Isuzu generates and analyzes a significant amount of vehicle performance data that currently resides in unconnected systems. Students on this team will develop AWS platform designs and integrate these individual pieces into a single work process pipeline.
Abstract:
As a global manufacturer of commercial vehicles, Isuzu delivers a broad range of models from light-duty vehicles such as pickups to heavy-duty tractors with massive 16-liter engines. Designing these products requires a significant amount of testing which creates a lot of data. Logging, storing, and sharing this data creates numerous challenges. Students on this team will support the platform integration for an existing ISUZU Amazon Web Service (AWS) based truck test data logger, online data management and AWS based data analysis, as well as elastic computing capability and online optimization algorithms. The existing ISUZU in-house data logger enables fast data storage and cuts the lead and analysis time from technicians to engineers. Cloud based service enables a deep learning based data analysis pipeline with collected data; machine learning based simulation can also utilize validated data to improve model accuracy and use an elastic computing fleet to perform optimization. Students on this team will develop AWS platform designs and integrate these individual pieces into a single work process pipeline.
More Information
AWS Integration (2 students)
Specific Skills: Basic understanding of AWS integration platform, database design.
Likely Majors: CS, Any
General Programming (2 students)
Specific Skills: General programming skills with a minimum completion of EECS 281. Implementing multithreading applications and leveraging in house optimization libraries.
Likely Majors: CS, Any
Data Science / Modeling (2 students)
Specific Skills: Basic knowledge in virtual modeling and/or Monte Carlo testing. Must have general programming skills.
Likely Majors: Data Science, CS, Any
Sponsor Mentors
Yifan Wei
Model Based Development Engineer II
Yifan was a member of 2016 ISUZU MDP project team which worked on solving engine modeling challenges, which is a crucial part of ISUZU’s model based development approaches. After graduation, he joined the ISUZU Technical Center of American development team to continuously challenge the boundary of model based engineering solutions. His experience includes testing, powertrain model development, hardware-in-loop simulation, optimization algorithm development and cloud computing integration. ISUZU would like to let more UofM students leverage their strengths to solve real world problems and to challenge themselves through MDP.
Yong Sun
Supervisor, Model based development
Yong is a 2012 University of Michigan Master of Science in Aerospace Engineering graduate. He has worked at Isuzu for 3 years, focusing on autonomous driving, electrification, and model based approach development.
Faculty Mentor
Shai Revzen
Assistant Professor, Electrical and Computer Engineering
Shai’s research interests include the study of bio-inspired robotics and new methods and mechanisms for control. He has also been involved with the scientific study of animal and human locomotion based on nonlinear dynamical systems, and application to design of legged robotic vehicles and other devices.
Course Substitutions: Honors, ChE Elective, CS MDE/Capstone, CE MDE, Data Science Capstone, EE MDE
Internship/Summer Opportunity: Students will be guaranteed an interview for 2021 internships. The interviews will take place in March of 2021.
Citizenship Requirements: This project is open to all students.
IP/NDA: Students will sign standard University of Michigan IP/NDA documents