Skip to main content
Log in

Asymmetric cycle time bounding in semiconductor manufacturing: an efficient and effective back-propagation-network-based method

  • Original Paper
  • Published:
Operational Research Aims and scope Submit manuscript

Abstract

Estimating the cycle time of every job in a semiconductor manufacturing factory is essential. However, because cycle times are uncertain, determining the cycle time range is also crucial. Manufactures use the lower bound of a cycle time to promise an attractive due date to customers and the upper bound to indicate the latest possible time that fabrication will be completed. Thus, an interval estimate of cycle time is preferable to a point estimate. In several previous studies, a symmetric interval estimate has been derived from a probabilistic perspective. However, the managerial implications of the upper and lower bounds differ, and an asymmetric interval estimate is more useful. Therefore, this paper proposes a back-propagation-network-based approach to estimating the job cycle time and determining the cycle time range. A real case from a semiconductor manufacturing factory was used to illustrate the proposed method. According to the results, the estimates of the job cycle time obtained using the proposed method were precise and accurate. The established upper and lower bounds (especially the lower bound) were much tighter than those used in existing methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  • Baker KR (2014) Setting optimal due dates in a basic safe-scheduling model. Comput Oper Res 41:109–114

    Article  Google Scholar 

  • Benardos PG, Vosniakos GC (2002) Prediciton of surface roughness in CNC face milling using neural networks and Taguchi’s design of experiments. Robot Comput Integr Manuf 18(5–6):343–354

    Article  Google Scholar 

  • Bernardi S, Campos J (2013) A min–max problem for the computation of the cycle time lower bound in interval-based time petri nets. IEEE Trans Syst Man Cybern Part A Syst Hum 43(5):1167–1181

    Article  Google Scholar 

  • Bonnans JF, Gilbert JC, Lemaréchal C, Sagastizábal CA (2006) Numerical optimization: theoretical and practical aspects. Springer, Berlin

    Google Scholar 

  • Carrier PL (2013) Experiment 2: single hidden layer MLP. https://plcift6266.wordpress.com/2013/02/18/experiment-2-single-hidden-layer-mlp/

  • Chang P-C, Hsieh J-C (2003) A neural networks approach for due-date assignment in a wafer fabrication factory. Int J Ind Eng 10(1):55–61

    Google Scholar 

  • Chang P-C, Hsieh J-C, Liao TW (2005) Evolving fuzzy rules for due-date assignment problem in semiconductor manufacturing factory. J Intell Manuf 16:549–557

    Article  Google Scholar 

  • Chen T (2003) A fuzzy back propagation network for output time prediction in a wafer fab. Appl Soft Comput 2(3):211–222

    Article  Google Scholar 

  • Chen T (2007) An intelligent hybrid system for wafer lot output time prediction. Adv Eng Inform 21:55–65

    Article  Google Scholar 

  • Chen T (2009) A fuzzy-neural knowledge-based system for job completion time prediction and internal due date assignment in a wafer fabrication plant. Int J Syst Sci 40(8):889–902

    Article  Google Scholar 

  • Chen T (2013) An effective fuzzy collaborative forecasting approach for predicting the job cycle time in wafer fabrication. Comput Ind Eng 66:834–848

    Article  Google Scholar 

  • Chen T, Lin Y-C (2011) A collaborative fuzzy-neural approach for internal due date assignment in a wafer fabrication plant. Int J Innov Comput Inf Control 7(9):5193–5210

    Google Scholar 

  • Chen T, Wang Y-C (2010) Incorporating the FCM-BPN approach with nonlinear programming for internal due date assignment in a wafer fabrication plant. Robot Comput Integr Manuf 26:83–91

    Article  Google Scholar 

  • Chen T, Wang Y-C, Tsai H-R (2009) Lot cycle time prediction in a ramping-up semiconductor manufacturing factory with a SOM-FBPN-ensemble approach with multiple buckets and partial normalization. Int J Adv Manuf Technol 42(11–12):1206–1216

    Article  Google Scholar 

  • Cheng TCE, Gupta MC (1989) Survey of scheduling research involving due date determination decisions. Eur J Oper Res 38:156–166

    Article  Google Scholar 

  • Chien CF, Hsu CY, Hsiao CW (2012) Manufacturing intelligence to forecast and reduce semiconductor cycle time. J Intell Manuf 23(6):2281–2294

    Article  Google Scholar 

  • Dawson CW, Wilby RL (2001) Hydrological modelling using artificial neural networks. Prog Phys Geogr 25(1):80–108

    Article  Google Scholar 

  • Frontline Solvers (2015) Training an artificial neural network—intro. http://www.solver.com/training-artificial-neural-network-intro

  • Hans Raj K, Sharma RS, Srivastava S, Patvardhan C (2000) Modeling of manufacturing processes with ANNs for intelligent manufacturing. Int J Mach Tools Manuf 40(6):851–868

    Article  Google Scholar 

  • Hung YF, Leachman RC (1996) A production planning methodology for semiconductor manufacturing based on iterative simulation and linear programming calculation. IEEE Trans Semicond Manuf 9(2):257–269

    Article  Google Scholar 

  • Janssens GK, Sorensen K, Dullaert W (2009) An upper bound on the cycle time of a stochastic marked graph using incomplete information on the transition firing time distributions. Math Comput Model 49(3–4):563–572

    Article  Google Scholar 

  • Karlik B, Olgac AV (2011) Performance analysis of various activation functions in generalized MLP architectures of neural networks. Int J Artif Intell Expert Syst 1(4):111–122

    Google Scholar 

  • Lu SCH, Ramaswamy D, Kumar PR (1994) Efficient scheduling policies to reduce mean and variation of cycle time in semiconductor manufacturing plant. IEEE Trans Semicond Manuf 7:374–388

    Article  Google Scholar 

  • Oracle (2014) Available to Promise (ATP). http://docs.oracle.com/cd/A60725_05/html/comnls/us/mrp/atp.htm

  • Pearn WL, Chung SL, Lai CM (2007) Due-date assignment for wafer fabrication under demand variate environment. IEEE Trans Semicond Manuf 20(2):165–175

    Article  Google Scholar 

  • Sukthomya W, Tannock J (2005) The optimization of neural network parameters using Taguchi’s design of experiments approach: an application in manufacturing process modeling. Neural Comput Appl 14(4):337–344

    Article  Google Scholar 

  • Tai YT, Pearn WL, Lee JH (2012) Cycle time estimation for semiconductor final testing processes with Weibull-distributed waiting time. Int J Prod Res 50(2):581–592

    Article  Google Scholar 

  • Tesauro G (1995) Temporal difference learning and TD-Gammon. Commun ACM 38(3):58–68

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Toly Chen.

Appendix: A detailed comparison

Appendix: A detailed comparison

j

a j

l j (Chen and Lin’s method)

u j (Chen and Lin’s method)

l j (the proposed methodology)

u j (the proposed methodology)

1

1200

1063

1302

1156 (tighter)

1289 (tighter)

2

862

782 (tighter)

914 (tighter)

675

957

3

1320

1168

1426

1297 (tighter)

1405 (tighter)

4

766

715 (tighter)

807 (tighter)

591

874

5

1113

989

1209

1045 (tighter)

1204 (tighter)

6

1332

1183

1442

1316 (tighter)

1421 (tighter)

7

1559

1399

1666

1558 (tighter)

1650 (tighter)

8

1073

962

1173

1002 (tighter)

1173

9

987

881 (tighter)

1062 (tighter)

864

1077

10

1016

911

1104 (tighter)

918 (tighter)

1113

11

1493

1336

1604

1493 (tighter)

1585 (tighter)

12

1236

1094

1339

1198 (tighter)

1323 (tighter)

13

1552

1390

1657

1549 (tighter)

1640 (tighter)

14

1188

1049

1285

1135 (tighter)

1272 (tighter)

15

1269

1124

1375

1240 (tighter)

1357 (tighter)

16

1207

1067

1307

1161 (tighter)

1293 (tighter)

17

1246

1095

1341

1200 (tighter)

1324 (tighter)

18

1190

1065

1305

1159 (tighter)

1291 (tighter)

19

1460

1302

1569

1455 (tighter)

1549 (tighter)

20

1631

1461

1723

1617 (tighter)

1712 (tighter)

21

1054

948

1154 (tighter)

979 (tighter)

1156

22

1336

1194

1455

1330 (tighter)

1434 (tighter)

23

1176

1036

1268

1116 (tighter)

1257 (tighter)

24

1262

1115

1364

1227 (tighter)

1346 (tighter)

25

1529

1365

1633

1523 (tighter)

1615 (tighter)

26

966

869 (tighter)

1045 (tighter)

843

1063

27

1070

948

1155 (tighter)

980 (tighter)

1157

28

1344

1181

1440

1313 (tighter)

1419 (tighter)

29

901

816 (tighter)

966 (tighter)

742

999

30

1105

990

1209

1046 (tighter)

1205 (tighter)

31

1212

1076

1318

1173 (tighter)

1303 (tighter)

32

1313

1158

1414

1284 (tighter)

1394 (tighter)

33

1170

959

1170

998 (tighter)

1170

34

1811

1664

1897 (tighter)

1793 (tighter)

1911

35

908

821 (tighter)

975 (tighter)

754

1006

36

1081

954

1162 (tighter)

989 (tighter)

1163

37

1491

1324

1592

1479 (tighter)

1572 (tighter)

38

986

891 (tighter)

1076 (tighter)

882

1089

39

1287

1138

1391

1258 (tighter)

1372 (tighter)

40

1363

1204

1466

1342 (tighter)

1445 (tighter)

41

1216

1079

1321

1177 (tighter)

1306 (tighter)

42

1070

951

1159 (tighter)

985 (tighter)

1160

43

1307

1153

1408

1278 (tighter)

1389 (tighter)

44

1179

1043

1277

1126 (tighter)

1266 (tighter)

45

1148

1017

1245

1088 (tighter)

1236 (tighter)

46

1237

1098

1344

1204 (tighter)

1328 (tighter)

47

1555

1393

1659

1551 (tighter)

1643 (tighter)

48

861

791 (tighter)

929 (tighter)

694

969

49

1359

1208

1470

1347 (tighter)

1449 (tighter)

50

1500

1341

1609

1498 (tighter)

1590 (tighter)

51

1315

1161

1418

1288 (tighter)

1397 (tighter)

52

944

823 (tighter)

978 (tighter)

757

1008

53

1125

998

1220

1059 (tighter)

1214 (tighter)

54

1623

1461

1724

1618 (tighter)

1713 (tighter)

55

981

881 (tighter)

1062 (tighter)

865

1078

56

902

808 (tighter)

954 (tighter)

727

989

57

1095

976

1192

1024 (tighter)

1189 (tighter)

58

1317

1168

1426

1297 (tighter)

1405 (tighter)

59

1675

1515

1772

1668 (tighter)

1767 (tighter)

60

921

832 (tighter)

990 (tighter)

773

1018

61

1228

1087

1331

1189 (tighter)

1316 (tighter)

62

1194

1053

1290

1142 (tighter)

1278 (tighter)

63

1030

930

1130 (tighter)

949 (tighter)

1136

64

1163

1032

1263

1110 (tighter)

1253 (tighter)

65

1037

927

1126 (tighter)

944 (tighter)

1131

66

2169

2119 (tighter)

2215 (tighter)

2092

2319

67

994

894 (tighter)

1081 (tighter)

888

1093

68

1233

1096

1343

1202 (tighter)

1326 (tighter)

69

1228

1101

1348

1209 (tighter)

1332 (tighter)

70

1058

942

1146 (tighter)

969 (tighter)

1149

71

1704

1550

1803

1699 (tighter)

1801 (tighter)

72

1026

921

1118 (tighter)

935 (tighter)

1125

73

1438

1277

1544

1428 (tighter)

1523 (tighter)

74

882

882 (tighter)

1063 (tighter)

865

1078

75

1301

1151

1407

1276 (tighter)

1387 (tighter)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, T. Asymmetric cycle time bounding in semiconductor manufacturing: an efficient and effective back-propagation-network-based method. Oper Res Int J 16, 445–468 (2016). https://doi.org/10.1007/s12351-015-0208-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12351-015-0208-7

Keywords

Navigation