Intelligent Decision Support for Maintenance: A New Role for Audit Trails

Abstract

The changing nature of manufacturing, in recent years, is evident in industries willingness to adopt network connected intelligent machines in their factory development plans. While advances in sensors and sensor fusion techniques have been significant in recent years, the possibilities brought by Internet of Things create new challenges in the scale of data and its analysis. The development of audit trail style practice for the collection of data and the provision of comprehensive framework for its processing, analysis and use should be an important goal in addressing the new data analytics challenges for maintenance created by internet connected devices. This paper proposes that further research should be conducted into audit trail collection of maintenance data and the provision of a comprehensive framework for its processing analysis and use. The concept of 'Human in the loop' is also reinforced with the use of audit trails, allowing streamlined access to decision making and providing the ability to mine decisions.

Human in the Loop: Industry 4.0 Technologies and Scenarios for Worker Mediation of Automated Manufacturing

“…An audit trail can be thought of as a time stamped consecutive series of transaction recordings. As such, the audit trail can provide a construct for verification and assurance of provenance when considering temporal event based industrial data [35]. Swartout [36] propose a system that might be described as an "audit trail" of expert reasoning, where justification of programing code construct s of a given software are generated based on execution tra ces.…”

“…Swartout [36] propose a system that might be described as an "audit trail" of expert reasoning, where justification of programing code construct s of a given software are generated based on execution tra ces. Turner et al [35] illustrate a potential way to use audit t ra ils for the control of decision making within systems for predictive maintenance intervention. This work also promotes the ability to 'mine' information streams, captu red in the form of raw recorded data logs, in order to derive the major stage gates in the decision-making process.…”