dobossy, Barnabás (vedoucí práce)
Cílem této práce je seznámit čtenáře s oblastí prediktivní údržby a jejími algoritmy především v rámci její prognostické části. Na datových sadách a provedeném experimentu dojde k určení zbývající životnosti daného systému pomocí vytvořených modelů v souladu s algoritmy popsanými v rešeršní části. Ke zpracování dat a tvorbě modelů bylo využito nástroje MATLAB a jeho dalších aplikací popsaných v práci.
|
|
|
Predictive maintenance of pneumatic pistons
Voronin, Artyom ; Rajchl, Matej (oponent) ; Brablc, Martin (vedoucí práce)
This thesis deals with creating a simulation model of a double-acting pneumatic piston with a mechanical assembly, including the sensors models, with the following parameter estimation and approximation to the behavior of a demonstration device. Another goal is the demonstration of various Predictive Maintenance approaches on a dataset measured on a demonstration device. Applying signal-based techniques to the measured dataset without using a simulation model and a model-based method that requires the use of a simulation model. The outcome of this work is the verification of the possibility of monitoring the device's condition state, using installed sensors, and evaluating the efficiency of the sensors in terms of accuracy/cost.
|
|
|
Methods of Technical Prognostics Applicable to Embedded Systems
Krupa, Miroslav ; Ďaďo, Stanislav (oponent) ; Tůma, Jiří (oponent) ; Bejček, Ludvík (vedoucí práce)
The main aim of the thesis is to provide a comprehensive overview of technical prognosis, which is applied in the condition based maintenance, based on continuous device monitoring and remaining useful life estimation, especially in the field of complex equipment and machinery. Nowadays technical prognosis is still evolving discipline with limited number of real applications and is not so well developed as technical diagnostics, which is fairly well mapped and deployed in real systems. Thesis provides an overview of basic methods applicable for prediction of remaining useful life, metrics, which can help to compare the different approaches both in terms of accuracy and in terms of computational/deployment cost. One of the research cores consists of recommendations and guide for selecting the appropriate forecasting method with regard to the prognostic criteria. Second thesis research core provides description and applicability of particle filtering framework suitable for model-based forecasting. Verification of their implementation and comparison is provided. The main research topic of the thesis provides a case study for a very actual Li-Ion battery health monitoring and prognostics with respect to continuous monitoring. The case study demonstrates the prognostic process based on the model and compares the possible approaches for estimating both the runtime and capacity fade. Proposed methodology is verified on real measured data.
|
host ::
RSS.