Next Article in Journal
Cross-Validated Neural Network Optimization for Explainable Energy Prediction in Industrial Mobile Robots
Previous Article in Journal
A Risk-Driven Probabilistic Framework for Blast Vibrations in Twin Tunnels: Integrating Monte Carlo Simulation to Quantify Cavity Effects
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 15
Issue 23
10.3390/app152312626
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Dynamic Flexible Job Shop Scheduling via an Adaptive Genetic Algorithm and Deep Learning

by
Zheng Zhang
1,
Hanning Chen
1,
Zhixue Wang
1 and
Jiatong Han
2,*
1
School of Artificial Intelligence,Tiangong University, 399 Binshui West Road, Xiqing District, Tianjin 300387, China
2
Faculty of Applied Science and Engineering, University of Toronto, 27 King’s College Cir, Toronto, ON M5S 1A1, Canada
*
Author to whom correspondence should be addressed.
Appl. Sci. 2025, 15(23), 12626; https://doi.org/10.3390/app152312626 (registering DOI)
Submission received: 27 October 2025 / Revised: 26 November 2025 / Accepted: 27 November 2025 / Published: 28 November 2025
Versions Notes

Abstract

To address the scheduling problem of dynamic flexible job shop, this study proposes a hybrid scheduling method that integrates an adaptive genetic algorithm, dynamic target smoothing, and a deep Q-network (DQN). The scheduling process is formulated as a Markov decision process, where a graph convolutional network (GCN) extracts feature representations from evolving job and machine states. The adaptive genetic algorithm dynamically generates target values, while the dynamic target smoothing mechanism—based on sliding windows or exponential smoothing—further stabilizes target updates and enhances training efficiency. Experiments on the Brandimarte benchmark with stochastic job arrivals show that the proposed method reduces makespan by up to 2.1% compared to the QNGA baseline. In addition, the integration of adaptive evolution and smoothed target learning provides more stable training and stronger adaptability to dynamic environments than the existing DQN-based approaches.
Keywords: dynamic flexible job shop scheduling; adaptive genetic algorithm; deep Q-network; graph convolutional network; dynamic target smoothing dynamic flexible job shop scheduling; adaptive genetic algorithm; deep Q-network; graph convolutional network; dynamic target smoothing

Share and Cite

MDPI and ACS Style

Zhang, Z.; Chen, H.; Wang, Z.; Han, J. Dynamic Flexible Job Shop Scheduling via an Adaptive Genetic Algorithm and Deep Learning. Appl. Sci. 2025, 15, 12626. https://doi.org/10.3390/app152312626

AMA Style

Zhang Z, Chen H, Wang Z, Han J. Dynamic Flexible Job Shop Scheduling via an Adaptive Genetic Algorithm and Deep Learning. Applied Sciences. 2025; 15(23):12626. https://doi.org/10.3390/app152312626

Chicago/Turabian Style

Zhang, Zheng, Hanning Chen, Zhixue Wang, and Jiatong Han. 2025. "Dynamic Flexible Job Shop Scheduling via an Adaptive Genetic Algorithm and Deep Learning" Applied Sciences 15, no. 23: 12626. https://doi.org/10.3390/app152312626

APA Style

Zhang, Z., Chen, H., Wang, Z., & Han, J. (2025). Dynamic Flexible Job Shop Scheduling via an Adaptive Genetic Algorithm and Deep Learning. Applied Sciences, 15(23), 12626. https://doi.org/10.3390/app152312626

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop