Award Abstract # 1931950
CPS: Small: Mitigating Uncertainties in Computer Numerical Control (CNC) as a Cloud Service using Data-Driven Transfer Learning

NSF Org: CMMI
Division of Civil, Mechanical, and Manufacturing Innovation
Recipient: REGENTS OF THE UNIVERSITY OF MICHIGAN
Initial Amendment Date: August 14, 2019
Latest Amendment Date: August 14, 2019
Award Number: 1931950
Award Instrument: Standard Grant
Program Manager: Bruce Kramer
CMMI
 Division of Civil, Mechanical, and Manufacturing Innovation
ENG
 Directorate for Engineering
Start Date: September 1, 2019
End Date: August 31, 2023 (Estimated)
Total Intended Award Amount: $500,000.00
Total Awarded Amount to Date: $500,000.00
Funds Obligated to Date: FY 2019 = $500,000.00
History of Investigator:
  • Chinedum Okwudire (Principal Investigator)
    okwudire@umich.edu
  • Raed Al Kontar (Co-Principal Investigator)
Recipient Sponsored Research Office: Regents of the University of Michigan - Ann Arbor
1109 GEDDES AVE STE 3300
ANN ARBOR
MI  US  48109-1015
(734)763-6438
Sponsor Congressional District: 06
Primary Place of Performance: University of Michigan Ann Arbor
Ann Arbor
MI  US  48109-1274
Primary Place of Performance
Congressional District:
06
Unique Entity Identifier (UEI): GNJ7BBP73WE9
Parent UEI:
NSF Program(s): CPS-Cyber-Physical Systems
Primary Program Source: 01001920DB NSF RESEARCH & RELATED ACTIVIT
Program Reference Code(s): 016Z, 082E, 152E, 7918, 7923, 9102, MANU
Program Element Code(s): 791800
Award Agency Code: 4900
Fund Agency Code: 4900
Assistance Listing Number(s): 47.041

ABSTRACT

Computer numerical control (CNC) is a critical feature of modern manufacturing machines. It provides automated control based on a set of programmed instructions, which traditionally run on a local computer that is physically tethered to the machine. This work envisions a future where manufacturing machines are controlled remotely over the Internet using CNC installed on cloud computers. Among several benefits over traditional CNC, cloud-based CNC holds promise to significantly improve the speed and accuracy of manufacturing machines at low cost. However, a major challenge with cloud-based CNC is that, somewhat like video streaming, it controls manufacturing machines primarily using pre-calculated commands that must be buffered to mitigate Internet transmission delays. For this reason, cloud-based CNC is susceptible to anomalies that result from delayed transmission of information on how the controlled machine is actually behaving. The award supports a scientific investigation into approaches for predicting impending anomalies from data gathered from past experience, and using the predictions to avoid incorrect control actions resulting from inadequate feedback. The U.S. stands to benefit economically from a transition from traditional to cloud-based CNC, since the U.S. is by far the market leader in cloud-based services. The project also will include outreach to U.S. companies, educational curriculum development to increase the U.S. talent pool in manufacturing and data analytics, and activities for middle schoolers in the Detroit area to inspire them to pursue careers in engineering.

The objective of the project is to mitigate uncertainties associated with real-time control of manufacturing machines from the cloud using data-driven transfer learning. The knowledge gained will boost the performance of manufacturing machines at low cost by providing the machines with reliable cloud-based CNC. In cloud-based CNC, advanced feedforward control functionalities are transitioned to the cloud while fast feedback loops are retained locally. However, with emphasis on feedforward control, uncertainties in modeling the dynamic behavior of machines could degrade the reliability and performance of cloud-based CNC by causing failures, due to inaccurate control actions. The system will predict failures using measured signals and mitigate them in a redundant, cloud-based CNC architecture by switching control authority from a cloud controller to a back-up local controller in the event of an impending failure. To this end, a data-driven transfer learning framework will predict and minimize uncertainties using data obtained from other machines connected to cloud-based CNC. Such transfer learning leverages data from one source to learn a different, but related, target source. The framework will allow cloud-based CNC to: (i) learn from a combination of condition monitoring signals and past failure data to predict impending failures, (ii) reduce uncertainties by leveraging condition monitoring data to calibrate physical models whose parameters are functions of their inputs, and (iii) plan feasible trajectories for switching from a cloud to a local controller when an impending failure is detected. The project will address the shortcomings of existing transfer learning methods by: (i) predicting failure events from a combination of condition monitoring and past failure data, and (ii) calibration of physics-based models with functional parameters from condition monitoring data. The methods will be evaluated experimentally on a CPS test bed consisting of a 3D printer controlled from the cloud using a cloud-based CNC prototype.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH

Note:  When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

Chou, Cheng-Hao and Duan, Molong and Okwudire, Chinedum E. "A linear hybrid model for enhanced servo error pre-compensation of feed drives with unmodeled nonlinear dynamics" CIRP annals , v.70 , 2021 https://doi.org/https://doi.org/10.1016/j.cirp.2021.04.070 Citation Details
Chou, Cheng-Hao and Duan, Molong and Okwudire, Chinedum E. "A Physics-Guided Data-Driven Feedforward Tracking Controller for Systems With Unmodeled DynamicsApplied to 3D Printing" IEEE Access , v.11 , 2023 https://doi.org/10.1109/ACCESS.2023.3244194 Citation Details
Chung, Seokhyun and Chou, Cheng-Hao and Fang, Xiaozhu and Al Kontar, Raed and Okwudire, Chinedum "A Multi-Stage Approach for Knowledge-Guided Predictions With Application to Additive Manufacturing" IEEE Transactions on Automation Science and Engineering , v.19 , 2022 https://doi.org/10.1109/TASE.2022.3160420 Citation Details
Chung, Seokhyun and Kontar, Raed "Functional Principal Component Analysis for Extrapolating Multistream Longitudinal Data" IEEE Transactions on Reliability , 2020 https://doi.org/10.1109/TR.2020.3035084 Citation Details
Kim, Heejin and Okwudire, Chinedum E. "Intelligent feedrate optimization using a physics-based and data-driven digital twin" CIRP Annals , v.72 , 2023 https://doi.org/10.1016/j.cirp.2023.04.063 Citation Details
Yue, Xubo and Kontar, Raed "Joint Models for Event Prediction From Time Series and Survival Data" Technometrics , 2020 https://doi.org/10.1080/00401706.2020.1832582 Citation Details

PROJECT OUTCOMES REPORT

Disclaimer

This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.

Computer numerical control (or CNC for short) is a critical feature in modern manufacturing machines. It provides automated control of manufacturing machines based on a set of programmed instructions which traditionally run on a local computer physically tethered to the machine it controls. The proposed work envisions a future where manufacturing machines are controlled remotely over the Internet using CNC installed on cloud computers. Among several benefits over traditional CNC, cloud-based CNC holds promise to significantly improve the performance (e.g., speed and accuracy) of manufacturing machines at low cost. However, a major challenge with cloud-based CNC is that, somewhat like video streaming, it controls manufacturing machines primarily using pre-calculated commands that can be buffered to mitigate Internet transmission delays. For this reason, cloud-based CNC is susceptible to anomalies which may result from inadequate feedback (i.e., not immediately knowing how the controlled machine is actually behaving). This award has supported a scientific investigation into approaches for predicting impending anomalies from data gathered from past experience, and using the predictions to avoid deleterious control actions that may result from inadequate feedback.

Intellectual Merit

The research objective was to mitigate uncertainties associated with real-time control of manufacturing machines from the cloud using data-driven transfer learning. This intellectual merit was achieved by carrying out three tasks, namely:

Task 1: Determination of Uncertainty Prediction Horizon using Reachability Analysis

Task 2: Predicting Event Probabilities via Joint Models

Task 3: Calibrating Physics-based Models having Functional Parameters

As part of Task 1, the team developed a strategy to determine when and how to switch from an advanced controller to a backup local controller. The proposed method was tested using an advanced algorithm that optimizes the speed of manufacturing machines using linear programming. Whenever the algorithm experienced uncertainty or infeasibility, it switched to a backup algorithm. The algorithm was demonstrated on a 3D printer where it achieved up to 25% improvement in motion speed without sacrificing motion accuracy.

As part of Task 2, the team developed a method to predict future failure events based on joint modeling of both longitudinal and time-to-event data. The methods achieved the state of art performance in joint models. In addition, the team developed a method for extrapolating multi-stream longitudinal data where multiple signals from different units are collected in real-time. It demonstrated a non-parametric approach to predict the evolution of multi-stream longitudinal data for an in-service unit through borrowing strength from other historical units.

As part of Task 3, the team developed a controller that calibrates a physics-based model using data gathered online during operation. The uncertainty from the physics based and data-driven models were incorporated into the controller. This resulted in an uncertainty-aware digital twin. The outcomes of using this uncertainty-aware digital twin were demonstrated experimentally on a 3D printer and machine tool; it led to cycle time reductions of up to 38% and 17% respectively, without sacrificing motion accuracy.

Broader Impacts

Some of the results of this project are being translated to industry through collaborations with two U.S. companies. The first is Ulendo Technologies, Inc., a start-up company that is leveraging the cloud infrastructure to provide calibration as a service to 3D printers. The second is CISCO, Inc., which is collaborating with the project team to translate the machine-learning related aspects of the findings to an infrastructure the company has developed for distributed computing.

Through the project, four PhD students have been trained, including a female student. Two of the students have graduated and have taken up positions as assistant professors at U.S. universities. Another graduate trained through this project has taken up a position as an engineer at a semiconductor manufacturing company. The fourth Ph.D. student is working towards his graduation.

The results of this project have been disseminated at manufacturing and controls conferences. They have also been published in very reputable journals in manufacturing, controls, mechatronics and statistics. A total of 10 journal papers have been published or submitted based on this project.


Last Modified: 12/20/2023
Modified by: Chinedum Okwudire

Please report errors in award information by writing to: awardsearch@nsf.gov.

Print this page

Back to Top of page