liu.seSearch for publications in DiVA
1 - 2 of 2
rss atomLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
  • Presentation: 2017-05-31 10:15 Planck, D-huset, Linköping
    Voronov, Sergii
    Linköping University, Department of Electrical Engineering, Vehicular Systems. Linköping University, Faculty of Science & Engineering.
    Data-driven lead-acid battery lifetime prognostics2017Licentiate thesis, comprehensive summary (Other academic)
    Abstract [en]

    To efficiently transport goods by heavy-duty trucks, it is important that vehicles have a high degree of availability and in particular avoid becoming standing by the road unable to continue the transport mission. An unplanned stop by the road does not only cost due to the delay in delivery, but can also lead to a damaged cargo. High availability can be achieved by changing components frequently, but such an approach is expensive both due to the frequent visits to a workshop and also due to the component cost. Therefore, failure prognostics and flexible maintenance has significant potential in the automotive field for both manufacturers, commercial fleet owners, and private customers.

    In heavy-duty trucks, one cause of unplanned stops are failures in the electrical power system, and in particular the lead-acid starter battery. The main purpose of the battery is to power the starter motor to get the diesel engine running, but it is also used to, for example, power auxiliary units such as cabin heating and kitchen equipment. Detailed physical models of battery degradation is inherently difficult and requires, in addition to battery health sensing which is not available in the given study, detailed knowledge of battery chemistry and how degradation depends on the vehicle and battery usage profiles.

    The main aim of the given work is to predict the lifetime of lead-acid batteries using data-driven approaches. Main contributions in the thesis are: a) the choice of the Random Survival Forest method as the model for predicting a conditional reliability function which is used as the estimator of the battery lifetime, b) variable selection for better predictability of the model and c) variance estimation for the Random Survival Forest method.

    When developing a data-driven prognostic model and the number of available variables is large, variable selection is an important task, since including non-informative variables in the model have a negative impact on prognosis performance. Two features of the dataset has been identified, 1) there are few informative variables, and 2) highly correlated variables in the dataset. The main contribution is a novel method for identifying important variables, taking these two properties into account, using Random Survival Forests to estimate prognostics models. The result of the proposed method is compared to existing variable selection methods, and applied to a real-world automotive dataset.

    Confidence bands are introduced to the RSF model giving an opportunity for an engineer to observe the confidence of the model prediction. Some aspects of the confidence bands are considered: a) their asymptotic behavior and b) usefulness in the model selection. A problem of including time related variables is addressed in the thesis with arguments why it is a good choice not to add them into the model. Metrics for performance evaluation are suggested which show that the model can be used to find and optimize cost of the battery replacement.

    List of papers
    1. Heavy-duty truck battery failure prognostics using random survival forests
    Open this publication in new window or tab >>Heavy-duty truck battery failure prognostics using random survival forests
    2016 (English)In: IFAC PAPERSONLINE, ELSEVIER SCIENCE BV , 2016, Vol. 49, no 11, 562-569 p.Conference paper (Refereed)
    Abstract [en]

    Predicting lead-acid battery failure is important for heavy-duty trucks to avoid unplanned stops by the road. There are large amount of data from trucks in operation, however, data is not closely related to battery health which makes battery prognostic challenging. A new method for identifying important variables for battery failure prognosis using random survival forests is proposed. Important variables are identified and the results of the proposed method are compared to existing variable selection methods. This approach is applied to generate a prognosis model for lead-acid battery failure in trucks and the results are analyzed. (C) 2016, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

    Place, publisher, year, edition, pages
    ELSEVIER SCIENCE BV, 2016
    Keyword
    Battery failure prognosis; Random survival forests; Variable selection
    National Category
    Transport Systems and Logistics
    Identifiers
    urn:nbn:se:liu:diva-132240 (URN)10.1016/j.ifacol.2016.08.082 (DOI)000383464400082 ()
    Conference
    8th IFAC Symposium on Advances in Automotive Control (AAC)
    Available from: 2016-10-24 Created: 2016-10-21 Last updated: 2017-05-19
    2. Variable selection for heavy-duty vehicle battery failure prognostics using random survival forests
    Open this publication in new window or tab >>Variable selection for heavy-duty vehicle battery failure prognostics using random survival forests
    2016 (English)Conference paper (Refereed)
    Abstract [en]

    Prognostics and health management is a useful tool for more flexible maintenance planning and increased system reliability. The application in this study is lead-acid battery failure prognosis for heavy-duty trucks which is important to avoid unplanned stops by the road. There are large amounts of data available, logged from trucks in operation. However, datais not closely related to battery health which makes battery prognostic challenging. When developing a data-driven prognostics model and the number of available variables is large,variable selection is an important task, since including non-informative variables in the model have a negative impact on prognosis performance. Two features of the dataset has been identified, 1) few informative variables, and 2) highly correlated variables in the dataset. The main contribution is a novel method for identifying important variables, taking these two properties into account, using Random Survival Forests to estimate prognostics models. The result of the proposed method is compared to existing variable selection methods,and applied to a real-world automotive dataset. Prognostic models with all and reduced set of variables are generated and differences between the model predictions are discussed, and favorable properties of the proposed approach are highlighted.

    Keyword
    variable selection, random survival forest, battery failure prognostics
    National Category
    Other Electrical Engineering, Electronic Engineering, Information Engineering
    Identifiers
    urn:nbn:se:liu:diva-131788 (URN)978-1-936263-21-9 (ISBN)
    Conference
    Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, July 5-8, 2016
    Available from: 2016-10-06 Created: 2016-10-06 Last updated: 2017-05-19
  • Presentation: 2017-06-02 10:15 ACAS, A-huset, Linköping
    Kahlin, Magnus
    Linköping University, Department of Management and Engineering. Linköping University, Faculty of Science & Engineering.
    Fatigue Performance of Additive Manufactured Ti6Al4V in Aerospace Applications2017Licentiate thesis, comprehensive summary (Other academic)
    Abstract [en]

    Additive Manufacturing (AM) for metals includes is a group of production methodst hat use a layer-by-layer approach to directly manufacture final parts. In recent years, the production rate and material quality of additive manufactured materials have improved rapidly which has gained increased interest from the industry to use AM not only for prototyping, but for serial production. AM offers a greater design freedom, compared to conventional production methods, which allows for parts with new innovative design. This is very attractive to the aerospace industry, in which parts could be designed to have reduced weight and improved performance contributing to reduced fuel consumption, increased payload and extended flight range. There are, however, challenges yet to solve before the potential of AM could be fully utilized in aerospace applications. One of the major challenges is how to deal with the poor fatigue behaviour of AM material with rough as-built surface.

    The aim of this thesis is to increase the knowledge of how AM can be used for high performance industrial parts by investigating the fatigue behaviour of the titanium alloy Ti6Al4V produced with different AM processes. Foremost, the intention is to improve the understanding of how rough as-built AM surfaces in combination with AM built geometrical notches affects the fatigue properties.This was done by performing constant amplitude fatigue testing to compare different combinations of AM material produced by Electron Beam Melting(EBM) and Laser Sintering (LS) with machined or rough as-built surfaces with or without geometrical notches and Hot Isostatic Pressing (HIP) treatment. Furthermore, the material response can be different between constant amplitude and variable amplitude fatigue loading due to effects of overloads and local plastic deformations. The results from constant amplitude testing were used to predict the fatigue life for variable amplitude loading by cumulative damage approach and these predictions were then verified by experimental variable amplitude testing.

    The constant amplitude fatigue strength of material with rough as-built surfaces was found to be 65-75 % lower, compared to conventional wrought bar, in which HIP treatments had neglectable influence on the fatigue strength. Furthermore, the fatigue life predictions with cumulative damage calculations showed good agreement with the experimental results which indicates that a cumulative damage approach can be used, at least for a tensile dominated load sequences, to predict the fatigue behaviour of additive manufactured Ti6Al4V.

    List of papers
    1. Fatigue Behaviour of Notched Additive Manufactured Ti6Al4V with As-built Surfaces
    Open this publication in new window or tab >>Fatigue Behaviour of Notched Additive Manufactured Ti6Al4V with As-built Surfaces
    2017 (English)In: International Journal of Fatigue, ISSN 0142-1123, E-ISSN 1879-3452, no 101, 51-60 p.Article in journal (Refereed) Published
    Abstract [en]

    Additive manufacturing (AM) allows the manufacturer to produce parts with complex geometries that are difficult to produce with conventional production methods. Generally, AM is considered to have great potential for the aerospace industry by contributing to reduced weight and lower costs. There are a number of challenges to be solved before AM can be fully utilized in the aerospace industry, and the understanding of fatigue behaviour is one of the major challenges. Although the fatigue properties of flat additive manufactured specimens with rough as-built surfaces already have been widely studied, in practice, few aerospace components have a simple flat geometry with no corners or radii that would act as stress concentrations. Therefore, the combined effect on fatigue life of a rough as-built surface and a geometrical notch needs to be established. In this study, the fatigue properties of both laser sintered and electron beam melted Ti6Al4V have been investigated and a combined effect of a rough as-built surface and a geometrical notch has been determined. In addition, hot isostatic pressing was found to have no impact on fatigue life for rough as-built surfaces. These findings can be directly applied to predict fatigue behaviour of an AM industrial component.

    Keyword
    Additive manufacturing, Fatigue, Ti6Al4V, Stress concentration, Fatigue notch factor
    National Category
    Materials Engineering
    Identifiers
    urn:nbn:se:liu:diva-137163 (URN)10.1016/j.ijfatigue.2017.04.009 (DOI)
    Available from: 2017-05-08 Created: 2017-05-08 Last updated: 2017-05-24Bibliographically approved