A Data-Driven Approach to Production Time Estimation and Capacity Planning in Manufacturing Systems

Read full text Summarise with VIRAT
Authors: Johanes Ravialdi Tami, Yosua Natanael Tantio, Safarudin Gazali Herawan
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Manufacturing systems operating under make-to-order environments face significant challenges in balancing demand variability with limited production capacity, often resulting in delivery delays and reduced customer satisfaction. This study aims to analyze production capacity and develop an accurate production time estimation system to improve delivery performance. A quantitative case-study approach is employed, integrating forecasting methods, time study analysis, Rough Cut Capacity Planning, and regression modeling. Forecasting results indicate that the Moving Average method provides the most reliable demand estimates, with values ranging from 4,126 mL to 7,175 mL. Time study analysis reveals that manual and packing processes contribute significantly to total production time, which reaches 25.886 min/mL. Capacity analysis shows that available capacity (398,823.484 units) exceeds forecasted demand, indicating that delivery delays are not caused by capacity shortages. A regression-based estimation system (Y = 0.969X + 2.209) demonstrates high predictive accuracy with an R² of approximately 0.9756, confirming strong alignment between estimated and actual production times. The study highlights that improving production time estimation is critical to enhancing scheduling accuracy and delivery reliability. The integration of forecasting, time study, and capacity planning provides a robust framework for addressing planning inefficiencies and improving operational performance in manufacturing systems.

Fields of Study & Subjects

Management and Optimization Techniques Scheduling and Optimization Algorithms Operations Management Techniques

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
31 March 2026
Language
EN
Document type
Dataset