Digital Twins and Their Use in Maintenance Optimization, a Business Perspective

No Thumbnail Available
Journal Title
Journal ISSN
Volume Title
School of Business | Bachelor's thesis
Electronic archive copy is available locally at the Harald Herlin Learning Centre. The staff of Aalto University has access to the electronic bachelor's theses by logging into Aaltodoc with their personal Aalto user ID. Read more about the availability of the bachelor's theses.
Degree programme
Tieto- ja palvelujohtaminen
26 + 7
With recent technological trends, companies and researchers alike are looking into predictive maintenance strategies as an approach for decreasing maintenance costs, improving production uptime and system availability, and optimizing maintenance operations in their entirety. While the idea of predicting maintenance needs is not new, the new technologies are seen as a necessary tool for making it possible in practice. Digital Twin is a key trend in the current technological development of the manufacturing industry. Many use cases have been identified for DTs in industrial operations, including product design, lifecycle management, and maintenance. Of these, maintenance is the most intensively investigated among businesses and researchers. In this thesis, the use of Digital Twin in optimizing industrial maintenance operations, is reviewed according to the current literature. The aim is to analyze whether a predictive maintenance strategy implemented using Digital Twin, would be both feasible and beneficial for optimizing maintenance operations. This question is approached both from theoretical and business perspective, with an extensive review of current research. Special consideration is paid on existing case studies, with the objective of determining how extensively Digital Twin predictive maintenance implementations have been created and studied, and whether the results can be used to assess the feasibility of such systems. From the literature it is clear, that both predictive maintenance itself and predictive maintenance implemented with a Digital Twin provide significantly improved machine failure prediction, which has massive potential in optimizing maintenance strategies. Certain industrial fields and applications, in which a predictive maintenance solution using a Digital Twin could have even greater potential, can be identified. However, as almost all credible case studies focus on very small-scale applications with little focus on the actual costs and monetary benefits of implementing such solutions, it is difficult to determine how beneficial they would be in actual production environments. For this, there is currently a dire need for larger-scale implementations and case studies on actual production equipment.
Thesis advisor
Hekkala, Riitta
digital twin, predictive maintenance, service science, Industry 4.0
Other note