Predicting Alcohol Concentration during Beer Fermentation Using Ultrasonic Measurements and Machine Learning

Bowler, Alexander; Escrig, Josep; Pound, Michael; Watson, Nicholas

Abstract

Beer fermentation is typically monitored by periodic sampling and off-line analysis. In-line sensors would remove the need for time-consuming manual operation and provide real-time evaluation of the fermenting media. This work uses a low-cost ultrasonic sensor combined with machine learning to predict the alcohol concentration during beer fermentation. The highest ac-curacy model (R2=0.952, MAE=0.265, MSE=0.136) used a transmission-based ultrasonic sensing technique along with the measured temperature. However, the second most accurate model (R2=0.948, MAE=0.283, MSE=0.146) used a reflection-based technique without the temperature. Both the reflection-based technique and the omission of the temperature data are novel to this research and demonstrate the potential for a non-invasive sensor to monitor beer fermentation.

Citation

Bowler, A., Escrig, J., Pound, M., & Watson, N. (2021). Predicting Alcohol Concentration during Beer Fermentation Using Ultrasonic Measurements and Machine Learning. Fermentation, 7(1), Article 34. https://doi.org/10.3390/fermentation7010034

• Journal Article Type: Article
• Acceptance Date: Mar 2, 2021
• Online Publication Date: Mar 4, 2021
• Publication Date: Mar 1, 2021
• Deposit Date: Mar 3, 2021
• Publicly Available Date: Mar 3, 2021
• Journal: Fermentation
• Print ISSN: 2311-5637
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 7
• Issue: 1
• Article Number: 34
• DOI: https://doi.org/10.3390/fermentation7010034
• Public URL: https://nottingham-repository.worktribe.com/output/5335780
• Publisher URL: https://www.mdpi.com/2311-5637/7/1/34#