MFI is catalyzing the future of manufacturing by combining three key areas: cyberinformation technologies (virtual modeling, big data analytics, augmented reality, Internet of Things, artificial intelligence, cybersecurity, and cloud computing), manufacturing technologies (design, materials, robotics, additive manufacturing, micro/nanofabrication) and the social sciences (learning science, policy, ethics).
In process monitoring of tissues during FRESH 3D bioprinting using optical coherence tomography
Monitoring 3D bioprinted parts can have improve the control and reproducibility of manufactured parts, which would expedite the translation of these technologies from R&D to industrial and clinical applications.
PI Kainerstorfer (BME, CIT), Co-PI Feinberg (BME & MSE, CIT)
Precise profiling and protection for IoT in manufacturing
Detecting and preventing attacks on Internet-of-Things (IoT) devices in manufacturing can be accomplished using device behavior profiling to create models that offer customized protection of devices.
PI Sekar (ECE, CIT), Co-PI Beuth (MechE, CIT), Wolf (CIT)
Launching the additive manufacturing of ceramics using machine learning
Additive manufacture of robust ceramic materials, which have many advanced energy applications, can be realized using externally applied electromagnetic fields and machine learning process optimization.
PI Singh (ML, SCS), Co-PIs Jayan (MechE, CIT), Beuth (MechE, CIT), Davis (EPP, CIT)
Robotic depowdering for additive manufacturing
Automating the conventionally manual task of de-powdering additive manufactured parts using robots equipped with sensors and cleaning actuators can improve worker safety as well as cost and time efficiency.
PI Shimada (MechE, CIT), Co-PI Kitani (RI, SCS)
Emerging manufacturing technologies and the demand for skills
The ability to more accurately predict the impacts of emerging technologies on labor markets can be achieved through a novel approach that combines engineering and economic cost models and can be used to accurately advise small to medium manufacturing enterprises on decisions to invest in technology.
PI Kovak (Heinz), Co-PIs Ales (Tepper), Fuchs (EPP, CIT), Whitefoot (MechE & EPP, CIT)
Profile-3D-printing for thermally tuned concrete panels
Real-time advanced robotic manufacturing can be used to produce concrete façade panels with designed surface geometries that improve building efficiency.
PI Bard (Architecture), Co-PIs Cupkova (Architecture), Bourne (RI, SCS), Washburn (RI, SCS and Chem, MCS)
Transforming additive manufacturing of polymers and multi-material composites using design-optimized print pathways and freeform reversible embedding 3D printing (FRE-3DP)
A novel approach to 3D printing using a support bath can greatly expand the types of polymers that can be printed, enable chemical reactions of the printed materials to gain novel material properties, and increase the mechanical strength and reduce the print time of mechanical parts through design optimization.
PI Feinberg (BME & MSE, CIT), Co-PIs Ozdoganlar (MechE, CIT), Kara (MechE, CIT), Bockstaller (MSE, CIT)
Training for mass production: A blueprint project in the food industry
In a smart classroom setting, sensors coupled with machine learned classifiers will analyze the quality of tasks performed by trainees to enable real-time data review by an instructor using augmented reality who can efficiently support and guide trainees.
PI McLaren (HCII, SCS), Co-PI Travers (RI, SCS)
HEALER: Computationally guided additive manufacturing of electrically-actuated self-healing robotic materials
Additive manufacturing of elastomeric soft robotic materials with electrically-actuating compartments can allow the material to be dismembered, reattached, and self-heal with complete functional recovery. Learn more about this project.Researchers
PI Islam (MSE, CIT), Co-PI Yao (HCII, SCS)
SimuLearn: Combining machine learning, mechanical and geometrical simulation for the inverse design and manufacture of self-assembling fiber-reinforced composites
Additive manufacturing can reduce the complexity of producing fiber-reinforced composites (FRC) while also enabling new properties, such as flat FRC sheets that can self-assemble into complex curved structures on demand.
PI Zhang (MechE, CIT), Co-PI Yao(HCII, SCS)
Data-driven fault detection and prediction in advanced manufacturing systems
A global view of the operations of a manufacturing plant can be realized using a reinforcement learning framework to combine information collected from different measurement mechanisms and enable the ability to efficiently diagnose system faults.
PI Joshi (ECE, CIT), Co-PIs Ozdoganlar (MechE, CIT) and Yagan (ECE, CIT)
Training in additive manufacturing using entertainment and tutoring technologies
Interactive systems that simulate the operation of additive manufacturing machines can be used to provide instructional support for learning how to use the machine and enable virtual training of large numbers of students and users.
PI Wolf (CIT), Co-PIs McLaren (HCII), Davidson (ETC)
Enabling a machine learning approach to develop a high entropy alloy coatings for additive manufacturing
High entropy alloy coatings can be developed to improve the mechanical properties of metals in extreme environments.
PI de Boer (MechE, CIT), Co-PI Webler (MSE, CIT)
Development of high-throughput photoreactors and computational tools for the discovery and manufacturing of solar fuels and functional materials
Fundamental limitations of modern chemistry and chemical discovery can be overcome using highly parallelized, computer guided procedures to describe and predict the construction and destruction of chemical bonds and the behavior of molecules.
PI Bernhard (Chem, MCS), Co-PIs Fragkiadaki (ML, SCS), Noonan (Chem, MCS), Poczos (ML, SCS), Yaron (Chem, MCS), Kowalewski (Chem, MCS)
Accelerating MAM commercialization and military readiness: Expert guided machine learning to identify candidate parts and subassemblies for additive manufacturing
Commercial implementation of metal additive manufacturing in parts and systems can be accelerated by combining 1) decision science and machine learning to improve candidate part selection and 2) tools developed to optimize part design, machine process parameters, part layout, and part consolidation.
PI Davis (EPP, CIT), Co-PIs Fuchs (EPP, CIT), Vaishnav (EPP, CIT), Kara (MechE, CIT), Whitefoot (MechE & EPP, CIT), Poczos (ML, SCS), Singh (ML, SCS)