Modern manufacturing operates in complex environments where traditional management approaches are no longer enough. This highlights the need for real-time, dynamic and self-adaptive management strategies. Manufacturing data analytics (MDA) has emerged as a powerful solution for transforming traditional manufacturing into smart manufacturing. Through MDA, manufacturers can identify hidden patterns in external and internal data, allowing them to better anticipate and respond to geopolitical risks and rapidly changing customer expectations and demands. However, despite these benefits, adoption of MDA remains surprisingly low, with fewer than one in five projects reaching full implementation.
Why the low uptake?
Because manufacturers face numerous challenges during MDA implementation. The MDA process typically involves five main steps: data preparation, data analysis, evaluation and interpretation of results, and implementation of results into manufacturing systems. Unique issues can arise at each of these steps. Additionally, there are broader issues related to technological, organizational, and environmental (TOE) contexts. While past studies have investigated many of these issues, they have not been able to provide a comprehensive list, overlooking TOE contexts, and being limited to only specific steps of MDA.
To address this gap, a research team led by Assistant Professor Ki-Hun Kim from the Department of Industrial Engineering at Pusan National University, South Korea, developed a comprehensive issue set for MDA implementation (CISM), with active contributions from Mr. Sa-Eun Park and Mr. Sang-Jae Lee, also from the same department. “To accelerate the adoption of MDA, manufacturers must first be able to identify and resolve the various challenges that may arise during its implementation. This includes not only technical issues but also organizational and environmental factors that significantly influence the success of MDA initiatives,” explains Dr. Kim. “CISM provides a structured framework to proactively recognize and resolve these issues, supporting a more efficient and effective MDA implementation.” The team included Mr. Sa-Eun Park and Mr. Sang-Jae Lee, also from Pusan National University. Their study was made available online on June 09, 2025, and published in Volume 82 of the Journal of Manufacturing Systems in October 2025.
The team first started by identifying relevant literature from the SCOPUS database. They identified 35 papers that addressed various issues related to MDA implementation. By systematically reviewing these papers, they identified a comprehensive set of 29 issues, grouped into 9 categories, each mapped to the relevant TOE context and step of the MDA process. Of these, 26 issues are related to technological context, 11 to organizational context, and 4 to environmental context. The 9 categories of CISM reflect different aspects of the MDA process, from understanding the problem and preparing data, to identifying the knowledge gap between data scientists and domain experts, and aligning MDA models to real-world manufacturing systems.
To validate CISM, the research team applied it to three real-world case studies in the rubber manufacturing industry, focusing on optimizing recipe formulation and mixing processes to ensure consistent, high-quality production. The framework effectively captured all implementation challenges encountered during the projects, demonstrating its comprehensiveness and practical applicability.
The authors also highlight directions for future research: ranking the relative importance of each issue, exploring their relevance across different manufacturing contexts, and developing tailored strategies to address them.
“CISM can help manufacturers establish clear guidelines for identifying and prioritizing the issues that need to be proactively addressed to ensure effective MDA implementation,” notes Dr. Kim. “Moreover, it can serve as a foundational reference for developing education and training resources related to MDA. These efforts will, in turn, enable manufacturers to deliver high-quality products more efficiently and reliably, extending the benefits directly to consumers.”
In summary, CISM provides a solid foundation for both researchers and practitioners working to improve real-world MDA implementation. It represents a meaningful step forward in the journey toward widespread, data-driven smart manufacturing.
***
Reference
Title of original paper: Comprehensive issue identification for manufacturing data analytics implementation: Systematic literature review and case studies
Journal: Journal of Manufacturing Systems
DOI: 10.1016/j.jmsy.2025.05.006
About Pusan National University
Pusan National University, located in Busan, South Korea, was founded in 1946 and is now the No. 1 national university of South Korea in research and educational competency. The multi-campus university also has other smaller campuses in Yangsan, Miryang, and Ami. The university prides itself on the principles of truth, freedom, and service and has approximately 30,000 students, 1,200 professors, and 750 faculty members. The university comprises 14 colleges (schools) and one independent division, with 103 departments in all.
Website: https://www.pusan.ac.kr/eng/Main.do
About Assistant Professor Ki-Hun Kim
Dr. Ki-Hun Kim is an Assistant Professor in the Department of Industrial Engineering at Pusan National University and is jointly affiliated with the Graduate School of Data Science. His research focuses on the development and applications of AI for various industries such as manufacturing, logistics, and healthcare.
Lab: https://sites.google.com/view/iai-lab/home?authuser=0
Scopus ID: 57020115300
About Mr. Sa-Eun Park
Sa-Eun Park is currently a graduate student in the Department of Industrial Engineering at Pusan National University. He is pursuing an MS-Ph.D. integrated course under the supervision of Professor Ki-Hun Kim. His research involves developing advanced AI methods to optimize industrial processes and enhance decision-making capabilities.
About Mr. Sang-Jae Lee
Sang-Jae Lee earned a master’s degree in industrial engineering from Pusan National University. His research focuses on a time series forecasting and practical AI applications in various industries.
END