Pitfalls and protocols of data science in manufacturing practice
- PDF / 1,556,978 Bytes
- 19 Pages / 595.276 x 790.866 pts Page_size
- 32 Downloads / 197 Views
Pitfalls and protocols of data science in manufacturing practice Chia-Yen Lee1,2
· Chen-Fu Chien3
Received: 17 November 2019 / Accepted: 2 November 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Driven by ongoing migration for Industry 4.0, the increasing adoption of artificial intelligence, big data analytics, cloud computing, Internet of Things, and robotics have empowered smart manufacturing and digital transformation. However, increasing applications of machine learning and data science (DS) techniques present a range of procedural issues including those that involved in data, assumptions, methodologies, and applicable conditions. Each of these issues may increase difficulties for implementation in practice, especially associated with the manufacturing characteristics and domain knowledge. However, little research has been done to examine and resolve related issues systematically. Gaps of existing studies can be traced to the lack of a framework within which the pitfalls involved in implementation procedures can be identified and thus appropriate procedures for employing effective methodologies can be suggested. This study aims to develop a five-phase analytics framework that can facilitate the investigation of pitfalls for intelligent manufacturing and suggest protocols to empower practical applications of the DS methodologies from descriptive and predictive analytics to prescriptive and automating analytics in various contexts. Keywords Machine learning · Data science · Smart manufacturing · Big data · Prescriptive analytics · Automating analytics
Introduction “Prediction is a process; decision-making is the purpose”. According to the Fourth Industrial Revolution, often called Industry 4.0, machine learning technologies, data science (DS hereafter) analytics, Internet of Things (IOT), cloud computing, and robotics will take on increasingly important roles as automation transforms on global supply chains and smart factory (Lee et al. 2013, 2015). In fact, manufacturingprocess innovation is critical (Pisano and Wheelwright 1995) and DS provides potential solutions to drive the technology migration. DS techniques show the strengths, weaknesses and major functionalities to address difficulties and challenges in production systems (Choi et al. 2018; Khakifirooz et al. 2018). Most of the Industry 4.0 studies have devel-
B
Chia-Yen Lee [email protected]
1
Department of Information Management, National Taiwan University, Taipei City 10617, Taiwan
2
Institute of Manufacturing Information and Systems, National Cheng Kung University, Tainan City 701, Taiwan
3
Department of Industrial Engineering and Engineering Management, National Tsing Hua University, Hsinchu 30013, Taiwan
oped various DS techniques for prediction and automation; however, few studies have investigated the practical aspects of decision-making and resolve related issues systematically when applying DS to manufacturing systems. Gaps of existing studies can be traced to the lack of a framework within wh
Data Loading...
