Towards Efficient Water Bottling Operations: A Continuous Improvement Analysis and Deep Learning-Driven Master Production Scheduler (#1809)
Read ArticleDate of Conference
July 17-19, 2024
Published In
"Sustainable Engineering for a Diverse, Equitable, and Inclusive Future at the Service of Education, Research, and Industry for a Society 5.0."
Location of Conference
Costa Rica
Authors
Tupayachi, José
Carbajal, Eduardo
Abstract
We present a comprehensive solution aimed at enhancing water bottling operations by addressing production planning inefficiencies and order non-compliance, the MPS integrates forecast modelling, inventory control, and production management to streamline operations. By mitigating rushed production and order shortages, the MPS implementation significantly reduced penalties (41.48%) and improved resource utilization, including an 80.22% decrease in overtime usage. Incorporating LSTM models for demand projection enhances accuracy by accommodating seasonality’s and non-linear trends effectively. Economic indicators validate the technical and economic viability of the proposed solutions, yielding an average monthly profit increase of 20.64K PEN. Integration with the company’s ERP system automates processes, while a modifiable forecast horizon and data-driven insights enable adaptive forecasting. Continuous improvement remains central, ensuring ongoing optimization of operational efficiency and predictive accuracy to meet evolving business needs.