Unlocking the Potential of Remanufacturing Through Machine Learning and Data-Driven Models—A Survey

As a key strategy for achieving a circular economy, remanufacturing involves bringing end-of-use (EoU) products or cores back to a ‘like new’ condition, providing more affordable and sustainable alternatives to new products. Despite the potential for substantial resources and energy savings, the ind...

Full description

Saved in:
Bibliographic Details
Main Authors: Yong Han Kim, Wei Ye, Ritbik Kumar, Finn Bail, Julia Dvorak, Yanchao Tan, Marvin Carl May, Qing Chang, Ragu Athinarayanan, Gisela Lanza, John W. Sutherland, Xingyu Li, Chandra Nath
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/17/12/562
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850050427877326848
author Yong Han Kim
Wei Ye
Ritbik Kumar
Finn Bail
Julia Dvorak
Yanchao Tan
Marvin Carl May
Qing Chang
Ragu Athinarayanan
Gisela Lanza
John W. Sutherland
Xingyu Li
Chandra Nath
author_facet Yong Han Kim
Wei Ye
Ritbik Kumar
Finn Bail
Julia Dvorak
Yanchao Tan
Marvin Carl May
Qing Chang
Ragu Athinarayanan
Gisela Lanza
John W. Sutherland
Xingyu Li
Chandra Nath
author_sort Yong Han Kim
collection DOAJ
description As a key strategy for achieving a circular economy, remanufacturing involves bringing end-of-use (EoU) products or cores back to a ‘like new’ condition, providing more affordable and sustainable alternatives to new products. Despite the potential for substantial resources and energy savings, the industry faces operational challenges. These challenges arise from uncertainties surrounding core quality and functionality, return times, process variation required to meet product specifications, and the end-of-use (EoU) product values, as well as their new life expectancy after extended use as a ‘market product’. While remanufacturing holds immense promise, its full potential can only be realized through concerted efforts towards resolving the inherent complexities and obstacles that impede its operations. Machine learning (ML) and data-driven models emerge as transformative tools to mitigate numerous challenges encountered by manufacturing industry. Recently, the integration of cutting-edge technologies, such as sensor-based product data acquisition and storage, data analytics, machine health management, artificial intelligence (AI)-driven scheduling, and human–robot collaboration (HRC), in remanufacturing procedures has received significant attention from remanufacturers and the circular economy community. These advanced computational technologies help remanufacturers to implement flexible operation scheduling, enhance quality control, and streamline workflows for EoU products. This study embarks on a comprehensive review and in-depth analysis of state-of-the-art algorithms across various facets of remanufacturing processes and operations. Additionally, it identifies key challenges to advancing remanufacturing practices through data-driven and ML methods and uncovers research opportunities in synergy with smart manufacturing techniques. The study aims to offer guidelines for stakeholders and to reinforce the industry’s pivotal role in circular economy initiatives.
format Article
id doaj-art-ea90f45e1b8b4ec0bd4d0926b460a20c
institution DOAJ
issn 1999-4893
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-ea90f45e1b8b4ec0bd4d0926b460a20c2025-08-20T02:53:27ZengMDPI AGAlgorithms1999-48932024-12-01171256210.3390/a17120562Unlocking the Potential of Remanufacturing Through Machine Learning and Data-Driven Models—A SurveyYong Han Kim0Wei Ye1Ritbik Kumar2Finn Bail3Julia Dvorak4Yanchao Tan5Marvin Carl May6Qing Chang7Ragu Athinarayanan8Gisela Lanza9John W. Sutherland10Xingyu Li11Chandra Nath12Environmental and Ecological Engineering, Purdue University, 500 Central Dr, West Lafayette, IN 47907, USASchool of Engineering Technology, Purdue University, 401 N. Grant St., West Lafayette, IN 47907, USAEnvironmental and Ecological Engineering, Purdue University, 500 Central Dr, West Lafayette, IN 47907, USAwbk Institute of Production Science, Karlsruhe Institute of Technology (KIT), Kaiserstrasse 12, 76131 Karlsruhe, Germanywbk Institute of Production Science, Karlsruhe Institute of Technology (KIT), Kaiserstrasse 12, 76131 Karlsruhe, GermanySchool of Engineering Technology, Purdue University, 401 N. Grant St., West Lafayette, IN 47907, USAwbk Institute of Production Science, Karlsruhe Institute of Technology (KIT), Kaiserstrasse 12, 76131 Karlsruhe, GermanyDepartment of Mechanical and Aerospace Engineering, University of Virginia, Charlottesville, VA 22903, USASchool of Engineering Technology, Purdue University, 401 N. Grant St., West Lafayette, IN 47907, USAwbk Institute of Production Science, Karlsruhe Institute of Technology (KIT), Kaiserstrasse 12, 76131 Karlsruhe, GermanyEnvironmental and Ecological Engineering, Purdue University, 500 Central Dr, West Lafayette, IN 47907, USASchool of Engineering Technology, Purdue University, 401 N. Grant St., West Lafayette, IN 47907, USAEnvironmental and Ecological Engineering, Purdue University, 500 Central Dr, West Lafayette, IN 47907, USAAs a key strategy for achieving a circular economy, remanufacturing involves bringing end-of-use (EoU) products or cores back to a ‘like new’ condition, providing more affordable and sustainable alternatives to new products. Despite the potential for substantial resources and energy savings, the industry faces operational challenges. These challenges arise from uncertainties surrounding core quality and functionality, return times, process variation required to meet product specifications, and the end-of-use (EoU) product values, as well as their new life expectancy after extended use as a ‘market product’. While remanufacturing holds immense promise, its full potential can only be realized through concerted efforts towards resolving the inherent complexities and obstacles that impede its operations. Machine learning (ML) and data-driven models emerge as transformative tools to mitigate numerous challenges encountered by manufacturing industry. Recently, the integration of cutting-edge technologies, such as sensor-based product data acquisition and storage, data analytics, machine health management, artificial intelligence (AI)-driven scheduling, and human–robot collaboration (HRC), in remanufacturing procedures has received significant attention from remanufacturers and the circular economy community. These advanced computational technologies help remanufacturers to implement flexible operation scheduling, enhance quality control, and streamline workflows for EoU products. This study embarks on a comprehensive review and in-depth analysis of state-of-the-art algorithms across various facets of remanufacturing processes and operations. Additionally, it identifies key challenges to advancing remanufacturing practices through data-driven and ML methods and uncovers research opportunities in synergy with smart manufacturing techniques. The study aims to offer guidelines for stakeholders and to reinforce the industry’s pivotal role in circular economy initiatives.https://www.mdpi.com/1999-4893/17/12/562remanufacturingcircular economymachine learningdata-driven modelssustainability
spellingShingle Yong Han Kim
Wei Ye
Ritbik Kumar
Finn Bail
Julia Dvorak
Yanchao Tan
Marvin Carl May
Qing Chang
Ragu Athinarayanan
Gisela Lanza
John W. Sutherland
Xingyu Li
Chandra Nath
Unlocking the Potential of Remanufacturing Through Machine Learning and Data-Driven Models—A Survey
Algorithms
remanufacturing
circular economy
machine learning
data-driven models
sustainability
title Unlocking the Potential of Remanufacturing Through Machine Learning and Data-Driven Models—A Survey
title_full Unlocking the Potential of Remanufacturing Through Machine Learning and Data-Driven Models—A Survey
title_fullStr Unlocking the Potential of Remanufacturing Through Machine Learning and Data-Driven Models—A Survey
title_full_unstemmed Unlocking the Potential of Remanufacturing Through Machine Learning and Data-Driven Models—A Survey
title_short Unlocking the Potential of Remanufacturing Through Machine Learning and Data-Driven Models—A Survey
title_sort unlocking the potential of remanufacturing through machine learning and data driven models a survey
topic remanufacturing
circular economy
machine learning
data-driven models
sustainability
url https://www.mdpi.com/1999-4893/17/12/562
work_keys_str_mv AT yonghankim unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey
AT weiye unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey
AT ritbikkumar unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey
AT finnbail unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey
AT juliadvorak unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey
AT yanchaotan unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey
AT marvincarlmay unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey
AT qingchang unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey
AT raguathinarayanan unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey
AT giselalanza unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey
AT johnwsutherland unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey
AT xingyuli unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey
AT chandranath unlockingthepotentialofremanufacturingthroughmachinelearninganddatadrivenmodelsasurvey