https://www.mdu.se/

In the realm of Industry 4.0, Industrial Internet of Things (IIoT) is pivotal for advancing Prognostics and Health Management (PHM) through real-time monitoring of asset conditions. The efficacy of these IIoT systems heavily relies on the precision and reliability of Acoustic Emission (AE) sensor data. Recognizing the critical dependence of IIoT system functionality on AE sensor capability, this study proposes a novel, systematic framework tailored for PHM applications. Our approach expands the application of the Gage Repeatability and Reproducibility (Gage R&R) technique, focusing on enhancing the reliability of IIoT-AE systems. In experimental study, AE sensors are deployed to collect data across various operational contexts, including different fault types, measurement positions, operators, speeds, and trial counts. This comprehensive exploration reveals how different contextual factors impact AE sensor capability, thereby facilitating the strategic selection of contexts for precise data acquisition. Additionally, we introduce an innovative three-region graph comprising key metrics, namely Percentage of Repeatability & Reproducibility (PRR), Precision-to-Tolerance Ratio (PTR), and Signal-to-Noise Ratio (SNR), to provide a clear and intuitive visualization of AE sensor capability and acceptability based on well-defined criteria. Our findings lay the groundwork for ensuring the accuracy and reliability in IIoT systems for PHM, while also provides invaluable guidance for contextual design and practical enhancement of AE sensor, with broader implications for real-time sensor capability evaluations in IoT systems. This work marks a significant step forward in ensuring the reliability of IIoT deployments in PHM, ultimately contributing to the advancement of sensor technology in Industry 4.0 applications.