Predictive maintenance for life science industry
Rane, Deepika (2024)
2024
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2024051010701
https://urn.fi/URN:NBN:fi:amk-2024051010701
Tiivistelmä
This thesis addresses the application of predictive maintenance techniques in the context of continuous monitoring systems within the Life Science industry. The business challenge revolves around optimizing system reliability and minimizing unplanned downtime. The scope encompasses a comprehensive analysis of current state monitoring systems, followed by the exploration of predictive maintenance methodologies, with a focus on machine learning approaches.
The research delves into various predictive maintenance techniques, particularly those leveraging machine learning algorithms, to predict system conditions.
Implementation details cover the entire lifecycle of predictive maintenance, including problem framing, data preprocessing, feature engineering, model implementation, and evaluation.
The conclusion summarizes the key findings and highlights the results of the implementation, emphasizing the potential impact on equipment reliability and maintenance efficiency. Future work is outlined to explore advanced machine learning techniques, improve model performance, and integrate predictive maintenance into broader asset management strategies within the Life Science industry.
The research delves into various predictive maintenance techniques, particularly those leveraging machine learning algorithms, to predict system conditions.
Implementation details cover the entire lifecycle of predictive maintenance, including problem framing, data preprocessing, feature engineering, model implementation, and evaluation.
The conclusion summarizes the key findings and highlights the results of the implementation, emphasizing the potential impact on equipment reliability and maintenance efficiency. Future work is outlined to explore advanced machine learning techniques, improve model performance, and integrate predictive maintenance into broader asset management strategies within the Life Science industry.