Metric Driven Framework for Evaluaiton of Logistics in PHM

Kurzfassung

In recent years, the aviation sector has been at the forefront of adopting Industry 4.0 technologies such as artificial intelligence, additive manufacturing, cyber-physical systems, big data analytics, and the Internet of Things (IoT). Within aircraft maintenance, these technologies have helped accelerate the development of Prescriptive Maintenance and Prognostics and Health Management (PHM) strategies. A key area where, which is expected to benefit significantly through these strategies is the spare part inventory management. The integration of these methods in inventory management not only reduces maintenance costs and aircraft downtime, but also provides improved service level improving customer relations. Despite the overwhelming benefits associated, the adoption of these methods in the industry remains scare due to lack of reliable health monitoring models as well as high computational costs associated with their development.

This study proposes a metric-driven framework, which emulates the behavior of prognostic models using only their performance metrics like model accuracy and the prognostic horizon, thereby eliminating the need for a dedicated health assessment model. By comparing key performance indicators, such as total cost and service level, against traditional reliability-based inventory decision policies, the framework evaluates the effect of prognostic integration under different demand patterns. Beyond this, the study also offers insight into how accurate a PHM model must be to deliver tangible operational benefits. Ultimately, the framework provides a light weight surrogate for studying and optimizing maintenance logistics and assessing the applicability of PHM strategies in real-world scenarios.”