TU Darmstadt / ULB / TUbiblio

Hidden semi-Markov Models for Predictive Maintenance of Rotating Elements

Anger, Christoph (2018):
Hidden semi-Markov Models for Predictive Maintenance of Rotating Elements.
Darmstadt, Technische Universität, [Online-Edition: http://tuprints.ulb.tu-darmstadt.de/7646],
[Ph.D. Thesis]

Abstract

The dissertation at hand introduces a novel algorithm to predict the remaining useful life (RUL) of rotating components such as grooved ball bearings or gear boxes. The focus of the implemented method is on so-called Hidden semi-Markov Models (HsMM), which are suitable for the modeling of sequential events. The selected method is designed to support maintenance processes based on advisory generation in the context of predictive maintenance. In this regard, the goal of predictive maintenance is the generation of predictions about the RUL of examined components based on their current state. Thus, maintenance events can be scheduled more precisely, downtime is reduced, and the actual useful life of components can be exploited. After an initial classification of the proposed method in the context of Prognostics and Health Management (PHM), the concept is described. The algorithm is based on methods, which apply historical data of the component’s degradation process for the estimation of the current and future damage state. A novel concept in the field of HsMM permits the identification of similar damage states within different degradation datasets to obtain more information about the damage process of the examined components. A further research question analyzes, whether the consideration of available information about the component’s endured load increases the prognostic performance. First results in the context of verification conclude the concept description. Subsequently, the design and realization of a new test rig, which permits an accelerated bearing aging for induction machines due to a so-called bearing current, is presented. Here, an alternating current flows through the tested bearing and reduces its life cycle significantly. By means of these data, the concept is evaluated. In comparison to state-of-the-art methods in field of bearing PHM, the validation is executed by examining the motor current of the induction machine instead of the widespread analysis of the resulting vibration signal. The results indicate that the precise and accurate prediction of the bearing’s RUL is possible. In addition, the consideration of already endured load for the generation of life cycle predictions is beneficial. A selected state-of-the-art algorithm, also based on HsMM, permits a realistic evaluation of the achieved prognostic performance. The dissertation ends with the estimation of possible cost savings in an exemplary aircraft maintenance scenario. For this, the obtained prognostic results are assessed with a state-of-the-art cost-benefit analysis tool. The outcome indicates that the application of the proposed algorithm leads to savings due to e.g. decreased downtimes.

Item Type: Ph.D. Thesis
Erschienen: 2018
Creators: Anger, Christoph
Title: Hidden semi-Markov Models for Predictive Maintenance of Rotating Elements
Language: English
Abstract:

The dissertation at hand introduces a novel algorithm to predict the remaining useful life (RUL) of rotating components such as grooved ball bearings or gear boxes. The focus of the implemented method is on so-called Hidden semi-Markov Models (HsMM), which are suitable for the modeling of sequential events. The selected method is designed to support maintenance processes based on advisory generation in the context of predictive maintenance. In this regard, the goal of predictive maintenance is the generation of predictions about the RUL of examined components based on their current state. Thus, maintenance events can be scheduled more precisely, downtime is reduced, and the actual useful life of components can be exploited. After an initial classification of the proposed method in the context of Prognostics and Health Management (PHM), the concept is described. The algorithm is based on methods, which apply historical data of the component’s degradation process for the estimation of the current and future damage state. A novel concept in the field of HsMM permits the identification of similar damage states within different degradation datasets to obtain more information about the damage process of the examined components. A further research question analyzes, whether the consideration of available information about the component’s endured load increases the prognostic performance. First results in the context of verification conclude the concept description. Subsequently, the design and realization of a new test rig, which permits an accelerated bearing aging for induction machines due to a so-called bearing current, is presented. Here, an alternating current flows through the tested bearing and reduces its life cycle significantly. By means of these data, the concept is evaluated. In comparison to state-of-the-art methods in field of bearing PHM, the validation is executed by examining the motor current of the induction machine instead of the widespread analysis of the resulting vibration signal. The results indicate that the precise and accurate prediction of the bearing’s RUL is possible. In addition, the consideration of already endured load for the generation of life cycle predictions is beneficial. A selected state-of-the-art algorithm, also based on HsMM, permits a realistic evaluation of the achieved prognostic performance. The dissertation ends with the estimation of possible cost savings in an exemplary aircraft maintenance scenario. For this, the obtained prognostic results are assessed with a state-of-the-art cost-benefit analysis tool. The outcome indicates that the application of the proposed algorithm leads to savings due to e.g. decreased downtimes.

Place of Publication: Darmstadt
Divisions: 16 Department of Mechanical Engineering
16 Department of Mechanical Engineering > Institute of Flight Systems and Automatic Control (FSR)
16 Department of Mechanical Engineering > Institute of Flight Systems and Automatic Control (FSR) > Safe Systems
Date Deposited: 19 Aug 2018 19:55
Official URL: http://tuprints.ulb.tu-darmstadt.de/7646
URN: urn:nbn:de:tuda-tuprints-76464
Referees: Klingauf, Prof. Dr. Uwe and Melz, Prof. Dr. Tobias
Refereed / Verteidigung / mdl. Prüfung: 20 February 2018
Alternative Abstract:
Alternative abstract Language
Die vorliegende Dissertation stellt einen neuartigen Algorithmus zur Lebensdauerbestimmung von rotierenden Bauteilen wie Rillenkugellagern oder Getrieben vor. Im Zentrum der implementierten Methode stehen sogenannte Hidden semi-Markov Modelle (HsMM), die sich für die Abbildung von sequentiellen Ereignissen eignen. Die gewählte Methode soll den Wartungsbetrieb durch Handlungsempfehlungen im Rahmen der prädiktiven Instandhaltung unterstützen. Ziel der prädiktiven Instandhaltung ist, ausgehend von dem aktuellen Zustand der Komponente, Prognosen hinsichtlich der verbleibenden Restlebensdauer zu generieren. Dadurch können Wartungsevents planbarer gestaltet, Stillstandszeiten verringert und der nutzbare Lebenszyklus von Komponenten ausgenutzt werden. Nach einer Einordung der Methode in den Kontext des Prognostics and Health Managements, erfolgt die Konzeptbeschreibung. Der Algorithmus besteht dabei aus Verfahren, die, basierend auf historischen Daten über den Degradierungsprozess der untersuchten Komponente, den aktuellen Schadenszustand schätzen sowie den zukünftigen Schadensverlauf prognostizieren. Ein neuartiges Konzept ermöglicht es, mithilfe der HsMM vergleichbare Schadenszustände in verschiedenen Degradierungsdaten zu identifizieren, um somit mehr Informationen über den Schädigungsprozess der untersuchten Komponente zu erhalten. Eine weitere Forschungsfrage betrachtet, ob das Einbinden von verfügbaren Informationen über die Belastung der Komponente Vorteile hinsichtlich der Prognosegenauigkeit zeigt. Erste Ergebnisse im Rahmen einer Verifikation schließen die Konzeptbeschreibung ab. Nachfolgend wird die Auslegung und Umsetzung eines Prüfstands beschrieben, der eine künstlich beschleunigte Rillenkugellageralterung in Asynchronmotoren mithilfe von sogenanntem Lagerstrom realisiert. Hierbei fließt ein elektrischer Wechselstrom durch das Testlager und reduziert drastisch seine Lebensdauer. Mit diesen Daten wird im Anschluss das Konzept validiert. Im Vergleich zu anderen Verfahren aus dem Bereich der Lagerlebensdauerschätzung, die den Körperschall für die Zustandsüberwachung untersuchen, wird für die Validierung in dieser Dissertation der Statorstrom des Asynchronmotors genutzt. Die Ergebnisse zeigen, dass auch hiermit eine genaue Prognose der Restlebensdauer von Kugellagern möglich ist. Auch die Verwendung der bereits ertragenen Belastung in die Generierung von Prognosen weisen deutliche Vorteile auf. Ein etabliertes Vergleichskonzept, welches ebenfalls auf HsMM basiert, ermöglicht eine realistische Einordnung der Prognoseergebnisse. Abschließend werden die Resultate hinsichtlich möglicher Einsparungen in einem exemplarischen Flugzeugwartungsszenario untersucht. Hierfür dient ein Kosten-Nutzen-Rechnung-Simulationswerkzeug aus der Literatur. Es zeigt sich, dass durch die Anwendung des vorgestellten Algorithmus Kosteneinsparungen, insbesondere im Bereich der Stillstandfolgekosten, möglich sind.German
Export:

Optionen (nur für Redakteure)

View Item View Item