Advanced Planning and Scheduling Framework for Manufacturing Operation with Demand Forecasting

View at publisher Summarise with VIRAT
Authors: Dohun Kim, Jinho Park, W. Kim
Cited by: 0
References: 9

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

Advanced Planning and Scheduling (APS) has been adopted as a systematic decision-support tool to address global supply chain instability and increasing demand volatility. This study introduces an AI-based APS framework that integrates demand-order forecasting models and constraint-based scheduling algorithms to enhance responsiveness, efficiency, and flexibility in manufacturing operations. The system integrates forecasting, planning, scheduling, and execution feedback based on data linkage with external systems such as ERP, PLM, and MES. By applying deep learning models such as LSTM and PatchTST, the system improved demand forecasting accuracy, while the CP-based scheduler optimized production plans under resource and delivery constraints. The results demonstrate that forecast-driven scheduling enhances responsiveness and reliability in manufacturing operation.

Fields of Study & Subjects

Scheduling and Optimization Algorithms Impact of AI and Big Data on Business and Society Management and Optimization Techniques

Publication details

Journal / source
International Conference on Consumer Electronics
Pages
1–4
Publication date
3 February 2026
Language
EN