Transfer Learning-Based Framework for Joint Scheduling and Control Across Manufacturing Domains Toward Industry 5.0

Panagiotis D. Parashos; Dimitrios E. Koulouriotis

doi:10.1016/j.eng.2026.08.030

Engineering ›› :202608030 DOI: 10.1016/j.eng.2026.08.030

research-article

Transfer Learning-Based Framework for Joint Scheduling and Control Across Manufacturing Domains Toward Industry 5.0

Author information +

History +

PDF (2797KB)

Abstract

Industry 5.0 is a novel manufacturing paradigm that aims to create human-centric, sustainable, and resilient manufacturing systems by fostering deep collaboration between humans and sophisticated technologies. Stochastic manufacturing environments require adaptable scheduling and control policies for fluctuating conditions such as demand, variable processing times, and frequent equipment failures. Although conventional dispatching rules and control policies are readily implemented, they often yield high scrap rates and excessive maintenance operations. Consequently, reinforcement learning (RL) has emerged as a data-driven alternative for addressing these issues. Despite its effectiveness, the practical implementation of RL presents several challenges including learning process initialization. This study addresses these limitations by proposing a transfer learning (TL)-based framework for joint scheduling and control in dynamic multi-line manufacturing environments. The objective is to improve production output and energy efficiency through intelligent manufacturing and predictive maintenance, thereby supporting long-term sustainability, human-centric operations, and operational resilience toward Industry 5.0. The proposed framework transfers knowledge from a conventional multi-line manufacturing environment to an additive manufacturing (AM) environment by implementing a long short-term memory network to facilitate the transfer of joint control policies across heterogeneous manufacturing domains. The generalizability and domain adaptation of the framework are evaluated by applying it to an AM environment to jointly control operations, including the printing process and output quality. The results reveal that the domain-adapted network achieves perfect diagonal scores with off-diagonal scores equivalent to zero, indicating that substantially distinct policies are developed for each domain without cross-domain confusion. These findings demonstrate that TL can significantly improve efficiency and reliability in a manufacturing setting, thereby providing a viable approach for practical deployment.

Keywords

Cyber-physical manufacturing / Additive manufacturing / Reinforcement learning / Attention-enhanced LSTM / Human-centric manufacturing / Dynamic decision-making

Cite this article

Download citation ▾

Panagiotis D. Parashos, Dimitrios E. Koulouriotis. Transfer Learning-Based Framework for Joint Scheduling and Control Across Manufacturing Domains Toward Industry 5.0. Engineering 202608030 DOI:10.1016/j.eng.2026.08.030

登录浏览全文

4963

注册一个新账户忘记密码

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	Leng J, Xu C, Song X, Liu Q, Chen X, Shen W, et al. High-performance manufacturing systems: concepts, performance metrics, enablers, challenges, and research directions. Adv Eng Inform 2025; 68: 103617.

[2]	Zhang C, Wang Z, Zhou G, Chang F, Ma D, Jing Y, et al. Towards new-generation human-centric smart manufacturing in Industry 5.0: a systematic review. Adv Eng Inform 2023; 57: 102121.

[3]	Leng J, Sha W, Wang B, Zheng P, Zhuang C, Liu Q, et al. Industry 5.0: prospect and retrospect. J Manuf Syst 2022; 65: 279-95.

[4]	Meftah S, Sahnoun M, Messaadia M, Benslimane SM . Enhancing decision-making in Industry 5.0 through adaptive human-machine interfaces: a systematic literature review. Comput Stand Interfaces 2026; 96: 104091.

[5]	Rame R, Purwanto P, Sudarno S . Industry 5.0 and sustainability: an overview of emerging trends and challenges for a green future. Innov Green Dev 2024; 3(4): 100173.

[6]	Hammedi S, Namoun A, Shili M . Reinforcement learning for real-time scheduling in dynamic reconfigurable manufacturing systems. Int J Adv Comput Sci Appl 2025; 16(6) 39.

[7]	Waubert de Puiseau C, Meyes R, Meisen T . On reliability of reinforcement learning based production scheduling systems: a comparative survey. J Intell Manuf 2022; 33(4): 911-27.

[8]	Kayhan BM, Yildiz G . Reinforcement learning applications to machine scheduling problems: a comprehensive literature review. J Intell Manuf 2023; 34(3): 905-29.

[9]	Paraschos PD, Koulouriotis DE . Learning-based production, maintenance, and quality optimization in smart manufacturing systems: a literature review and trends. Comput Ind Eng 2024; 198: 110656.

[10]	Shah M, Zhou Y, Wu J, Mowbray M . Deep reinforcement learning for scheduling of a steel plant in the electricity spot market. Engineering 2026 In Press.

[11]	Paraschos PD, Koulinas GK, Koulouriotis DE . Model-driven deep learning for joint control and decision-making in failure-prone circular multistage manufacturing systems. Int J Comput Integr Manuf 2026; 39: 384-404.

[12]	Zhang F, Li J, Li YC, Zhang Z, Yu Y, Ye D . Improving sample efficiency of reinforcement learning with background knowledge from large language models. IEEE Trans Neural Netw Learn Syst 2025; 36(11): 19681-92.

[13]	Samsonov V, Ben Hicham K, Meisen T . Reinforcement learning in manufacturing control: baselines, challenges and ways forward. Eng Appl Artif Intell 2022; 112: 104868.

[14]	Stöckermann P, Feudel S, Immordino A, Hayen N, Altenmüller T, Gebser M, et al. Reinforcement learning based dispatching solutions in semiconductor manufacturing: a literature review on validation and deployment. Prod Manuf Res 2025; 13(1): 2582472.

[15]	Alginahi YM, Sabri O, Said W . Reinforcement learning for industrial automation: a comprehensive review of adaptive control and decision-making in smart factories. Machines 2025; 13(12): 1140.

[16]	Inayathullah S, Buddala R . Review of machine learning applications in additive manufacturing. Results Eng 2025; 25: 103676.

[17]	Khan UA, Khan NM, Zafar MH . Resource efficient PV power forecasting: transductive transfer learning based hybrid deep learning model for smart grid in Industry 5.0. Energy Convers Manag X 2023; 20: 100486.

[18]	Rožanec JM, Novalija I, Zajec P, Kenda K, Tavakoli Ghinani H, Suh S, et al. Human-centric artificial intelligence architecture for Industry 5.0 applications. Int J Prod Res 2023; 61(20): 6847-72.

[19]	Ali I, Nguyen K, Oh I . Systematic literature review on Industry 5.0: current status and future research directions with insights for the Asia Pacific countries. Asia Pac Bus Rev 2025; In Press.

[20]	Sarkar I, Kakarla HHH, Hazra A, Gupta K, Kumari P, Munusamy A. Machine learning for Industry 5.0: a survey. IEEE Internet Things J 2025; 12: 44444-67.

[21]	Wang C, Tan XP, Tor SB, Lim CS . Machine learning in additive manufacturing: state-of-the-art and perspectives. Addit Manuf 2020; 36: 101538.

[22]	Equbal MA, Equbal A, Khan ZA, Badruddin IA . Machine learning in additive manufacturing: a comprehensive insight. Int J Light Mater Manuf 2025; 8(2): 264-84.

[23]	Zhao Z, Alzubaidi L, Zhang J, Duan Y, Gu Y. A comparison review of transfer learning and self-supervised learning: definitions, applications, advantages and limitations. Expert Syst Appl 2024; 242: 122807.

[24]	Zhu Z, Lin K, Jain AK, Zhou J . Transfer learning in deep reinforcement learning: a survey. IEEE Trans Pattern Anal Mach Intell 2023; 45(11): 13344-62.

[25]	Huang JD, Peng C, Liu J, Zheng G . Reinforcement learning-based optimization for freeze-dried fruit production scheduling under time-of-use electricity tariffs. Eng Appl Artif Intell 2025; 160: 111824.

[26]	Yan X, Wang Z, Zhao C, Melkote SN, Rosen DW . Machine learning-based cyber manufacturing services: a review of manufacturing process selection, process planning, and design for manufacturing. Engineering 2026; 63: 47-67.

[27]	Meng Q, Bogle IDL, Charitopoulos VM . Hedging against material uncertainty via chance-constrained recurrent neural networks: a continuous pharmaceutical manufacturing case study. Engineering 2025; 52: 129-41.

[28]	Zou H, Wang K, Hou Z, Li Y, Guo J, Gao L. A reinforcement learning-improved genetic algorithm for order reorganization-driven energy-efficient flexible job-shop hybrid batch scheduling towards mass personalized manufacturing. Comput Oper Res 2026; 185: 107304.

[29]	Sun X, Shen W, Fan J, Vogel-Heuser B, Bi F, Zhang C . Deep reinforcement learning-based multi-objective scheduling for distributed heterogeneous hybrid flow shops with blocking constraints. Engineering 2025; 46: 278-91.

[30]	Zhang J, Lü Z, Ding J, Su Z, Li X, Gao L . An effective local search algorithm for flexible job shop scheduling in intelligent manufacturing systems. Engineering 2025; 50: 117-27.

[31]	Liu C, Chen K, Wang H, Yang B, Leng J . Job shop scheduling by deep dual-Q network with prioritized experience replay for resilient production control in flexible manufacturing system. Comput Oper Res 2025; 183: 107190.

[32]	Paraschos PD, Papadopoulos G, Koulouriotis DE . Multi-objective evolution and swarm-integrated optimization of manufacturing processes in simulation-based environments. Machines 2025; 13(7): 611.

[33]	Chen K, Zhang P, Yan H, Chen G, Sun T, Lu Q, et al. A review of machine learning in additive manufacturing: design and process. Int J Adv Manuf Technol 2024; 135: 1051-87.

[34]	Chung J, Shen B, Law ACC, Kong Z . Reinforcement learning-based defect mitigation for quality assurance of additive manufacturing. J Manuf Syst 2022; 65: 822-35.

[35]	Dharmadhikari S, Menon N, Basak A . A reinforcement learning approach for process parameter optimization in additive manufacturing. Addit Manuf 2023; 71: 103556.

[36]	Sun M, Ding J, Zhao Z, Chen J, Huang GQ, Wang L . Out-of-order execution enabled deep reinforcement learning for dynamic additive manufacturing scheduling. Robot Comput-Integr Manuf 2025; 91: 102841.

[37]	Yuk JC, Park SH . Reinforcement learning-driven optimization of additively manufactured lattices for enhancement of mechanical stiffness and lightweight property. Engineering 2026; 63: 110-22.

[38]	Dulac-Arnold G, Levine N, Mankowitz DJ, Li J, Paduraru C, Gowal S, et al. Challenges of real-world reinforcement learning: definitions, benchmarks and analysis. Mach Learn 2021; 110(9): 2419-68.

[39]	Bahador A, Du C, Ng HP, Dzulqarnain NA, Ho CL . Cost-effective classification of tool wear with transfer learning based on tool vibration for hard turning processes. Measurement 2022; 201: 111701.

[40]	Azari MS, Flammini F, Santini S, Caporuscio M . A systematic literature review on transfer learning for predictive maintenance in Industry 4.0. IEEE Access 2023; 11: 12887-910.

[41]	Wang P, Qi J, Xu X, Yang S . Machining quality prediction of multi-feature parts using integrated multi-source domain dynamic adaptive transfer learning. Robot Comput-Integr Manuf 2024; 90: 102815.

[42]	Li W, Huang R, Li J, Liao Y, Chen Z, He G, et al. A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: theories, applications and challenges. Mech Syst Signal Process 2022; 167: 108487.

[43]	Fan L, Rao S, Wang J . Multilayer perceptron-based lightweight model for unsupervised cross domain fault diagnosis. Chem Eng Sci 2026; 320: 122426.

[44]	Zhou J, Yue C, Xia W, Liu X, Zhou Y, Li Z, et al. Tool condition monitoring and remaining useful life prediction based on multi-modal fusion and transfer learning under variable working conditions. J Manuf Syst 2025; 82: 730-47.

[45]	Woo JM, Ju SH, Sung JH, Seo KM . Meta-learning-based LSTM-autoencoder for low-data anomaly detection in retrofitted CNC machine using multi-machine datasets. 2025; 13: 534.

[46]	Liang Y, Wang Y, Li W, Pham DT, Lu J. Adaptive fault diagnosis of machining processes enabled by hybrid deep learning and incremental transfer learning. Comput Ind 2025; 167: 104262.

[47]	Caliskan A, O’Brien C, Panduru K, Walsh J, Riordan D . An efficient Siamese network and transfer learning-based predictive maintenance system for more sustainable manufacturing. Sustainability 2023; 15(12): 9272.

[48]	Qi X, Chen G, Li Y, Cheng X, Li C . Applying neural-network-based machine learning to additive manufacturing: current applications, challenges, and future perspectives. Engineering 2019; 5(4): 721-9.

[49]	Pandiyan V, Drissi-Daoudi R, Shevchik S, Masinelli G, Le-Quang T, Logé R, et al. Deep transfer learning of additive manufacturing mechanisms across materials in metal-based laser powder bed fusion process. J Mater Process Technol 2022; 303: 117531.

[50]	Zhang J, Yu K, Yao Y, Lu L, Gao Q, Zhang P, et al. A transformer-based framework for cross-material in situ monitoring in extrusion-based bioprinting. Adv Eng Inform 2026; 71: 104323.

[51]	Zhang H, Zhao Z, Wang C, Zhang X, Chen X. Mitigating domain shift in online process monitoring for material extrusion additive manufacturing via transfer learning. Addit Manuf 2024; 94: 104467.

[52]	Tang Y, Rahmani Dehaghani M, Sajadi P, Wang GG . Selecting subsets of source data for transfer learning with applications in metal additive manufacturing. J Intell Manuf 2025; 36(5): 3185-206.

[53]	Pashmforoush F, Seyedzavvar M . A transfer learning-based machine learning approach to predict mechanical properties of different material types fabricated by selective laser melting process. Proc Inst Mech Eng Pt E J Process Mech Eng 2025; 239(3): 1400-14.

[54]	Deng C, Tang J, Lu S, Ma Y, Lin L, Miao J . Improved milling stability analysis for chatter-free machining parameters planning using a multi-fidelity surrogate model and transfer learning with limited experimental data. Int J Prod Res 2024; 62(4): 1126-43.

[55]	Skiadopoulos M, Kifer D, Shokouhi P . A transfer learning approach to the prediction of porosity in additively manufactured metallic components. NDT Int 2026; 157: 103531.

[56]	Li H, Gao F, Jiao J, Liu Z, Ji D, Lin J . Acoustic emission-based cross-domain process health monitoring for additive manufacturing. IEEE Trans Instrum Meas 2023; 72: 1-8.

[57]	Xie J, Yang Z, Hu CC, Yang HC, Lu Y, Zhao YF . Investigation on domain adaptation of additive manufacturing monitoring systems to enhance digital twin reusability. IEEE Int Conf Autom Sci Eng 2024: 690-7.

[58]	Qin J, Hu F, Liu Y, Witherell P, Wang CCL, Rosen DW, et al. Research and application of machine learning for additive manufacturing. Addit Manuf 2022; 52: 102691.

[59]	Tang Y, Rahmani Dehaghani M, Wang GG . Review of transfer learning in modeling additive manufacturing processes. Addit Manuf 2023; 61: 103357.

[60]	Rasiya G, Shukla A, Saran K . Additive manufacturing―a review. Mater Today Proc 2021; 47: 6896-901.

[61]	Gan Z, Li H, Wolff SJ, Bennett JL, Hyatt G, Wagner GJ, et al. Data-driven microstructure and microhardness design in additive manufacturing using a self-organizing map. Engineering 2019; 5(4): 730- 5.

[62]	Storn R, Price K . Differential evolution―a simple and efficient heuristic for global optimization over continuous spaces. J Glob Optim 1997; 11(4): 341-59.

[63]	Lambora A, Gupta K, Chopra K . Genetic algorithm―a literature review. In: Proceedings of the 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon); Faridabad, India; 14-16 Feb 2019. Piscataway: IEEE; 2019. p. 380-4.

[64]	Clerc M, Kennedy J . The particle swarm-explosion, stability, and convergence in a multidimensional complex space. IEEE Trans Evol Comput 2002; 6(1): 58-73.

[65]	Zheng M, Zhang J, Zhan C, Ren X, Lü S . Proximal policy optimization with reward-based prioritization. Expert Syst Appl 2025; 283: 127659.

[66]	Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, et al. Human-level control through deep reinforcement learning. Nature 2015; 518: 529-33.