This study introduces an advanced approach to the Parallel Assembly Sequence Planning (PASP) problem, addressing the complexities of task interdependencies and real-time adaptability across multiple parallel assembly lines. Traditional PASP methods often rely on static heuristics and struggle to accommodate dynamic production environments. To overcome these limitations, we propose the Advanced Priority Relationship Algorithm (APRA), a machine learning-enhanced framework that dynamically predicts assembly sequence parameters using a random forest model. APRA incorporates a priority relationship algorithm to optimize task sequencing in real-time, striking a balance between efficiency, cost, and quality. Experimental evaluations on complex assembly scenarios demonstrate APRA’s effectiveness, achieving a 26% reduction in assembly time (from 120 to 88.8 h) and a Coefficient of determination (R2) accuracy score of 0.8686, capturing 86.86% of the variability in efficiency. Additionally, small-scale validation confirms its ability to provide near-optimal solutions with reduced computational time, making it feasible for large-scale industrial applications. This research presents a novel problem formulation for PASP and a robust, adaptive solution framework, providing manufacturers with a powerful tool for enhancing productivity and responsiveness in dynamic assembly scheduling.
LiDXZhaoYLiuYXueYT.Study on the method of assembly sequence integrated evaluation for wind turbine. Modern Manuf Eng2013; 16: 1671–3133. 2013.
2.
MutaleSWangYYasirJ, et al. Advanced optimization techniques for PASP: a comparative study of improved PSO and BFO. In: 2024 6th international conference on power and energy technology (ICPET). Beijing: IEEE, 2024. pp. 867–871.
3.
YiYYanYLiuX, et al. Digital twin-based smart assembly process design and application framework for complex products and its case study. J Manuf Syst2021; 58: 94–107.
4.
YangYYangMShuL, et al. A novel parallel assembly sequence planning method for complex products based on PSOBC. Math Probl Eng2020; 2020: 7848329.
5.
GaoBZhangSSunH, et al. Assembly sequence planning based on adaptive gravitational search algorithm. Int J Adv Manuf Technol2021; 115(11–12): 3689–3700.
6.
HuYBaoXJinJS.Minimising makespan on parallel machines with precedence constraints and machine eligibility restrictions. Int J Prod Res2009; 48(6): 1639–1651.
7.
ZhangZZYuanB.A new discrete double-population firefly algorithm for assembly sequence planning. Proc Inst Mech Eng Part B: J Eng Manuf2016; 230(12): 2229–2238.
8.
LaiGLXingXMSunYF, et al. Optimisation of assembly sequences for compliant body assemblies. Int J Prod Res2009; 47(21): 6129–6143.
9.
MutaleSWangYYasirJ, et al. Exploring the economic prospects of wind energy in Zambia. Int J Sustain Eng2024; 17(1): 30–45.
10.
WuHJiangZZhuS, et al. A knowledge graph based disassembly sequence planning for end-of-life power battery. Int J Precis Eng Manuf Green Technol2023; 11(3): 849–861.
11.
ChenTZhaoYLiX, et al. Machine learning in manufacturing towards Industry 4.0: From ‘For Now’ to ‘Four-Know’. Appl Sci2023; 13(3): 1903.
12.
VishwanadhamMSurabhiSNR. Leveraging AI and ML for enhanced efficiency and innovation in manufacturing: a comparative analysis. J Artif Intell Big Data2021; 1: 943.
13.
RaiATiwariMKIvanovD, et al. Machine learning in manufacturing and industry 4.0 applications. Int J Prod Res2021; 59(16): 4773–4778.
14.
PouriyehKKAllahyariMLiuQ, et al. Ontology summarization: Graph-based methods and beyond. Int J Semant Comput2019; 13(2): 259–283.
15.
NayakBBRBahubalendruniMVAR. Comparison of liaison concatenation method with simulated annealing for assembly sequence generation problems. In: 1st international conference on next generation computing technologies (NGCT), 2015. pp. 531–535. Dehradun: IEEE.
16.
BasarMADerO. AI-powered hybrid metaheuristic optimization for predicting surface roughness and kerf width in CO2 laser cutting of 3D-printed PLA-CF composites. J Thermoplast Compos Mater2025; 38(7): 2688–2717.
17.
YaghoubiAYaghoubiEKhameesA, et al. A systematic review and meta-analysis of artificial neural network, machine learning, deep learning, and ensemble learning approaches in field of geotechnical engineering. Neural Comput Appl2024; 36: 12655–12699.
18.
ChandranCPSNPatelGCMChateGR, et al. Multi-input multi-output modeling of anthill clay-bonded sand mold system using artificial neural networks: forward and reverse predictions. Eng Reports2025; 7(6).
19.
IvanovDDolguiA. A digital supply chain twin for managing the disruption risks and resilience in the era of Industry 4.0. Prod Plan Control2020; 31(5): 375–388.
20.
ChampatirayCDBahubalendruniMVARMahapatraRN.Optimisation of assembly sequence planning with tool uncertainties. Proc Inst Mech Eng Part B: J Eng Manuf2024; 238(6–7): 851–862.
21.
WanXLiuKQiuW, et al. An assembly sequence planning method based on multiple optimal solutions genetic algorithm. Mathematics2024;12(4): 574.
22.
ZhuXXuZWangJ, et al. Graph-based assembly sequence planning algorithm with feedback weights. Int J Adv Manuf Technol2023; 125(7–8): 3607–3617.
23.
WangYWangJFengJ, et al. Integrated task sequence planning and assignment for human–robot collaborative assembly station. Flex Serv Manuf J2023; 35(4): 979–1006.
24.
TaoYCQiaoFZhangL, et al. GA-BHTR: An improved genetic algorithm for partner selection in virtual manufacturing. Int J Prod Res2011; 50(8): 2079–2100.
25.
LinSWYingKC.Single machine scheduling problems with sequence-dependent setup times and precedence delays. Sci Rep2022; 12(1): 1–12.
26.
GaoLZhangCLiX, et al. Discrete electromagnetism-like mechanism algorithm for assembly sequences planning. Int J Prod Res2014; 52(12): 3485–3503.
27.
ÖzdemirRGKulaUHelalM.Assembly line balancing with product and operator oriented sequence dependent task times using tabu search algorithm. Int J Interact Des Manuf2024; 18(6): 4209–4222.
28.
TarekAEHodaA.Reactive design methodology for product family platforms, modularity and parts integration. CIRP J Manuf Sci Technol2013; 6(1): 34–43.
29.
GulivindalaAKBahubalendruniMVARInkuluAK, et al. A modified cut-set method for mechanical subassembly identification. Assem Autom2021; 41(6): 659–680.
30.
BahubalendruniMVARBiswalBB. An efficient stable subassembly identification method towards assembly sequence generation. Natl Acad Sci Lett2018; 41: 375–378.
31.
GulivindalaAKBahubalendruniMVARVarupalaSSVPK. A heuristic method with a novel stability concept to perform parallel assembly sequence planning by subassembly detection. Assem Autom2020; 40(5): 779–787.
32.
BiswalMRBBiswalBB. A review on assembly sequence generation and its automation. Proc Inst Mech Eng Part C: J Mech Eng Sci2016; 30(5): 1–15.
33.
ZiqiuTCagatayKBedirC.Machine learning applications in production lines: a systematic literature review. Comput Ind Eng2020; 149: 106773.
34.
XuJLiXWangH, et al. A review on AI for smart manufacturing: Deep learning challenges and solutions. Appl Sci2022; 12(16): 8239.
35.
YinJYuJ.Assembly line balancing based on an adaptive genetic algorithm. Int J Adv Manuf Technol2010; 48(1): 347–354.
36.
MutaleSWangYTianD.Optimizing assembly error reduction in wind turbine gearboxes using parallel assembly sequence planning and hybrid particle Swarm-Bacteria foraging optimization Aagorithm. Energies2025; 18(15): 3997.
37.
GohilD.Impact of real time data in manufacturing operations. Int Res J Eng Technol2020; 7(9): 1376–1379.
38.
ZhangZWangXSongQ, et al. Human-robot collaboration in mixed-flow assembly line balancing under uncertainty: an efficient discrete bees algorithm. J Ind Inf Integr2021; 23: 100216.
39.
ÇilEALiZMeteS, et al. Mathematical model and bee algorithms for mixed-model assembly line balancing problem with physical human-robot collaboration. Appl Soft Comput2020; 93: 106394.
40.
BoschettiRFaccioMMilaneseM, et al. C-ALB (Collaborative Assembly Line Balancing): a new approach in cobot solutions. Int J Adv Manuf Technol2021; 116: 3027–3042.
41.
DeepakBBVLMuraliGBBahubalendruniMVAR. Assembly sequence planning using soft computing methods: a review. Proc Inst Mech Eng Part E: J Process Mech Eng2019; 233(3): 653–683.
42.
ShahiVJMasoumiAFranciosaP, et al. A quality-driven assembly sequence planning and line configuration selection for non-ideal compliant structures assemblies. Int J Adv Manuf Technol2020; 106(1–2): 15–30.
43.
XiangyuQLiuLWanX, et al. Assembly sequence optimization based on improved PSO algorithm. In: Advances in intelligent systems and computing, 2019. pp. 457–465.
44.
JiangLMoHTianP.An adaptive decentralized control strategy for deployment and aggregation of swarm robots based on bacterial chemotaxis. Appl Intell2023; 53(10): 13018–13036.
45.
PanHLiuYXuB, et al. Hybrid feedback feedforward: an efficient design of adaptive neural network control. Neural Netw2015; 76: 122–134.
46.
XuJLiXWangH, et al. Real-time adaptive control in smart manufacturing: enhancing responsiveness with continuous model updates. J Manuf Syst2022; 63: 312–323.
47.
MichalosGSpiliotopoulosJMakrisS, et al. A method for planning human robot shared tasks. CIRP J Manuf Sci Technol2018; 22: 76–90.
48.
WuBLuPLuJ, et al. A hierarchical parallel multi-station assembly sequence planning method based on GA-DFLA. Proc Inst Mech Eng Part C: J Mech Eng Sci2022; 236(4): 2029-2045.
49.
JabeurMHMahjoubSToublancC, et al. Optimizing integrated lot sizing and production scheduling in flexible flow line systems with energy scheme: a two level approach based on reinforcement learning. Comput Ind Eng. 2024; 190: 110095.
50.
Soysal-KurtHİşleyenSKGökçenH.Balancing and sequencing of mixed-model parallel robotic assembly lines considering energy consumption. Flex Serv Manuf J2025; 37: 38–66.
51.
SlamaMArbaouiINourmohammadiT, et al. Assembly line balancing with collaborative robots under uncertainty of human processing times. In: Proceedings of the 2023 9th international conference on control, decision and information technologies (CoDIT), 2023. pp. 2649–2663.
GkournelosCKonstantinouCAngelakisP, et al. Praxis: a framework for AI-driven human action recognition in assembly. J Intell Manuf2023; 35(8): 3697–3711.
54.
MutaleSWangYYasirJ.Enhanced efficiency and quality in wind turbine gearbox assembly: A new parallel assembly sequence planning (PASP) model. Int J Sustain Eng2024; 17(1): 1048–1065.
55.
HastieTTibshiraniRFriedmanJ.The elements of statistical learning: Data mining, inference, and prediction. 2nd ed.New York: Springer, 2009.
56.
BocklischFPaczkowskiGZimmermannS, et al. Integrating human cognition in cyber-physical systems: a multidimensional fuzzy pattern model with application to thermal spraying. J Manuf Syst2022; 63: 162–176.
57.
JamesGWittenDHastieT, et al. An introduction to statistical machine learning with applications in Python. Springer Texts in Statistics. 2023. Available at: https://www.statlearning.com/
58.
HastieTTibshiraniRJamesG, et al. An introduction to statistical learning. Springer Texts in Statistics. Vol. 102. New York: Springer; 2006. p. 618.
59.
HyndmanRJKoehlerAB.Another look at measures of forecast accuracy. Int J Forecast2006; 22(4): 679–688.
60.
CleitonFPierreR.Análise em caixa multiplicadora eólica utilizando o método de inspeção boroscopica. 2022.
61.
YasirJWangYMutaleS, et al. Quantifying the impact of wind shear coefficient on annual energy production of coastal wind farm in Balochistan, Pakistan. 2025.
62.
MutaleSBandaAWangY, et al. Capability of Zambian industries to manufacture grid-scale wind turbine blades and towers. Preprints. 2023.
63.
MutaleSJanYWangY, et al. Evaluation of wind energy potential in Lunga District, Luapula Province, Zambia. 2025.
64.
MutaleSWangYYasirJ, et al. Effect of wind shear coefficients on electrical energy generation in Lunga, Renewable Energies2025; 3(1).
65.
Heidary DahooieWKMBJZavadskasEKFiroozfarHR, et al. An improved fuzzy MULTIMOORA approach for multi-criteria decision making based on objective weighting method (CCSD) and its application to technological forecasting method selection. Eng Appl Artif Intell2019; 79: 114–128.
