Completion time prediction is crucial for analyzing and monitoring the execution of shop-floor’s production planning. However, predicting completion time is still challenging because production process has high uncertainty and influenced by the interaction of various factors. To address above challenges, the stacking ensemble learning based probabilistic prediction model (SEL-PP) to predict completion time is developed. Thereinto, fully connected neural network (FCNN), random forest (RF) and gradient boosted regression tree (GBRT) are used as the first-level base learner to exhibit better nonlinear characteristics, and quantile regression neural network (QRNN) is used as the second-level meta-learner to rectify the mistakes in the prediction of the base learner. After that, the kernel density estimation (KDE) is employed for achieving probability density prediction of completion time. Moreover, particle swarm optimization (PSO) is adopted for key parameter optimization of SEL-PP. Taking the aircraft overhaul shop-floor as an example, a case study is constructed to demonstrate the feasibility and effectiveness of SEL-PP. Through comparing the results, it indicates that the SEL-PP model has better performance in predicting completion time of flexible shop-floor.
ZhangYGuoZLvJ, et al. A framework for smart production-logistics systems based on CPS and industrial IoT. IEEE Trans Ind Inform2018; 14(9): 4019–4032.
2.
HajibabaeiMBehnamianJ.Flexible job-shop scheduling problem with unrelated parallel machines and resources-dependent processing times: a tabu search algorithm. Int J Manag Sci Eng2021; 16(4): 242–253.
3.
ZhuHJiangTWangY, et al. Multi-objective discrete water wave optimization algorithm for solving the energy-saving job shop scheduling problem with variable processing speeds. J Intell Fuzzy Syst2021; 40(6): 10617–10631.
4.
FangWGuoYLiaoW, et al. A Parallel Gated Recurrent Units (P-GRUs) network for the shifting lateness bottleneck prediction in make-to-order production system. Comput Ind Eng2020; 140: 106246.
5.
WangSGuoYHuangS, et al. A spatial-temporal feature fusion network for order remaining completion time prediction in discrete manufacturing workshop. Int J Prod Res2024; 62(10): 3638–3653.
6.
WangCJiangY.Deep neural networks based order completion time prediction by using real-time job shop RFID data. J Intell Manuf2019; 30(3): 1303–1318.
7.
HuHJiaXLiuK, et al. Self-adaptive traffic control model with behavior trees and reinforcement learning for AGV in Industry 4.0. IEEE Trans Ind Inform2021; 17(12): 7968–7979.
8.
HuHJiaXHeQ, et al. Deep reinforcement learning based AGVs real-time scheduling with mixed rule for flexible shop floor in industry 4.0. Comput Ind Eng2020; 149: 106749.
9.
WangWZhangYGuJ, et al. A proactive manufacturing resources assignment method based on production performance prediction for the smart factory. IEEE Trans Ind Inform2022; 18(1): 46–55.
10.
ChenTJeangAWangY.A hybrid neural network and selective allowance approach for internal due date assignment in a wafer fabrication plant. Int J Adv Manuf Tech2008; 36: 570–581.
11.
CaoZLiuXHaoJ, et al. Simultaneous prediction for multiple key performance indicators in semiconductor wafer fabrication. Chinese J Electron2016; 25(6): 1159–1165.
12.
JohanssonSKullströmMBjörkJ, et al. Digital production innovation projects-The applicability of managerial controls under high levels of complexity and uncertainty. J Manuf Technol Manag2021; 32(3): 772–794.
13.
KhosraviANahavandiSCreightonD.Prediction intervals for short-term wind farm power generation forecasts. IEEE Trans Sustain Energy2013; 4(3): 602–610.
14.
SaeedALiCGanZ, et al. A simple approach for short-term wind speed interval prediction based on independently recurrent neural networks and error probability distribution. Energy2022; 238: 122012.
15.
ChangJKongXYinL.A novel approach for product makespan prediction in production life cycle. Int J Adv Manuf Tech2015; 80(5–8): 1433–1448.
16.
ChenMZengGLuK, et al. A two-layer nonlinear combination method for short-term wind speed prediction based on ELM, ENN, and LSTM. IEEE Internet Things J2019; 6(4): 6997–7010.
17.
ZhangZZhangYWenY, et al. An improved stacking ensemble learning model for predicting the effect of lattice structure defects on yield stress. Comput Ind2023; 151: 103986.
18.
YangHLiWHuK, et al. Deep ensemble learning with non-equivalent costs of fault severities for rolling bearing diagnostics. J Manuf Syst2021; 61: 249–264.
19.
MaSChuF.Ensemble deep learning-based fault diagnosis of rotor bearing systems. Comput Ind2019; 105: 143–152.
20.
CuiSYinYWangD, et al. A stacking-based ensemble learning method for earthquake casualty prediction. Appl Soft Comput2021; 101: 107038.
21.
WeiYWuD.Material removal rate prediction in chemical mechanical planarization with conditional probabilistic autoencoder and stacking ensemble learning. J Intell Manuf2024; 35: 115–127.
22.
ChungDYunJLeeJ, et al. Predictive model of employee attrition based on stacking ensemble learning. Expert Syst Appl2023; 215: 119364.
23.
HeYXiaoJAnX, et al. Short-term power load probability density forecasting based on GLRQ-Stacking ensemble learning method. Int J Electr Power Energy Syst2022; 142: 108243.
24.
HeYZhengY.Short_term power load probability density forecasting based on Yeo_Johnson transformation quantile regression and Gaussian kernel function. Energy2018; 154: 143–156.
25.
ZhangZQinHLiuY, et al. Wind speed forecasting based on quantile regression minimal gated memory network and Kernel density estimation. Energy Convers Manag2019; 196(15): 1395–1409.
26.
JiangNYuXAlamM.A hybrid carbon price prediction model based-combinational estimation strategies of quantile regression and long short-term memory. J Clean Prod2023; 429: 139508.
27.
ZhaoJXueZLiT, et al. An energy and time prediction model for remanufacturing process using graphical evaluation and review technique (GERT) with multivariant uncertainties. Environ Sci Pollut Res. Epub ahead of print 13April2021. DOI: 10.1007/s11356-021-13438-z.
28.
RennaP.Controllable processing times with limited resources and energy consumption in flow shops: an assessment by simulation. Int J Manag Sci Eng Manag2024; 19(3): 239–250.
29.
MourtzisD.Simulation in the design and operation of manufacturing systems: state of the art and new trends. Int J Prod Res2020; 58(7): 1927–1949.
30.
WangJZhangJWangX.A two-dimensional long-short-term memory model with multiply memory units for short-term cycle time forecasting in re-entrant manufacturing systems. IEEE Trans Ind Inform2017; 14: 748–758.
31.
TripathiVSaraswatSGautamG.Improvement in shop floor management using ANN coupled with VSM: a case study. Proc IMechE, Part C: J Mechanical Engineering Science2022; 236(10): 5651–5662.
32.
HuangSGuoYLiuD, et al. A two-stage transfer learning-based deep learning approach for production progress prediction in IoT-enabled manufacturing. IEEE Internet Things J2019; 6(6): 10627–10638.
33.
FangWGuoYLiaoW, et al. Big data driven jobs remaining time prediction in discrete manufacturing system: a deep learning-based approach. Int J Prod Res2020; 58(9): 2751–2766.
34.
MohsenOMohamedYAl-HusseinM.A machine learning approach to predict production time using real-time RFID data in industrialized building construction. Adv Eng Inform2022; 52: 101631.
35.
BackusPJanakiramMMowzoonS, et al. Factory cycle-time prediction with a data-mining approach. IEEE Trans Semicond Manuf2006; 19: 252–258.
36.
OzturkAKayalgilSOzdemirelN.Manufacturing lead time estimation using data mining. Eur J Oper Res2006; 173(2): 683–700.
37.
LingitzLGallinaVAnsariF, et al. Lead time prediction using machine learning algorithms: a case study by a semiconductor manufacturer. Procedia CIRP2018; 72: 1051–1056.
38.
HouSLiuYYangQ.Real-time prediction of rock mass classification based on TBM operation big data and stacking technique of ensemble learning. J Rock Mech Geotech2022; 14: 123–143.
39.
ZhouDZhuangXZuoH.A hybrid deep neural network based on multi-time window convolutional bidirectional LSTM for civil aircraft APU hazard identifcation. Chinese J Aeronaut2022; 35(4): 344–361.
40.
ZhouPXuZZhuX, et al. Granulation-based long-term interval prediction considering spatial–temporal correlations for gas demand prediction in the steel industry. Expert Syst Appl2024; 248: 123382.
41.
LiQSongZ.Prediction of compressive strength of rice husk ash concrete based on stacking ensemble learning model. J Clean Prod2023; 382: 135279.
42.
ZhangZHongWLiJ.Electric load forecasting by hybrid self-recurrent support vector regression model with variational mode decomposition and improved cuckoo search algorithm. IEEE Access2020; 8: 14642–14658.
