Whirlpool is looking at advanced controls technologies including machine learning, neural networks, and model predictive controllers that will more efficiently cool complex refrigerator systems. Students on this team will evaluate current capabilities on the Python framework that will be fast prototyped and applied in a simulation environment with a conceptual plant model.
Abstract:
Whirlpool, the world’s leading major home appliance company, has been an innovator for over 100 years, beginning with a patent for an electric-driven wringer washer. Current refrigerator advancements are taking the appliance from a two compartment device (refrigerator and freezer) to one with multiple compartment systems that allow the user to quickly access snacks or even convert compartments from refrigerator to freezer and back again. These compartments increase the energy consumption of the system and require significant increases in expensive insulation to manage temperature control.
In order to drive disruptive innovation on performance algorithms, Whirlpool is looking at methods and ways to easily design, prototype, and test advanced controls technologies including machine learning, neural networks, and model predictive controllers that will more efficiently cool these complex systems.
Impact:
Development of advanced controls for refrigeration will allow Whirlpool to decrease energy consumption, and reduce insulation costs. This energy reduction will further help Whirlpool in its mission to exceed carbon emission reduction targets that are aligned with the Paris Climate Agreement.
See complete details
Python programming (2-4 Students)
Specific Skills: General programming skills.
Completion of EECS 281 or equivalent knowledge.
The project will run in Python please indicate your experience level.
Should be interested and motivated to learn more about controls and developing ML skills.
Likely Majors: CS, Any
Controls (4-5 Students)
Specific Skills: Modern controls, fuzzy logic.
Open source Python framework experience or motivation to learn.
Should be strongly motivated to increase your controls skills. Completion of a controls course is a big plus.
Likely Majors: CE, EE, ROB, ME
Sponsor Mentors
Jean Rusczak
Jean is a lead engineer in model based design at Whirlpool. He is an Electrical engineer, with an MsC in electrical engineering, specialized in Control Systems, with 10+ years of industry experience. He has actively worked with Classical Control as well as with Advanced Controls and Sensing Techniques, such as Neural Networks, Machine Learning, and new sensors.
Matthias von Andrian
Matthias is a model based design engineer at Whirlpool. He is a chemical engineer with an MsC in chemical engineering, specialized in process modelling. He holds a PhD in chemical engineering from MIT, where his research focused on model predictive control for chemical processes under uncertainties. At Whirlpool, he has worked on models, as well as development of advanced control algorithms for refrigeration systems.
Executive Mentor
Fernando A. Ribas Junior
Fernando is a Senior Principal Engineer & Director in model based design at Whirlpool. He is a Mechanical engineer with 16+ yrs of industry experience, and an MsC in Thermal Sciences with intense work experience on modeling and simulation of the most diverse systems. More than 20 papers published in the area of modeling and simulation. Leading a global organization of 25+ people (US, Europe, India) in the area of Model Based Design. (Modeling & Simulation & Controls) Fernando will be supporting the team in the area of modeling and simulation.
Faculty Mentor
Peter Seiler
Associate Professor, Electrical Engineering and Computer Science
Peter works in the area of robust control theory, which focuses on the impact of model uncertainty on systems design. He is a co-author of the Robust Control Toolbox in Matlab. He is currently developing theoretical and numerical algorithms to assess the robustness of systems on finite time horizons. He is also investigating the use of robust control techniques to better understand optimization algorithms and model-free reinforcement learning methods.
He joined Michigan in 2020 from the University of Minnesota, where he had been working on advanced control techniques for wind turbines, fault-detection methods for safety-critical systems and robust control of disk drives.
Course Substitutions: Honors, ChE Elective, CS MDE/Capstone, CE MDE, EE MDE, IOE Senior Design, IOE Grad Cognate, ISD AUTO 503, ISD GAME, MECHENG 490, MECHENG 590, ROB 590, SI Elective, SI Grad Cognate
Citizenship Requirements: This project is open to all students on campus.
IP/NDA: Students will sign a non-disclosure agreement with Whirlpool
In Person/Remote Participation Options: Most project work will take place on campus in Ann Arbor, with opportunities to visit Whirlpool facilities in Benton Harbor, MI. (MDP will provide transportation.)
On Campus Requirements: Students who are approved to attend classes remotely for Winter (and Fall if necessary) 2022 may participate on this project.
Internship/Summer Opportunity: Students will be guaranteed an interview for a 2022 The interviews will take place in Q1 of 2022.