EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

1692. Manufacturing Process Optimisation and Predictive Analytics: Leveraging Data to Minimise Giveaway in Cheese Production

Invited abstract in session TD-31: Analytics for Combinatorial Problems from Health Care to the Food Industry, stream Analytics.

Tuesday, 14:30-16:00
Room: 046 (building: 208)

Authors (first author is the speaker)

1. Giwa Reagan Iziomo
Operations and Information Management, Aston University
2. Ozren Despic
Operations and Information Management, Aston University
3. Jiabin Luo
Operations and Information Management, Aston University
4. Viktor Pekar
Operations & Information Management, Aston University
5. Eliseo Vilalta-Perdomo
Operations and Information Management, Aston University
6. Tim Fisher
Dairy Technology, Butlers Farmhouse Cheeses

Abstract

This study addresses the challenge of high giveaway in Soft Cheese (British Brie) manufacturing, aiming to standardise weights and increase yields. Soft Cheese is produced by placing wet curds into moulds to form specific shapes and weights, which cannot be modified post-formation. Initial hypotheses suggested that weight variations were due to differences in properties between the outer and inner cheeses within a mould, caused by design issues. The project employed optimisation techniques and designed experiments to collect intricate data from the production process. This data aimed to capture variations in causes (production steps) and effects (weight inconsistencies), generating analytical datasets which were examined using descriptive visualisations, hypothesis testing, and predictive analytics, including machine learning. Causal inference methods were applied to quantify the impact of different factors on weight variations. Key recommendations included the introduction of a standardised mould filling system and improved mould trays to address intra-tray effects. For inter-tray effects, mainly linked to changing curd properties during production, a software-driven solution was implemented to automatically adjust for these changes. These measures reduced giveaways from 21% to 9%, resulting in substantial savings. This interdisciplinary initiative showcases the integration of optimisation techniques and predictive analytics to solve a critical issue in food manufacturing.

Keywords

Status: accepted

Back to the list of papers