An equipment behavioral study in fluidic production processes using data for an optimized predictive maintenance: Application to pneumatic valves in biopharmaceutical Industry
Predictive maintenance of production equipment is gaining increasing interest in the biopharmaceutical industry in the context of Industry 4.0, where reliability is essential to ensure product quality, equipment availability, and compliance with strict standards. Pneumatic membrane valves, critical...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Belgrade - Faculty of Mechanical Engineering, Belgrade
2025-01-01
|
| Series: | FME Transactions |
| Subjects: | |
| Online Access: | https://scindeks-clanci.ceon.rs/data/pdf/1451-2092/2025/1451-20922503345W.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Predictive maintenance of production equipment is gaining increasing interest in the biopharmaceutical industry in the context of Industry 4.0, where reliability is essential to ensure product quality, equipment availability, and compliance with strict standards. Pneumatic membrane valves, critical for regulating fluid and gas flows in production systems, are of particular importance. The membrane, a primary wear component, is subject to mechanical stresses that can lead to deformations or ruptures. These can disrupt production and compromise product quality. Prognostic Health Management (PHM) is a promising approach to monitoring equipment condition. By leveraging representative data, it offers the possibility of modelling the evolution of equipment condition and anticipating potential failures. This predictive strategy, based on lifecycle phases and trends, facilitates targeted maintenance interventions before major failures occur. This article investigates PHM integration for pneumatic valve membrane maintenance in the biopharmaceutical sector. It proposes a method to identify experimental data, define lifecycle criteria, analyse these criteria, compare them with planned maintenance practices, and evaluate signal drifts to characterise the membrane state for future predictive maintenance development. |
|---|---|
| ISSN: | 1451-2092 2406-128X |