A Data-Driven Methodology for Hierarchical Production Planning with LSTM-Q Network-Based Demand Forecast

Symmetry, Journal Year: 2025, Volume and Issue: 17(5), P. 655 - 655

Published: April 26, 2025

Mass customization makes it necessary to upgrade production planning systems improve the flexibility and resilience of in response volatile demand. The ongoing development digital twin technologies supports system. In this paper, we propose a data-driven methodology for Hierarchical Production Planning (HPP) that addresses requests management system fuel tank manufacturing workshop. proposed first introduces novel hybrid neural network framework with symmetry integrates Long Short-Term Memory Q-network (denoted as LSTM-Q network) real-time iterative demand forecast. symmetric balances forward backward flow information, ensuring continuous extraction historical order sequence information. Then, develop two relax-and-fix (R&F) algorithms solve mathematical model medium- long-term planning. Finally, use simulation dispatching rules realize dynamic adjustment short-term case study numerical experiments demonstrate effectively achieves systematic optimization

Language: Английский

A Cluster Chaotic Optimization for solving power loss and voltage profiles problems on electrical distribution networks

Knowledge-Based Systems, Journal Year: 2025, Volume and Issue: unknown, P. 113145 - 113145

Published: Feb. 1, 2025

Language: Английский