The PhD position is part of the European Training Network ‟ELO-X – Embedded Learning and Optimization for the neXt generation of smart industrial control systems”. ELO-X will recruit altogether 15 PhD fellows at 6 research universities and 5 international companies from 5 European countries, who will meet regularly during exchange visits, training events, workshops, and summer schools organized by the network.
The position at Bosch Research has a strong focus on application of advanced optimization based control algorithms to electric drive systems in the automotive field. The position will be based in the dynamic systems control group at Robert Bosch Research Campus in Renningen, Germany. Their aim is the development of advanced optimal control methods and their application to industrially relevant optimization and estimation problems. While the numeric optimization methods will be mainly developed in close cooperation with the other ELO-X PhD fellows, the target of the PhD Position at Bosch will be their application to electric drive systems containing dynamics with different time constants. The work will include mutual exchange visits of several months duration with partners at Albert-Ludwigs-University of Freiburg, Politecnico di Milano, and Universitatea Politehnica din Bucuresti.
Robert Bosch GmbH is the worlds biggest automotive supplier with 400k employees around the globe. Its research campus in Renningen, Germany, is the international hub of Bosch Research. Here, associates from all over the world are dedicated to finding answers to tomorrow’s questions. The PhD position will be with the dynamics system control group. With its twenty control scientists, this group brings together cutting-edge modeling and control methods with a broad spectrum of next generation Bosch applications. Among these are highly specialiced electric drives for future automotive systems.
PhD Project Description
PhD Project: Adaptive Multilayer MPC for Electrical Drives.
Although MPC offers a rich framework to realize optimal control regarding constraints, (cascaded) linear controllers are still state of the art for electric drives within industrial applications. The full potential of modern electric drive systems may only be exploited by regarding all system degrees of freedom at once, e.g., an entire electric drive system comprises interacting components like battery, inverter, electrical machine and mechanics. One challenge of such a unified approach are the different dynamic layers that have to be considered, e.g., current dynamics in the milliseconds range, temperature in the seconds range, and dynamics of wear ranging from hours to years. The objective for this PhD topic is threefold: (1) Multilayer MPC: The entire electrical drive system is to be taken into consideration for online optimization. Since computation of the entire dynamics at a rate higher than the fastest plant dynamics would be cumbersome, the target shall be to appropriately split the optimization problem into different computation time layers in order to reduce the overall computation burden. (2) Hybrid MPC: A typical electric drive system consists of continuous (currents or velocity) and discrete states (inverter switch positions, position of gear shift). Discontinuities render the optimization problem inherently a (mixed)-integer problem. Unlike exponentially complex solution approaches based on full-enumeration, the question is, whether solution of the optimization problem may be obtained in real time by appropriate relaxations and heuristic approaches. (3) Adaptive and learning MPC: Certain parameters of the e-drive will vary over life-time. Hence, they need to be learned on a high level in order to ensure optimal performance of the controlled system.
The expected milestones of this PhD project are: (1) Development of a control-oriented model of the entire electric drive system. (2) Development of a multilayer MPC algorithm for dynamics within the millisecond to minute range. (3) Extension of multilayer MPC towards learning of uncertain slowly varying parameters. (4) Verification of real-time capability of the multilayer MPC by appropriate solver development and evaluation on an embedded hardware in the loop system. (5) Verification of performance on existing test bench.
Timeline and remuneration:
The ideal start time is in the first half of 2021. The PhD project lasts for the duration of three years, and is carried out at Bosch in Renningen, Germany. The PhD years include at least one longer visit – a so called “secondment” – between one and six months to another group in the ELO-X network, depending on the project needs and the scientific interests of the PhD fellows. The first year is mainly dedicated to studying and getting acquainted with derivation of an appropriate system model, the second year focuses on development of appropriate MPC schemes and simulative studies, and the third year on application at test bench and publications. A fourth PhD year can be added and funds are reserved for this at the University of Freiburg. The remuneration is generous and will be in line with the EC rules for Marie Curie grant holders. It consists of a salary augmented by a mobility allowance, resulting in a net monthly salary of about 1900-2300 Euro depending on family status.
Supervisors and Main Contacts
Supervising team at Bosch Research:
Dr. Maximilian Manderla (project leader and research engineer working on next generation e-drive systems)
Dr. Stefan Gering (research engineer working on embedded optimization and control of electric drives)
Main Contacts at the ELO-X Partner Groups which could host secondments:
Prof. Dr. Moritz Diehl (University of Freiburg)
Prof. Lorenzo Mario Fagiano (Politecnico di Milano)
Prof. Ion Necoara (Polytechnic University of Bucharest)
Ideal candidates have a master degree in one of the following disciplines or a related field: control engineering or technical cybernetics, electrical engineering, numerical mathematics, or computational physics. They should have a good background or interest in electric machines, advanced control methods, dynamic system modelling and numeric optimization. Knowledge of machine learning methods and adaptive control is a plus. Proficiency in English is a requirement. The positions adhere to the European policy of balanced ethnicity, age and gender. Both men and women are encouraged to apply.
To apply, send an email to firstname.lastname@example.org in form of one single PDF attachment containing all contents or links (any other information within the email will not be processed). Subject of your email should be: “ELO-X PhD Application – ESR 11”.
Please include, in your single PDF document, the following items in this order:
A cover letter incl. statement of research interests and career goals (max. 2 pages);
An academic CV;
Contact details of at least two referees incl. phone numbers and emails;
Your diplomas and transcript of course work and grades;
Sample of technical writing (publication or thesis);
Proof of English language proficiency test results.
Applications for this position are being processed, but it is still possible to apply.
Note that your PDF will be forwarded to several people in the ELO-X institutions and that in particular all Supervisory Board members of ELO-X will have access to your application material. If you want to apply to more than one ELO-X position, please create and send separate PDFs.
Marie Curie Fellowship Eligibility Criteria in Short
To be eligible, you need to be an “early stage researcher” i.e. simultaneously fulfill the following criteria at the time of recruitment:
Nationality: you may be of any nationality.
Mobility: you must not have resided or carried out your main activity (work, studies, etc…) in Germany for more than 12 months in the 3 years immediately prior to your recruitment under the ELO-X project.
Qualifications and research experience: you must be in the first 4 years of your research career after the master degree was awarded.
Embedded learning and optimization for the next generation of smart industrial control systems European Training Network (ETN)
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No.953348
Project coordinated by:
Department of Microsystems Engineering (IMTEK)
University of Freiburg, Germany