Master thesis: The application of machine learning to optimize the
Siemens Energy AB / Maskiningenjörsjobb / Finspång
Observera att sista ansökningsdag har passerat.
Visa alla maskiningenjörsjobb i Finspång,
Norrköping,
Linköping,
Vingåker,
Katrineholm eller i
hela Sverige Visa alla jobb hos Siemens Energy AB i Finspång,
Norrköping,
Örebro,
Västerås,
Filipstad eller i
hela Sverige Background
Artificial intelligence (AI) is crafting the digital transformation of our world today. AI is increasingly being adopted for quality control and process optimization in manufacturing. Machine learning (ML) is a meaningful element that enables the adoption of AI. Machine learning (ML) models and tools, for example Neural Network, Decision Trees and Gaussian processes, can be utilized to optimize manufacturing processes. ML enables a model to be successively trained by labelled or unlabeled data until a suitable model that can predict previously unseen data is obtained. Thus, it is of interest to utilize ML to optimize manufacturing processes. Such optimization will produce components with improved properties, high productivity and low cost. The manufacturing process of interest here is laser powder bed fusion which is an additive manufacturing (AM) process. AM is a technology which is also shaping new ways of producing components. AM enables complex components to be manufactured by printing successive layers of powder. The components produced by an optimized AM process possess superior performance to those manufactured by conventional methods. When AM part is built with a high layer thickness, high efficiency and low cost can be attained.
Aims
The aim is to use ML models and tools to optimize a high layer thickness (120 um) laser powder bed fusion process. This layer thickness is higher than that of many processes currently available in the literature. With certain combinations of Powder Bed Fusion - Laser Beam (PBF-LB) process parameters, there are risks that defects will be formed or that the required properties are not attained. With other combinations, the required microstructure and properties could be attained. Using the high layer PBF-LB process, we will manufacture samples, and their properties will be tested thereby generating data. Thus, the input will be data describing the equipment process parameters and the output will be data describing the material microstructure and properties. The data whose attributes are the mechanical properties will be labelled. The student's main goal is to apply suitable ML tools to train and produce a predictive model. This model will be used to optimize the process. Your results will be valuable and will provide the knowledge necessary for Siemens Energy to eventually optimize the manufacturing of our components.
* The student will engage in the following activities:
* Perform a literature review of ML methods suitable for AM process optimization.
* Identify suitable problem statements and ML methods.
* Train and develop models to predict/ optimize the PBF-LB process.
* Test and validate the developed models.
Interpret useful results and give valuable insight into the suitability of ML for AM process optimization.
Let's talk about you
We believe this thesis is suitable for a master's degree student within Mathematics, Statistics, Data Science, Computer Science, Mechanical Engineering, Manufacturing Engineering, Material science or related programs. Knowledge of ML and suitable software for example Python is essential. You will probably need the following attributes to succeed:
* Enthusiasm about the latest technology.
* Willingness to learn new things.
* Interest in gaining practical insight of theoretical concepts.
* Interest in systematic ways of performing tasks.
Let's talk about us
We have the right skills and environment to help you succeed. You will work in a friendly team, learn leadership skills, and establish valuable network necessary to accelerate your career. Working on this thesis with Siemens energy gives you an opportunity to gain industry experience in additive manufacturing technology that is shaping the new ways of making things.
Our Gas Services division offers Low-emission power generation through service and decarbonization. Zero or low emission power generation and all gas turbines under one roof, steam turbines and generators. Decarbonization opportunities through service offerings, modernization, and digitalization of the fleet.
Check out this page to learn more about our Gas Service business
https://www.siemens-energy.com/global/en/offerings/power-generation.htmlWe can offer you employment benefits such as: reduction of working hours, advance vacation, health care allowance and an eventual possibility to a flexible working place.
What's it like to work at Siemens Energy? Take a look:
https://bit.ly/3hD9pvK Who is Siemens Energy?
At Siemens Energy, we are more than just an energy technology company. We meet the growing energy demand across 90+ countries while ensuring our climate is protected. With more than 92,000 dedicated employees, we not only generate ele...
Ersättning Fixed salary
Så ansöker du Sista dag att ansöka är 2023-05-21
Klicka på denna länk för att göra din ansökan Arbetsgivarens referens Arbetsgivarens referens för detta jobb är "244001".
Omfattning Detta är ett deltidsjobb.
Arbetsgivare Siemens Energy AB (org.nr 556606-6048)
Arbetsplats Siemens Energy
Jobbnummer 7716309
Observera att sista ansökningsdag har passerat.