Energy-efficient buffer and service rate allocation in manufacturing systems using hybrid machine learning and evolutionary algorithms

doi:10.1007/s40436-023-00461-1

Advances in Manufacturing ›› 2024, Vol. 12 ›› Issue (2): 227-251.doi: 10.1007/s40436-023-00461-1

• • 上一篇

Energy-efficient buffer and service rate allocation in manufacturing systems using hybrid machine learning and evolutionary algorithms

Si-Xiao Gao¹, Hui Liu¹, Jun Ota²

1 Key Laboratory of Traffic Safety on Track of Ministry of Education, Institute of Artificial Intelligence and Robotics (IAIR), School of Traffic and Transportation Engineering, Central South University, Changsha 410075, People's Republic of China;
2 Research into Artifacts Center for Engineering, School of Engineering, The University of Tokyo, Tokyo, Japan

收稿日期:2022-08-09 修回日期:2023-02-16 发布日期:2024-05-16
通讯作者: Hui Liu,E-mail:csuliuhui@csu.edu.cn E-mail:csuliuhui@csu.edu.cn
作者简介:Si-Xiao Gao received the B.S. and M.S. degrees in mechanical engineering from Central South University, Changsha, China, in 2011 and 2014, respectively, the Ph.D. degrees from the Faculty of Engineering, The University of Tokyo, in 2020. He is currently a post researcher at the School of Traffic and Transportation Engineering, Central South University. His research interests include design and optimization of manufacturing systems, and intelligent manufacturing big data;
Hui Liu received the B.Sc. (Honors) and M.Sc. degrees from Central South University, China, in 2004 and 2008, respectively, the Ph.D. from Central South University, China, in 2011, the Dr.-Ing. degree from University of Rostock, Germany, in 2013 and the habil. degree from University of Rostock, Germany in 2015. Currently, he is a full professor of robotics & artificial intelligence at Central South University, China. He is deputy dean of the faculty of traffic and transportation engineering at Central South University, China. He previously served as the BMBF junior group leader appointed by the Ministry of Education & Research of Germany at University of Rostock, Germany. His current research areas of interest include robotics, time series forecasting, big data analysis, smart devices, and systems, etc;
Jun Ota received the B.E., M.E., and Ph.D. degrees from the Faculty of Engineering, The University of Tokyo, in 1987, 1989, and 1994, respectively, where he is currently a Professor of Research into Artifacts Center for Engineering (RACE). From 1989 to 1991, he was with Nippon Steel Cooperation. In 1991, he was a Research Associate with The University of Tokyo. In 1994, he became a Lecturer. In 1996, he became an Associate Professor. From 1996 to 1997, he was a Visiting Scholar at Stanford University. In 2009, he became a professor with the Graduate School of Engineering, The University of Tokyo. In 2009, he became a Professor with RACE. Since 2015, he has been a Guest Professor with the South China University of Technology. His research interests include multi-agent robot systems, embodied-brain systems science, design support for large-scale production/material handling systems, and human behavior analysis and support.

Energy-efficient buffer and service rate allocation in manufacturing systems using hybrid machine learning and evolutionary algorithms

Si-Xiao Gao¹, Hui Liu¹, Jun Ota²

1 Key Laboratory of Traffic Safety on Track of Ministry of Education, Institute of Artificial Intelligence and Robotics (IAIR), School of Traffic and Transportation Engineering, Central South University, Changsha 410075, People's Republic of China;
2 Research into Artifacts Center for Engineering, School of Engineering, The University of Tokyo, Tokyo, Japan

Received:2022-08-09 Revised:2023-02-16 Published:2024-05-16
Contact: Hui Liu,E-mail:csuliuhui@csu.edu.cn E-mail:csuliuhui@csu.edu.cn

摘要/Abstract

摘要： Currently, simultaneous buffer and service rate allocation is a topic of interest in the optimization of manufacturing systems. Simultaneous allocation problems have been solved previously to satisfy economic requirements; however, owing to the progress of green manufacturing, energy conservation and environmental protection have become increasingly crucial. Therefore, an energy-efficient approach is developed to maximize the throughput and minimize the energy consumption of manufacturing systems, subject to the total buffer capacity, total service rate, and predefined energy efficiency. The energy-efficient approach integrates the simulated annealing-non-dominated sorting genetic algorithm-II with the honey badger algorithm-histogram-based gradient boosting regression tree. The former algorithm searches for Pareto-optimal solutions of sufficient quality. The latter algorithm builds prediction models to rapidly calculate the throughput, energy consumption, and energy efficiency. Numerical examples show that the proposed hybrid approach can achieve a better solution quality compared with previously reported approaches. Furthermore, the prediction models can rapidly evaluate manufacturing systems with sufficient accuracy. This study benefits the multi-objective optimization of green manufacturing systems.

The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-023-00461-1

关键词: Energy-efficient allocation, Multi-objective optimization, Energy efficiency, Energy consumption, Machine learning

Abstract: Currently, simultaneous buffer and service rate allocation is a topic of interest in the optimization of manufacturing systems. Simultaneous allocation problems have been solved previously to satisfy economic requirements; however, owing to the progress of green manufacturing, energy conservation and environmental protection have become increasingly crucial. Therefore, an energy-efficient approach is developed to maximize the throughput and minimize the energy consumption of manufacturing systems, subject to the total buffer capacity, total service rate, and predefined energy efficiency. The energy-efficient approach integrates the simulated annealing-non-dominated sorting genetic algorithm-II with the honey badger algorithm-histogram-based gradient boosting regression tree. The former algorithm searches for Pareto-optimal solutions of sufficient quality. The latter algorithm builds prediction models to rapidly calculate the throughput, energy consumption, and energy efficiency. Numerical examples show that the proposed hybrid approach can achieve a better solution quality compared with previously reported approaches. Furthermore, the prediction models can rapidly evaluate manufacturing systems with sufficient accuracy. This study benefits the multi-objective optimization of green manufacturing systems.

The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-023-00461-1

Key words: Energy-efficient allocation, Multi-objective optimization, Energy efficiency, Energy consumption, Machine learning

Si-Xiao Gao, Hui Liu, Jun Ota. Energy-efficient buffer and service rate allocation in manufacturing systems using hybrid machine learning and evolutionary algorithms[J]. Advances in Manufacturing, 2024, 12(2): 227-251.

参考文献

1. Lin G, Hao B (2020) Research on green manufacturing technology. J Phys Conf Ser 1601:042046. https://doi.org/10.1088/1742-6596/1601/4/042046
2. Tekkaya AE (2018) Energy saving by manufacturing technology. Procedia Manuf 21:392–396
3. Cruz FRB, Kendall G, While L et al (2012) Throughput maximization of queueing networks with simultaneous minimization of service rates and buffers. Math Probl Eng 2012:1–19. https://doi.org/10.1155/2012/692593
4. Gao S, Higashi T, Kobayashi T et al (2020) Buffer allocation via bottleneck-based variable neighbourhood search. Appl Sci-Basel 10(23):8569. https://doi.org/10.3390/app10238569
5. Frigerio N, Matta A (2016) Analysis on energy efficients witching of machine tool with stochastic arrivals and buffer information. IEEE Trans Autom Sci Eng 13:238–246
6. Wang J, Fei Z, Chang Q et al (2019) Multi-state decision of unreliable machines for energy-efficient production considering work-in-process inventory. Int J Adv Manuf Technol 102:1009–1021
7. Alaouchiche Y, Ouazene Y, Yalaoui F (2021) Energy-efficient buffer allocation problem in unreliable production lines. Int J Adv Manuf Technol 114:2871–2885
8. Alaouchiche Y, Ouazene Y, Yalaoui F (2020) Economic and energetic performance evaluation of unreliable production lines: an integrated analytical approach. IEEE Access 8:185330–185345
9. Gao S (2022) A bottleneck detection-based tabu search algorithm for the buffer allocation problem in manufacturing systems. IEEE Access 10:60507–60520
10. Nahas N, Nourelfath M, Gendreau M (2014) Selecting machines and buffers in unreliable assembly/disassembly manufacturing networks. Int J Prod Econ 154:113–126
11. Smith JM (2018) Simultaneous buffer and service rate allocation in open finite queueing networks. IISE Trans 50(3):203–216
12. Ng AHC, Shaaban S, Bernedixen J (2017) Studying unbalanced workload and buffer allocation of production systems using multi-objective optimisation. Int J Prod Res 55(24):7435–7451
13. Xi S, Smith JM, Chen Q et al (2021) Simultaneous machine selection and buffer allocation in large unbalanced series-parallel production lines. Int J Prod Res 60(7):2103–2125
14. Renna P, Materi S (2021) A literature review of energy efficiency and sustainability in manufacturing systems. Appl Sci-Basel 11:7366. https://doi.org/10.3390/app11167366
15. Weiss S, Schwarz JA, Stolletz R (2019) The buffer allocation problem in production lines: formulations, solution methods, and instances. IISE Trans 51(5):456–485
16. Weiss S, Matta A, Stolletz R (2018) Optimization of buffer allocations in flow lines with limited supply. IISE Trans 50:191–202
17. Liberopoulos G (2020) Comparison of optimal buffer allocation in flow lines under installation buffer, echelon buffer, and CONWIP policies. Flex Serv Manuf J 32:297–365
18. Kose SY, Kilincci O (2015) Hybrid approach for buffer allocation in open serial production lines. Comput Oper Res 60:67–78
19. Koyuncuoğlu MU, Demir L (2021) A comparison of combat genetic and big bang–big crunch algorithms for solving the buffer allocation problem. J Intell Manuf 32:1529–1546
20. Cruz FRB (2009) Optimizing the throughput, service rate, and buffer allocation in finite queueing networks. Electron Notes Discrete Math 35:163–168
21. George Shanthikumar J, Xu SH (1997) Asymptotically optimal routing and service rate allocation in a multiserver queueing system. Oper Res 45(3):464–469
22. Song D, Xing W, Sun Y (1998) Optimal service rate allocation policy of an unreliable manufacturing system with random demands. Cont Theo Apps 15(4):621–626
23. Hillier FS, So KC (1996) On the simultaneous optimization of server and work allocations in production line systems with variable processing times. Oper Res 44(3):435–443
24. Nahas N, Nourelfath M (2018) Joint optimization of maintenance, buffers and machines in manufacturing lines. Eng Optimiz 50:37–54
25. Nahas N (2017) Buffer allocation and preventive maintenance optimization in unreliable production lines. J Intell Manuf 28:85–93
26. Yegul MF, Erenay FS, Striepe S et al (2017) Improving configuration of complex production lines via simulation-based optimization. Comput Ind Eng 109:295–312
27. Pedrielli G, Matta A, Alfieri A et al (2018) Design and control of manufacturing systems: a discrete event optimisation methodology. Int J Prod Res 56:543–564
28. Balsamo S (2011) Queueing networks with blocking: analysis, solution algorithms and properties. Springer, Berlin. https://doi.org/10.1007/978-3-642-02742-0_11
29. Gordon WJ, Newell GF (1967) Cyclic queuing systems with restricted length queues. Oper Res 15(2):266–277
30. Zhang M, Pastore E, Alfieri A et al (2021) Buffer allocation problem in production flow lines: a new Benders-decomposition-based exact solution approach. IISE Trans 54(5):421–434
31. Gao S, Rubrico JIU, Higashi T et al (2019) Efficient throughput analysis of production lines based on modular queues. IEEE Access 7:95314–95326
32. Gao S, Kobayashi T, Tajiri A et al (2021) Throughput analysis of conveyor systems involving multiple materials based on capability decomposition. Comput Ind 132:103526. https://doi.org/10.1016/j.compind.2021.103526
33. Yan FY, Wang JQ, Li Y et al (2021) An improved aggregation method for performance analysis of Bernoulli serial production Lines. IEEE Trans Autom Sci Eng 18:114–121
34. Mohammadi M, Dauzère-pérès S, Yugma C et al (2020) A queuebased aggregation approach for performance evaluation of a production system with an AMHS. Comput Oper Res 115:104838. https://doi.org/10.1016/j.cor.2019.104838
35. Bai Y, Tu J, Yang M et al (2021) A new aggregation algorithm for performance metric calculation in serial production lines with exponential machines: design, accuracy and robustness. Int J Prod Res 59:4072–4089
36. Florescu A, Barabas SA (2018) Simulation tool for assessing the performance of a flexible manufacturing system. IOP Conf Ser Mater Sci Eng 398:012023. https://doi.org/10.1088/1757-899X/398/1/012023
37. Oljira DG, Abeya TG, Ofgera G et al (2020) Manufacturing system modeling and performance analysis of mineral water production line using ARENA simulation. Int J Eng Adv Technol 9:312–317
38. Wang J, Xu C, Zhang J et al (2021) Big data analytics for intelligent manufacturing systems: a review. J Manuf Syst 62:738–752
39. Tsadiras AK, Papadopoulos CT, O’Kelly MEJ (2013) An artificial neural network based decision support system for solving the buffer allocation problem in reliable production lines. Comput Ind Eng 66:1150–1162
40. Demir L, Tunali S, Eliiyi DT (2014) The state of the art on buffer allocation problem: a comprehensive survey. J Intell Manuf 25:317–392
41. Ke G, Meng Q, Finley T et al (2017) LightGBM: a highly efficient gradient boosting decision tree. In: The 31st conference on neural information processing systems, NIPS, California
42. Sklearn. https://scikit-learn.org/stable/. Accessed 7 August
43. Hashim FA, Houssein EH, Hussain K et al (2022) Honey badger algorithm: new metaheuristic algorithm for solving optimization problems. Math Comput Simul 192:84–110
44. Chaudhari P, Thakur AK, Kumar R et al (2021) Comparison of NSGA-III with NSGA-II for multi objective optimization of adiabatic styrene reactor. Mater Today Proc 57(4):1509–1514
45. Niyomubyeyi O, Sicuaio TE, Díaz González JI et al (2020) A comparativestudy of four metaheuristic algorithms, AMOSA, MOABC, MSPSO, and NSGA-II for evacuation planning. Algorithms 13(1):16. https://doi.org/10.3390/a13010016
46. Deb K, Pratap A, Agarwal S et al (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE T Evolut Comput 6:182–197
47. Spinellis DD, Papadopoulos CT (2000) A simulated annealing approach for buffer allocation in reliable production lines. Ann Oper Res 93:373–384
48. Yelkenci KS, Kilincci O (2020) A multi-objective hybrid evolutionary approach for buffer allocation in open serial production lines. J Intel Manuf 31:33–51
49. Cruz FRB, Duarte AR, Souza GL (2018) Multi-objective performance improvements of general finite single-server queueing networks. J Heuristics 24:757–781
50. Su C, Shi Y, Dou J (2017) Multi-objective optimization of buffer allocation for remanufacturing system based on TS-NSGAII hybrid algorithm. J Clean Prod 166:756–770
51. Zhang K, Shen C, Liu X et al (2020) Multiobjective evolution strategy for dynamic multiobjective optimization. IEEE T Evolut Comput 24:974–988
52. Huang CL (1999) The construction of production performance prediction system for semiconductor manufacturing with artificial neural networks. Int J Prod Res 37:1387–1402
53. Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46–61
54. Mirjalili S, Saremi S, Mirjalili SM et al (2016) Multi-objective grey wolf optimizer: a novel algorithm for multi-criterion optimization. Expert Syst Appl 47:106–119
55. Li L, Qian Y, Yang YM et al (2016) A fast algorithm for buffer allocation problem. Int J Prod Res 54:3243–3255
56. Demir L, Diamantidis AC, Eliiyi DT et al (2019) Optimal buffer allocation for serial production lines using heuristic search algorithms: a comparative study. Int J Ind Syst Eng 33:252. https://doi.org/10.1504/IJISE.2019.102473
57. Nahas N, Ait-Kadi D, Nourelfath M (2006) A new approach for buffer allocation in unreliable production lines. Int J Prod Econ 103:873–881

[1]	Ling-Bao Kong, Yi Yu. Precision measurement and compensation of kinematic errors for industrial robots using artifact and machine learning[J]. Advances in Manufacturing, 2022, 10(3): 397-410.
[2]	Muhammad Rizwan Awan, Hernán A. González Rojas, José I. Perat Benavides, Saqib Hameed. Experimental technique to analyze the influence of cutting conditions on specific energy consumption during abrasive metal cutting with thin discs[J]. Advances in Manufacturing, 2022, 10(2): 260-271.
[3]	Kai-Ning Shi, Ning Liu, Cong-Le Liu, Jun-Xue Ren, Shan-Shan Yang, Wei Chit Tan. Indirect approach for predicting cutting force coefficients and power consumption in milling process[J]. Advances in Manufacturing, 2022, 10(1): 101-113.
[4]	Long-Hua Xu, Chuan-Zhen Huang, Jia-Hui Niu, Jun Wang, Han-Lian Liu, Xiao-Dan Wang. Prediction of cutting power and surface quality, and optimization of cutting parameters using new inference system in high-speed milling process[J]. Advances in Manufacturing, 2021, 9(3): 388-402.
[5]	Cai-Xia Zhang, Shu-Lin Dong, Hong-Yan Chu, Guo-Zhi Ding, Zhi-Feng Liu, Shi-Yao Guo, Chong-Bin Yang. Layout design of a mixed-flow production line based on processing energy consumption and buffer configuration[J]. Advances in Manufacturing, 2021, 9(3): 369-387.
[6]	Chunling Du, Choon Lim Ho, Jacek Kaminski. Prediction of product roughness, profile, and roundness using machine learning techniques for a hard turning process[J]. Advances in Manufacturing, 2021, 9(2): 206-215.
[7]	Zhao-Hui Liu, Zhong-Jie Wang, Chen Yang. Multi-objective resource optimization scheduling based on iterative double auction in cloud manufacturing[J]. Advances in Manufacturing, 2019, 7(4): 374-388.

Energy-efficient buffer and service rate allocation in manufacturing systems using hybrid machine learning and evolutionary algorithms

Energy-efficient buffer and service rate allocation in manufacturing systems using hybrid machine learning and evolutionary algorithms

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价