A data-driven method to predict future bottlenecks in a remanufacturing system with multi-variant uncertainties

Abstract

The remanufacturing system is remolding the manufacturing industry by bringing scrapped products back to such a condition that reintegrated performance is just as good as new. The remanufacturing environment is featured by a far deeper level of uncertainty than new manufacturing, such as probabilistic routing files, and highly variable processing time. The stochastic disturbances result in the production bottlenecks, which constrain the productivity of the job shop. The uncertainties in the remanufacturing process cause the bottlenecks to shift when the workshop is processing. Considering this outstanding problem, many researchers try to optimize the production process to mitigate dynamic bottlenecks toward a balanced state. This paper proposes a data-driven method to predict bottlenecks in the remanufacturing system with multi-variant uncertainties. Firstly, discrete event simulation technology is applied to establish a simulation model of the remanufacturing production line and calculate the bottleneck index to identify bottlenecks. Secondly, a data-driven method, auto-regressive moving average (ARMA) model is employed to predict the bottlenecks in the system based on real-time data captured by the Arena software. Finally, the proposed prediction method is verified on real data from the automobile engine remanufacturing production line.

Keywords

bottleneck identification / dynamic bottleneck / remanufacturing system / auto-regressive moving average model

References

[1] PengS-T, LiT, ZhaoJ-L, et al.. Petri net-based scheduling strategy and energy modeling for the cylinder block remanufacturing under uncertainty [J]. Robotics and Computer-Integrated Manufacturing, 2019, 58: 208-219

[2] XiangW, MingC. Implementing extended producer responsibility: Vehicle remanufacturing in China [J]. Journal of Cleaner Production, 2011, 19(67): 680-686

[3] LiL-L, LiC-B, TangY, et al.. An integrated approach of reverse engineering aided remanufacturing process for worn components [J]. Robotics and Computer-Integrated Manufacturing, 2017, 48: 39-50

[4] ZanoniS, SegerstedtA, TangO, et al.. Multi-product economic lot scheduling problem with manufacturing and remanufacturing using a basic period policy [J]. Computers & Industrial Engineering, 2012, 62(4): 1025-1033

[5] AliA, ChenX-H, YangZ-M, et al.. Optimized maintenance design for manufacturing performance improvement using simulation [C]. 2008 Winter Simulation Conference, 2008, Miami, FL, USA, IEEE, 18111819

[6] GopalakrishnanM, SkooghA, LaroqueC. Simulation-based planning of maintenance activities in the automotive industry [C]. 2013 Winter Simulations Conference (WSC), 2013, Washington, DC, USA., IEEE, 26102621

[7] SubramaniyanM, SkooghA, GopalakrishnanM, et al.. An algorithm for data-driven shifting bottleneck detection [J]. Cogent Engineering, 2016, 3(1): 1239516

[8] WuestT, WeimerD, IrgensC, et al.. Machine learning in manufacturing: Advantages, challenges, and applications [J]. Production & Manufacturing Research, 2016, 4123-45

[9] LiL, ChangQ, NiJ. Data driven bottleneck detection of manufacturing systems [J]. International Journal of Production Research, 2009, 47(18): 5019-5036

[10] SubramaniyanM, SkooghA, SalomonssonH, et al.. A data-driven algorithm to predict throughput bottlenecks in a production system based on active periods of the machines [J]. Computers & Industrial Engineering, 2018, 125: 533-544

[11] Jin Xiaoning, SiegelD, WeissB A, et al.. The present status and future growth of maintenance in US manufacturing: Results from a pilot survey [J]. Manufacturing Review, 2016, 3: 10

[12] QingC, JunN, PulakB, et al.. Supervisory factory control based on real-time production feedback [J]. Journal of Manufacturing Science and Engineering, 2007, 129(3): 653-660

[13] MuthiahK M N, HuangS H. Overall throughput effectiveness (OTE) metric for factory-level performance monitoring and bottleneck detection [J]. International Journal of Production Research, 2007, 45(20): 4753-4769

[14] LiL. Bottleneck detection of complex manufacturing systems using a data-driven method [J]. International Journal of Production Research, 2009, 47(24): 6929-6940

[15] LiL, ChangQ, XiaoG-X, AmbaniS. Throughput bottleneck prediction of manufacturing systems using time series analysis [J]. Journal of Manufacturing Science and Engineering, 2011, 133(2): 021015

[16] BangaloreP, TjernbergL B. An artificial neural network approach for early fault detection of gearbox bearings [J]. IEEE Transactions on Smart Grid, 2015, 62980-987

[17] SubramaniyanM, SkooghA, GopalakrishnanM, et al.. Real-time data-driven average active period method for bottleneck detection [J]. International Journal of Design & Nature and Ecodynamics, 2016, 11(3): 428-437

[18] ZhangJ-B, SongG-H, YuL, et al.. Identification and characteristics analysis of bottlenecks on urban expressways based on floating car data [J]. Journal of Central South University, 2018, 25(8): 2014-2024

[19] ChiangS-Y, KuoC T, MeerkovS M. DT-bottlenecks in serial production lines: Theory and application [J]. IEEE Transactions on Robotics and Automation, 2000, 16(5): 567-580

[20] ChiangS Y, KuoC T, MeerkovS M. C-Bottlenecks in serial production lines: Identification and application [J]. Mathematical Problems in Engineering, 2001, 7(6): 543-578

[21] AldenJ M, BurnsL D, CostyT, et al.. General motors increases its production throughput [J]. Interfaces, 2006, 36(1): 6-25

[22] SenguptaS, DasK, VantilR P. A new method for bottleneck detection [C]. 2008 Winter Simulation Conference, 2008, Miami, FL, USA, IEEE, 1741-1745

[23] GERSHWIN S B. An efficient decomposition method for the approximate evaluation of production lines with finite storage space [C]//Analysis and Optimization of Systems. 1984: 645–658. DOI: https://doi.org/10.1007/BFb0006317.

[24] LIM J T, MEERKOV S M, TOP F. Homogeneous, asymptotically reliable serial production lines: Theory and case study [C]// Proceedings of ICCON IEEE International Conference on Control and Applications. 1989: 596–601. DOI: https://doi.org/10.1109/ICCON.1989.770587.

[25] BillerS, LiJ-S, MarinS P, et al.. Bottlenecks in bernoulli serial lines with rework [J]. IEEE Transactions on Automation Science and Engineering, 2010, 7(2): 208-217

[26] HeH-W, QuanS-W, SunF-C, et al.. Model predictive control with lifetime constraints based energy management strategy for proton exchange membrane fuel cell hybrid power systems [J]. IEEE Transactions on Industrial Electronics, 2020, 67(10): 9012-9023

[27] ZhaoB, QuanZ-Y, LiY-W, et al.. A hybrid-driven elevator system with energy regeneration and safety enhancement [J]. IEEE Transactions on Industrial Electronics, 2020, 67(9): 7715-7726

[28] HofmannC, StaehrT, CohenS, et al.. Augmented Go & See: An approach for improved bottleneck identification in production lines [J]. Procedia Manufacturing, 2019, 31: 148-154

[29] LiL, ChangQ, NiJ, et al.. Real time production improvement through bottleneck control [J]. International Journal of Production Research, 2009, 47(21): 6145-6158

[30] CorbynJ. Time series analysis with applications in R [J]. Journal of the Royal Statistical Society: Series A (Statistics in Society), 2011, 174(2): 507

[31] KeskinM E, TaylanD, TerziÖ. Adaptive neural-based fuzzy inference system (ANFIS) approach for modelling hydrological time series [J]. Hydrological Sciences Journal, 2006, 514588-598

[32] WangJ-J, WangJ-Z, ZhangZ G, et al.. Stock index forecasting based on a hybrid model [J]. Omega, 2012, 40(6): 758-766

[33] WillmottC J, MatsuuraK. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance [J]. Climate Research, 2005, 30: 79-82

[34] ChaiT, DraxlerR R. Root mean square error (RMSE) or mean absolute error (MAE)?–Arguments against avoiding RMSE in the literature [J]. Geoscientific Model Development, 2014, 7(3): 1247-1250

[35] SuC, CaoB-X. Dynamic bottleneck analusis for remanufacturing system cosidering quality uncertainty [J]. Computer Integrated Manufacturing System, 2014, 20(5): 1062-1069(in Chinese)