Predictive Maintenance Information Systems: The Underlying Conditions and Technological Aspects

Predictive Maintenance Information Systems: The Underlying Conditions and Technological Aspects

Michael Möhring (Munich University of Applied Sciences, Lothstr, Germany), Rainer Schmidt (Munich University of Applied Sciences, Lothstr, Germany), Barbara Keller (Munich University of Applied Sciences, Lothstr, Germany), Kurt Sandkuhl (The University of Rostock, Rostock, Germany) and Alfred Zimmermann (Reutlingen University, Reutlingen, Germany)
Copyright: © 2020 |Pages: 16
DOI: 10.4018/IJEIS.2020040102


Predictive maintenance has the potential to improve the reliability of production and service provisioning. However, there is little knowledge about the proper implementation of predictive maintenance in research and practice. Therefore, we conducted a multi-case study and investigated underlying conditions and technological aspects for implementing a predictive maintenance system and where it leads to. We found that predictive maintenance initiatives are triggered by severe impacts of failures on revenue and profit. Furthermore, successful predictive maintenance initiatives require that pre-conditions are fulfilled: Data must be available and accessible. Very important is also the support by the management. We identified four factors important for the implementation of predictive maintenance. The integration of data is highly facilitated by Cloud-based mechanisms. The detection of events is enabled by advanced analytics. The execution of predictive maintenance operations is supported by data-driven process automation and visualization.
Article Preview

1. Introduction

The best running enterprises are running enterprises. The manufacturing of goods and the provisioning of services without interruptions is important to create revenue and increase (Stenström et al., 2016). Therefore, enterprises use maintenance to minimize or avoid downtime (Stenström et al., 2016).

The impact of maintenance strategies on firm performance has already been analyzed by Swanson (Swanson, 2001). Two basic strategies can be differentiated. Reactive and proactive strategies (Bateman, 1995; Stenström et al., 2016). Reactive or also run-to-failure approaches try to optimize the reaction to failures of plants according to Mobley (2002). This reactive (or corrective) maintenance is composed of post-hoc activities, executed after a warning or error occurred (Tsang et al., 2006; Nadj et al., 2016). A reactive approach to maintenance implies that an enterprise must keep personnel available and maintain a spare parts inventory for reacting to failures. Even if the parts inventory can be reduced by cooperating with equipment vendors that provide immediate delivery, the vendors demand premiums for quick reaction times. As many failures require deep skills for handling, a significant training effort is necessary. Furthermore, the staff available must be able to cope even with multiple concurrent failures. Additionally, the failures may happen at unfavourable times thus create high overtime labour cost. Mobley (2002) and Stenström et al. (2016) estimate that reactive maintenance operations are approximately three times more expensive than scheduled ones. Also, Swanson (2001) found that reactive strategies have a negative impact on firm performance. Even after a quick repair the manufacturing of products and the delivery of services are interrupted resulting in lost revenue and profit. Furthermore, contractual penalties may also become due because production and availability targets are not met.

On the other hand, Swanson (2001) and Stenström et al. (2016) showed that proactive strategies in maintenance have a significant positive impact on performance. They can be differentiated into preventive and predictive strategies (Bateman, 1995). Preventive approaches have a breadth first approach. They apply maintenance actions to all parts. On the contrary, predictive strategies follow a depth-first approach. They try to identify those parts most likely to fail and fix them before failure.

The first predictive maintenance management approaches were time-driven (Mobley, 2002). They use models such as bathtub curves and statistical trend data to determine the schedule maintenance tasks. Furthermore, the observations of employees were used to detect indicators of a future failure, e.g. vibrations of machinery (Mobley, 2002). The new potential created by digital technologies was already identified by different authors (Kusiak et al., 2009; Ding and Kamaruddin, 2015). Newer predictive maintenance approaches schedule maintenance activities on as-needed basis by obtaining and analysing the actual operating conditions (Kusiak et al., 2009). For this purpose, a new type of information system, so-called predictive maintenance systems were designed (Canito et al., 2017; Chiu et al., 2017; Fernandes et al., 2018). They use the actual operation condition of plant equipment to optimize total plant operation.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 17: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 16: 4 Issues (2020): 3 Released, 1 Forthcoming
Volume 15: 4 Issues (2019)
Volume 14: 4 Issues (2018)
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing