Smart Prognostics and Health Management (SPHM) in Smart Manufacturing: An Interoperable Framework

Area of Science:

• Manufacturing Engineering
• Industrial Informatics
• Systems Engineering

Background:

• Modern manufacturing employs Industry 4.0, Cyber-Physical Systems, and Digital Twins, evolving from hierarchical to interconnected architectures.
• Shop floor devices generate vast data crucial for predictive maintenance and operational insights.
• Existing research on Prognostics and Health Management (PHM) often emphasizes tool wear and Condition-Based Monitoring (CBM), neglecting broader PHM applications.

Purpose of the Study:

• To conduct a comprehensive review of current Prognostics and Health Management (PHM) approaches and research trends.
• To propose a novel, three-phased, interoperable framework for implementing Smart Prognostics and Health Management (SPHM).
• To demonstrate the applicability of the SPHM framework through a use-case analysis.

Main Methods:

• Literature review of PHM techniques and Smart Manufacturing (SM) trends.
• Development of a three-phased SPHM framework: data acquisition, data preparation/analysis, and modeling/prediction/deployment.
• Application of the initial two phases of the SPHM framework to real-world milling machine operational data.

Main Results:

• The review highlights gaps in current PHM research, particularly concerning its multifaceted applications.
• A unique, adaptable SPHM framework is proposed, applicable across diverse manufacturing operations.
• The initial phases of the SPHM framework were successfully applied to milling machine data, validating its practical implementation.

Conclusions:

• The proposed SPHM framework offers a structured approach to leverage manufacturing data for enhanced predictive maintenance.
• The framework's interoperability and phased implementation facilitate its adoption in various industrial settings.
• Further research will focus on Phase 3 of the SPHM framework, encompassing advanced modeling and deployment strategies.