臺灣博碩士論文加值系統

Although numerous attempts have been made on the study of predictive maintenance, little is known about to develop a predictive model that can detect the failure for the machines that run at different conditions.
One of the major reasons is that a machine’s failure mode strongly depends on the customer’s machine parameter setting. Some customers run machine at tight specifications while others run different specifications for their operation of purposes. It is difficult to develop a golden predictive model that can applicable for all machines the run under different condition settings.
Moreover, the ‘failure data’ for model building is unexplained or difficult to acquire. The poor quality of ‘failure data’ will increase the difficulty of analysis on the predictive model, and could lead to wrong decision.
A new un-supervised modeling approach - Trend Attribute Extraction based Predictive Modeling (TAE-PM) is proposed to detect the potential machine failures. Compared with traditional predictive maintenance modeling, the presented methodology shows its adaptability and effectiveness to a gradually deteriorating system.

Although numerous attempts have been made on the study of predictive maintenance, little is known about to develop a predictive model that can detect the failure for the machines that run at different conditions.
One of the major reasons is that a machine’s failure mode strongly depends on the customer’s machine parameter setting. Some customers run machine at tight specifications while others run different specifications for their operation of purposes. It is difficult to develop a golden predictive model that can applicable for all machines the run under different condition settings.
Moreover, the ‘failure data’ for model building is unexplained or difficult to acquire. The poor quality of ‘failure data’ will increase the difficulty of analysis on the predictive model, and could lead to wrong decision.
A new un-supervised modeling approach - Trend Attribute Extraction based Predictive Modeling (TAE-PM) is proposed to detect the potential machine failures. Compared with traditional predictive maintenance modeling, the presented methodology shows its adaptability and effectiveness to a gradually deteriorating system.

ABSTRACT II
ACKNOWLEDGEMENT III
TABLE OF CONTENTS IV
LIST OF FIGURES V
LIST OF TABLES V
1 INTRODUCTION 1
1.1 LITHOGRAPHY SYSTEM BACKGROUND 1
1.2 THE CHALLENGES OF PREDICTIVE MAINTENANCE 2
1.3 MOTIVATION AND GOALS 4
2 LITERATURE REVIEW 6
2.1 PREDICTIVE MAINTENANCE REVIEW 6
2.2 TREND ANALYSIS REVIEW 7
2.3 SEMICONDUCTOR EQUIPMENT PERFORMANCE MEASUREMENT 9
2.3.1 RELIABILITY 10
2.3.2 AVAILABILITY 10
3 TREND ATTRIBUTE EXTRACTION BASED PREDICTIVE MODELING (TAE-PM) 11
3.1 CONCEPT OF METHODOLOGY 11
3.2 RESEARCH FRAMEWORK 12
3.3 MODELING PREPARATION 13
3.3.1 THE DATA SOURCE 13
3.3.2 DATA COLLECTION AND PREPROCESS 14
3.4 TREND ANALYSIS MODELING 15
3.5 MODEL VALIDATION AND EXECUTION 19
4 EVALUATION – THE CASE STUDY 20
4.1 TREND MODELING CASE STUDY 21
4.2 MODEL VALIDATION – HISTORICAL DATA 27
4.3 MODEL DEPLOYMENT 29
4.4 MODEL VALIDATION – REAL CASE 30
5 CONCLUSION 33

Reference
Agami, N. (2008). A neural network based dynamic forecasting model for Trend Impact Analysis. Technological Forecasting and Social Change, Volume 76, Issue 7, September 2009, Pages 952-962.
Agami, N. M. (2008). An enhanced approach for Trend Impact Analysis. Technological Forecasting and Social Change, Volume 75, Issue 9, November 2008, Pages 1439-1450.
Callan, R. (2010). An Integrated Approach to the Development of an Intelligent Prognostic Health Management System. Aerospace Conference.
Cao, K. (2007). A trend pattern assessment approach to microarray gene expression profiling data analysis. Pattern Recognition Letters,, Volume 28, Issue 12, 1 September 2007, Pages 1472-1482.
Charbonnier, S. (2007). A trend-based alarm system to improve patient monitoring in intensive care units. Control Engineering Practice, Volume 15, Issue 9, September 2007, Pages 1039-1050.
Charbonniera, S. (2012). A self-tuning adaptive trend extraction method for process monitoring and diagnosis. Journal of Process Control, Volume 22, Issue 6, July 2012, Pages 1127-1138.
Chen, C. (2011). Machine remaining useful life prediction: An integrated adaptive neuro-fuzzy and high-order particle filtering approach. Mechanical Systems and Signal Processing, Volume 28, April 2012, Pages 597-607.
Costa, C. A. (2011). A multi-criteria model for auditing a Predictive Maintenance Programme. European Journal of Operational Research, Volume 217, Issue 2, 1 March 2012, Pages 381-393.
Fasulo, D. (1999). An alalysis of Recent Work on Clustering Algorithms.
Flores-Colen, I. (2010). A systematic approach for maintenance budgeting of buildings façades based on predictive and preventive strategies. Construction and Building Materials, Volume 24, Issue 9, September 2010, Pages 1718-1729.
ILANGO, M. (2010). A Survey of Grid Based Clustering Algorithms. Computers &; Geosciences, Volume 49, December 2012, Pages 140-150.
Janusz, M. (1911). Automatic generation of qualitative description of process trends for fault detection and diagnosis. Engineering Applications of Artificial Intelligence, Volume 4, Issue 5, 1991, Pages 329-339.
Mack, C. (n.d.). LITHOGRAPHY. Retrieved from LITHOGRAPHY: http://www.lithoguru.com/scientist/lithobasics.html
Magro, M. C. (2009). A confirmation technique for predictive maintenance using the Rough Set Theory. Computers &; Industrial Engineering, Volume 56, Issue 4, May 2009, Pages 1319-1327.
Mahamada, A. K. (2010). Predicting remaining useful life of rotating machinery based artificial neural network. Computers &; Mathematics with Applications, Volume 60, Issue 4, August 2010, Pages 1078-1087.
Maurya, M. R. (2007). Fault diagnosis using dynamic trend analysis: A review and recent developments. Engineering Applications of Artificial Intelligence, Volume 20, Issue 2, March 2007, Pages 133-146.
Philip, N. S. (2003). A neural network tool for analyzing trends in rainfall. Computers &; Geosciences, Volume 29, Issue 2, March 2003, Pages 215-223.
Quinlan, R. (1993). Current status of machine prognostic in condition-based maintenance . Elsevier.
RamMaurya, M. (2010). A frame work for on-line trend extraction and faultdiagnosis.
Sa´ez, J. A. (2013). Predicting noise filtering efficacy with data complexity measures for nearest neighbor classification. Pattern Recognition, Volume 46, Issue 1, January 2013, Pages 355-364.
Semiconductor equipment sales leaders by year. (n.d.). Retrieved from WKIPEDIA: http://en.wikipedia.org/wiki/Semiconductor_equipment_sales_leaders_by_year
Seyma, G. (2011). Development of a Condition Based Maintenance Decision Model by Data Mining.
Si, X.-S. (2013). Remaining useful life estimation – A review on the statistical data driven approaches. European Journal of Operational Research, Volume 213, Issue 1, 16 August 2011, Pages 1-14.
Tabari, H. (2011). Analysis of trends in temperature data in arid and semi-arid regions of Iran. Global and Planetary Change, Volume 79, Issues 1–2, October–November 2011, Pages 1-10.
Tabaria, H. (2010). Trend analysis of reference evapotranspiration in the western half of Iran. Agricultural and Forest Meteorology, Volume 151, Issue 2, 15 February 2011, Pages 128-136.
Tan, C. M. (2008). A framework to practical predictive maintenance modeling for multi-state systems. Reliability Engineering &; System Safety, Volume 93, Issue 8, August 2008, Pages 1138-1150.
Tian, Z. (2009). A neuralnetwork approach for remaining useful life prediction utilizing both failure and suspension histories.
Tsai, H.-H. (2012). Global data mining: An empirical study of current trends, future forecasts and technology diffusions.
TungTran, V. (2012). Machin eperformance degradation assessment and remaining useful life prediction using proportion al hazard model and support vector machine.
Vismara, M. (2012). An Integrated Approach to a Condition Based Maintenance policy and applications.
Wang, Q. (2012). Research and application of risk and condition based maintenance task optimization technology in an oil transfer station. Journal of Loss Prevention in the Process Industries, Volume 25, Issue 6, November 2012, Pages 1018-1027.
Wua, F.-S. (2011). A systematic approach for integrated trend analysis—The case of etching. Technological Forecasting and Social Change, Volume 78, Issue 3, March 2011, Pages 386-407.
Yang, P. (2010). Finding key attribute subset in dataset for outlier detection. Knowledge-Based Systems, Volume 24, Issue 2, March 2011, Pages 269-274.
Zhao, Z. (2010). Predictive maintenance policy based on process data. Chemometrics and Intelligent Laboratory Systems, Volume 103, Issue 2, 15 October 2010, Pages 137-143.