Case: Using remote monitoring data for condition-based
maintenance
Geert-Jan van HoutumProf. of Reliability and Maintenance
SCTL workshop, Helsinki, 8 July 2014
PAGE 28-Sept-2013/ School of Industrial Engineering
Case company: ASML
• Produces lithography machines for semiconductor industry
• All new machines are under service contracts with system availability constraints
• High targets for system availability (because of high downtime costs for semiconductor factories)
/ School of Industrial Engineering PAGE 38-Sept-2013
Service Network
Supply spare parts
Central Stockpoint
LocalStockpoint
Customers with contracts
Reg. repl.:1-2 weeks
Emergency Shipm.: 1-2 days
Reg. repl.:1-2 weeks
LocalStockpoint
Lateral Shipments: A few hours
Customers with contracts
Direct sales
Central level:Collection of many parameters
/ School of Industrial Engineering PAGE 48-Sept-2013
Monitoring data
• Condition data: parameters which are directly or indirectly related with the health state of Module X
• Failure data: failure time
Sample Data: Collected at central level, for one critical unit
MACHINE NUMBER
TIME STAMP VALUE
MACHINE TYPE
SITE ID
CUSTOMER CONTINENT
CUSTOMER COUNTRY
CUSTOMER NUMBER
PARAM ID
M1297 17-Dec-09 -8.856 T0010 1288 Asia South Korea 188 3756M2572 22-Oct-09 -8.9597 T0005 665 Asia Singapore 2046 990M2488 30-Jul-09 -3.9977 T0083 755 Other Other OT01 981
M0822 14-Jul-09 -4.0141 T0016 1284 Asia South Korea 188 960
M1621 08-May-09 -3.8854 T0010 1294 Asia South Korea 1146 957
M1647 23-Oct-09 -3.9167 T0001 277North America USA 196 966
M0003 21-Jul-09 -3.873 T0010 1291 Asia South Korea 188 990
M0004 21-Feb-09 -3.8264 T0010 1291 Asia South Korea 188 966M2862 27-Aug-09 -3.7398 T0004 629 Asia Taiwan 222 993M2631 06-Jan-09 -8.551 T0004 801 Europe France 192 972
M1141 10-Aug-09 -6.8885 T0011 1290 Asia South Korea 1146 966M3241 22-Apr-09 -8.551 T0010 629 Asia Taiwan 222 963M0051 05-Sep-09 -8.9597 T0008 1178 Asia Taiwan 386 996M1171 28-Feb-09 -3.9977 T0006 629 Asia Taiwan 222 987M1171 12-Aug-09 -6.8885 T0006 629 Asia Taiwan 222 990
M1614 04-Dec-09 -8.551 T0007 1284 Asia South Korea 188 990
M1951 16-Jul-09 -8.9597 T0019 1286 Asia South Korea 188 960
M2785 05-Jul-09 -3.9977 T0010 1291 Asia South Korea 188 996
Aligned data
MACHINE NUMBER
TIMESTAMPMACHINE
TYPECUSTOMER
IDP955 P956 P957 P958 P959 P960 P961
M0005 07-Jan-09 T0007 C1058 -6.8961 -6.8860 -6.8910 -6.9177 -6.8542 -6.8860 -3.7979
M0005 13-Feb-09 T0007 C1058 -7.3892 -7.3831 -7.3862 -7.4487 -7.3123 -7.3805 -4.3121
M0005 16-Feb-09 T0007 C1058 -7.4847 -7.4738 -7.4792 -7.5021 -7.4451 -7.4736 -4.3567
M0005 17-Feb-09 T0007 C1058 -7.5400 -7.5320 -7.5360 -7.5974 -7.4640 -7.5307 -4.3823
M0005 19-Feb-09 T0007 C1058 -7.5305 -7.5201 -7.5253 -7.5479 -7.4915 -7.5197 -4.3793
M0005 01-Mar-09 T0007 C1058 -7.6871 -7.6767 -7.6819 -7.7032 -7.6489 -7.6761 -4.5276
M0005 07-Mar-09 T0007 C1058 -7.7783 -7.7686 -7.7734 -7.7954 -7.7414 -7.7684 -4.6072
M0005 10-Mar-09 T0007 C1058 -7.7222 -7.7109 -7.7165 -7.7396 -7.6819 -7.7107 -4.6219
M0005 06-Apr-09 T0007 C1058 -8.0890 -8.0804 -8.0847 -8.1049 -8.0527 -8.0788 -4.9698
M0006 06-Apr-09 T0007 C1058 -7.9700 -7.9602 -7.9651 -7.9858 -7.9337 -7.9597 -4.9725
M0006 22-Apr-09 T0007 C1058 -8.1674 -8.1635 -8.1654 -8.2214 -8.0994 -8.1604 -5.1675
M0006 01-Jun-09 T0007 C1058 -8.5568 -8.5504 -8.5536 -8.5730 -8.5239 -8.5484 -5.6113
M0006 09-Jun-09 T0007 C1058 -8.5599 -8.5553 -8.5576 -8.6090 -8.4949 -8.5519 -5.6860
M0006 22-Jul-09 T0007 C1058 -8.7384 -8.7350 -8.7367 -8.7869 -8.6755 -8.7312 -6.2033
M0006 24-Jul-09 T0007 C1058 -8.8330 -8.8257 -8.8293 -8.8461 -8.8004 -8.8232 -6.1697
M0006 14-Aug-09 T0007 C1058 -8.9163 -8.9142 -8.9153 -8.9639 -8.8553 -8.9096 -6.3815
M0006 14-Aug-09 T0007 C1058 -8.9392 -8.9371 -8.9381 -8.9871 -8.8776 -8.9323 -6.3531
M0006 16-Aug-09 T0007 C1058 -8.8599 -8.8574 -8.8586 -8.9078 -8.7988 -8.8533 -6.4169
8-Sept-2013/ School of Industrial Engineering PAGE 5
Coupling with failure data
Failure Instant
STRONG CORRELATION BETWEEN FAILURE AND CONDITION DATA
8-Sept-2013/ School of Industrial Engineering PAGE 6
/ School of Industrial Engineering PAGE 78-Sept-2013
• A prediction method has been developed that predicts 70% of the failures
• No false predictions• Timing of the failure can be predicted a few
weeks in advance. • Method outperformed the prediction model
based on physical behavior
Results
/ School of Industrial Engineering PAGE 88-Sept-2013
• Improvement of the physical model• Development of prediction models for other
components• Possible use of the predictions for maintenance
optimization• Pure statistical predictions may be used for spare
parts supply
Barrier: Many departments involved!
Next steps