Challenges Building a Data Value Chain to Enable Data-Driven Decisions: A Predictive Maintenance Case in 5G-Enabled Manufacturing
Paper i proceeding, 2018
Improvements in data storage and processing technologies have led many managers to change how they make decisions, relying less on intuition and more on data. This trend is especially notable for the manufacturing industry where Big Data applications, i.e. data analytics, are mentioned as an important enabler of value creation with the event of the fourth industrial revolution. Designing and building the entire data value chain that enables Big Data applications in manufacturing requires new knowledge about digital technologies combined with already established knowledge about the specific manufacturing processes. This paper focuses on the convergence of these different knowledge spaces applied to a specific case of implementing a Big Data application for predictive maintenance. Every step of building the data value chain from data acquisition to system feedback is presented and discussed in terms of the major challenges that were observed during the project. Results show that, just as the literature suggests, the knowledge gaps between different domains is a key component to manage for succeeding when building Big Data applications in the context of future manufacturing and maintenance.
Data-Driven Decision making
Cyber-Physical Production Systems