This site uses cookies to enhance navigation. If you continue with your visit, you accept the use of cookies and privacy policy. Accept

IK4 Doctorados

 

TEKNIKER

People whose vocation are focused on enhancing the innovative capabilities of their customers and furthering their technological capital.

 
DOCTORATES

TEKNIKER

Development of degradation and prediction models to determine the health of lubricated rotary machines

TEKNIKER

START: 10/2017

OPEN

OBTAINING DOCTOR DEGREE: 09/2020

Description

The proliferation of Industry 4.0-related machines opens up a whole host of monitoring possibilities that will enable the emergence of new businesses based on extracting knowledge from existing data. This is why knowing how components wear out and being able to predict their behaviour in order to improve the reliability and maintenance of the equipment will be a key to accessing these new opportunities. It will therefore be necessary to have a solid understanding of the existing analytical possibilities:

  • - Predictive analytics is a discipline that encompasses a variety of techniques such as statistics, modelling, machine learning and data mining, used to analyse past and present facts and to make predictions about the future or other uncertain events.

    - The resulting models identify relationships between the different factors to facilitate the assessment of the risks and benefits associated with a particular set of conditions, which are used to guide decision-making.

Prescriptive analytics goes a step further and determines the actions to perform depending on the prediction made; essentially, identifying maintenance actions to be carried out and determining the best time and way to do this, taking into account the equipment degradation models.

The aim of the thesis is to study predictive and prescriptive analysis in the field of rotating machines. The thesis will focus on the use of commercial sensor systems to determine the health of rotating components such as bearings and gears, and thus predict how their health will evolve. For this, we will use a combination of information from different sensors that will enrich the information from the degradation model.

The main points studied will be:

  • - Processing data to extract useful characteristics for monitoring the health of the components.

  • - Determining, using automatic learning techniques, the characteristics that best identify the degradation of components.

  • - Models to predict the evolution of the health of components.

  • - Simulation of options for decision-making depending on the maintenance opportunities.

Department or unit of the Associates Technology Center

Intelligent Information Systems Unit

Investigation line

Predictive and prescriptive analytics

Start date planned

10/2017

Obtaining date of the doctor degree

09/2020

Requeriments

- Masters level required (completed before starting the Ph.D. programme)
- Research vocation
- English
- Particularly welcome is a University Master"s Degree in Computational Engineering and Intelligent Systems from the EHUUPV (University of the Basque Country), but other studies will also be considered.
- Knowledge of data mining and machine learning will be highly valued.
- Programming skills in R, Matlab, and Weka are also welcome.
- Initiative and the ability to solve problems are essential.

IK4 Research Alliance SELECT IN ORDER OF PREFERENCE THE OFFERS YOU WISH TO APPLY FOR

With number 1 as the first option, 2 as the second and 3 as the last option.

Remember, only click "Send" once you have configured your options correctly. Click on the "Save" button to add more options, or to change their position.