Manufacturing Intelligence to Exploit the Value of Production and Tool Data to Reduce Cycle Time
IEEE Transactions on Automation Science and EngineeringPublished 2 March 2010
Chung-Jen Kuo, Chen–Fu Chien, Jan-Daw Chen
Citations86
SJR quartileQ1
SJR score1.92
SNIP2.57
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A manufacturing intelligence (MI) approach based on neural networks (NNs) to exploit the value of the wealthy production data and tool data for predicting the WIP levels of the tool sets for cycle time reduction is proposed.
Abstract
Cycle time reduction is crucial for semiconductor wafer fabrication companies to maintain competitive advantages as the semiconductor industry is becoming more dynamic and changing faster. According to Little's Law, while maintaining the same throughput level, the reduction in Work-in-Process (WIP) will result in cycle time reduction. On one hand, the existing queueing models for predicting the WIP of tool sets in wafer fabrication facilities (fab) have limitations in real settings. On the other hand, little research has been done to predict the WIP of tool sets with tool dedication and waiting time constraint so as to control the corresponding WIP levels of various tool sets to reduce cycle time without affecting throughput. This study aims to fill the gap by proposing a manufacturing intelligence (MI) approach based on neural networks (NNs) to exploit the value of the wealthy production data and tool data for predicting the WIP levels of the tool sets for cycle time reduction. To validate this approach, empirical data were collected and analyzed in a leading semiconductor company. The comparison results have shown practical viability of this approach. Furthermore, the proposed approach can identify and improve the critical input factors for reducing the WIP to reduce cycle time in a fab.
Keywords
Engineering
Communications of the ACMThe KDD process for extracting useful knowledge from volumes of data
1,899 Citations1996Usama M. Fayyad, Gregory Piatetsky-Shapiro +1 more
A new generation of computational techniques and tools is required to support the extraction of useful knowledge from the rapidly growing volumes of data, the subject of the emerging field of knowledge discovery in databases (KDD) and data mining.
NeurocomputingFinancial time series forecasting using support vector machines
1,688 Citations2003Kyoung-jae Kim
The experimental results show that SVM provides a promising alternative to stock market prediction and the feasibility of applying SVM in financial forecasting is examined by comparing it with back-propagation neural networks and case-based reasoning.
Factory Physics : Foundations of Manufacturing Management
1,375 Citations1995Wallace J. Hopp, M Leroy Spearman
IIE TransactionsA REVIEW OF PRODUCTION PLANNING AND SCHEDULING MODELS IN THE SEMICONDUCTOR INDUSTRY PART I: SYSTEM CHARACTERISTICS, PERFORMANCE EVALUATION AND PRODUCTION PLANNING
596 Citations1992Reha Uzsoy, Chung‐Yee Lee +1 more
Journal of Chemical Information and Computer SciencesComparison of Support Vector Machine and Artificial Neural Network Systems for Drug/Nondrug Classification
561 Citations2003Evgeny Byvatov, Uli Fechner +2 more
Although SVM outperformed the ANN classifiers with regard to overall prediction accuracy, both methods were shown to complement each other, as the sets of true positives, false positives, true negatives, and false negatives produced by the two classifiers were not identical.
Computers & Operations ResearchNeural networks in business: techniques and applications for the operations researcher
288 Citations2000Kate Smith‐Miles, Jatinder N.D. Gupta
An overview of the different types of neural network models which are applicable when solving business problems is presented, as well as their historical and current use in business.
Expert Systems with ApplicationsData mining for yield enhancement in semiconductor manufacturing and an empirical study
283 Citations2006Chen–Fu Chien, Wen-Chih Wang +1 more
This study aims to develop a framework for data mining and knowledge discovery from database that consists of a Kruskal-Wallis test, K-means clustering, and the variance reduction splitting criterion to investigate the huge amount of semiconductor manufacturing data and infer possible causes of faults and manufacturing process variations.
International Journal of Production EconomicsHybrid data mining approach for pattern extraction from wafer bin map to improve yield in semiconductor manufacturing
188 Citations2006Shao-Chung Hsu, Chen–Fu Chien
This study proposes a hybrid data mining approach that integrates spatial statistics and adaptive resonance theory neural networks to quickly extract patterns from wafer bin maps and associate with manufacturing defects.
IEEE Transactions on Semiconductor ManufacturingA queueing network model for semiconductor manufacturing
151 Citations1996Daniel P. Connors, G. Feigin +1 more
IEEE Transactions on Automation Science and EngineeringQueueing Theory for Semiconductor Manufacturing Systems: A Survey and Open Problems
148 Citations2007J. George Shanthikumar, Shengwei Ding +1 more
This paper surveys applications of queueing theory for semiconductor manufacturing systems (SMSs), conducts a survey on the important works and proposes a novel solution by relaxing a key assumption in the classicalQueueing theory.
International Journal of Electronic FinanceComparison of support-vector machines and back propagation neural networks in forecasting the six major Asian stock markets
140 Citations2006Wun Hua Chen, Jen–Ying Shih +1 more
This research applies Support-Vector Machines and Back Propagation neural networks for six Asian stock markets and the experimental results showed the superiority of both models, compared to the early researches.
IEEE Transactions on Semiconductor ManufacturingCycle-time improvements for photolithography process in semiconductor manufacturing
135 Citations2001E. Akcalt, K. Nemoto +1 more
NeurocomputingRecurrent neural network for forecasting next 10 years loads of nine Japanese utilities
113 Citations1998B. Kermanshahi
Total system load forecast reflecting current and future trends, tempered with good judgement which is the key to all planning and indeed financial success is carried out for nine utilities in Japan.
IEEE Transactions on Semiconductor ManufacturingImplementation of modeling and simulation in semiconductor wafer fabrication with time constraints between wet etch and furnace operations
84 Citations2000Wolfgang Scholl, Joerg Domaschke
IEEE Transactions on Semiconductor ManufacturingUsing Rough Set Theory to Recruit and Retain High-Potential Talents for Semiconductor Manufacturing
83 Citations2007Chen–Fu Chien, Lifei Chen
An effective data mining approach based on Rough Set Theory to explore and analyze human resource data for personnel selection and human capital enhancement and concludes with discussions of empirical findings and future research directions.
OR SpectrumA novel timetabling algorithm for a furnace process for semiconductor fabrication with constrained waiting and frequency-based setups
79 Citations2006Chen–Fu Chien, Chien‐Hung Chen
A genetic algorithm for batch sequencing combined with a novel timetabling algorithm that optimally solves most cases of the ONO scheduling problem in real settings and significantly outperforms dispatching rule-based heuristics.
International Journal of Machine Tools and ManufactureSelecting an artificial neural network for efficient modeling and accurate simulation of the milling process
67 Citations2002Jorge F. Briceno, Hazim El-Mounayri +1 more
Two supervised neural networks are used to estimate the forces developed during milling and it is shown that the Radial Basis Network model is superior in this particular case.
Expert Systems with ApplicationsPrediction of vehicle reliability performance using artificial neural networks
65 Citations2007S. Lolas, Oluremi Olatunbosun
Computers & StructuresPrediction of wind-induced pressures on a large gymnasium roof using artificial neural networks
61 Citations2006Jiyang Fu, Shan Liang +1 more
International Journal of Production EconomicsProcess optimization via neural network metamodeling
61 Citations2002Mark A. Chambers, Clark A. Mount‐Campbell
The approach is to develop an artificial neural network (ANN) metamodel of components of the entire system rather than of the whole system, which is used to select the buffer sizes in front of each process that provide a desired mix of product throughput rates, while minimizing average system sojourn time.
IEEE Transactions on Automation Science and EngineeringPractical Extensions to Cycle Time Approximations for the $G/G/m$-Queue With Applications
54 Citations2007James R. Morrison, D.P. Martin
This paper extends popular approximate mean cycle time formulae to address practical manufacturing issues, and test the approximations using parameters gleaned from production tool groups in IBM's 200 mm semiconductor wafer fabricator.
International Journal of Production ResearchOptimal batching in a wafer fabrication facility using a multiproduct G/G/c model with batch processing
50 Citations2002John Fowler, Nipa Phojanamongkolkij +2 more
International Journal of Production ResearchThe construction of production performance prediction system for semiconductor manufacturing with artificial neural networks
45 Citations1999Chun-Wel Huang
This work systematically constructs artificial Neural network models to predict production performances for a semiconductor manufacturing factory and an application for a local DRAM wafer fabrication has demonstrated the accuracy of neural network models in predicting production performances.
European Journal of Operational ResearchA total standard WIP estimation method for wafer fabrication
39 Citations2001Yu‐Hsin Lin, Ching‐En Lee
Results of simulation experiment indicate that under the Fixed-WIP control policy, the total standard WIP level estimated from this study achieves a target throughput rate while keeping the corresponding cycle time relatively low, and demonstrate that the queueing network-based algorithm is a very useful method to determine the standard W IP level efficiently.
Microelectronic EngineeringModeling plasma etching process using a radial basis function network
28 Citations2004Byungwhan Kim, Kyungyoung Park
Expert Systems with ApplicationsUsing an artificial neural network prediction model to optimize work-in-process inventory level for wafer fabrication
26 Citations2008Yu‐Hsin Lin, Jie‐Ren Shie +1 more
This study focused on finding an optimal WIP value of wafer fabrication processes by developing an algorithm integrating an artificial neural network (ANN) and the sequential quadratic programming (SQP) method, which offered an effective and systematic way to identify an optimalWIP level.
Journal of the Chinese Institute of Industrial EngineersCONSTRUCTING SEMICONDUCTOR MANUFACTURING PERFORMANCE INDEXES AND APPLYING DATA MINING FOR MANUFACTURING DATA ANALYSIS
25 Citations2004Chen–Fu Chien, Allen Hsiao +1 more
This study reviews the related studies on semiconductor manufacturing management and develops a complete set of performance indexes in hierarchy, and applies data mining techniques for analyzing production data collected in a semiconductor fab in Taiwan to validate this approach.
International Journal of Production ResearchDispatching for make-to-order wafer fabs with machine-dedication and mask set-up characteristics
20 Citations2008Muh-Cherng Wu, Shau-Jie Chiou +1 more
Production Planning & ControlCapacity allocation model for photolithography workstation with the constraints of process window and machine dedication
18 Citations2006S. H. Chung, Chun‐Ying Huang +1 more
Journal of the Chinese Institute of Industrial EngineersCAPACITY DETERMINATION MODEL WITH TIME CONSTRAINTS AND BATCH PROCESSING IN SEMICONDUCTOR WAFER FABRICATION
11 Citations2006Ying-Mei Tu, Chuen-Shiuan Liou
This paper applied GI/G/m queuing theory to develop a capacity determination model for batch processing machines and demonstrates that it is superior to the current planning method.
Journal of the Chinese Institute of Industrial EngineersCapacity Determination Model with Time Constraints and Batch Processing in Semiconductor Wafer Fabrication
10 Citations2006Ying-Mei Tu, Chuen-Shiuan Liou
IEEE Transactions on Semiconductor ManufacturingOn-line learning delivery decision support system for highly product mixed semiconductor foundry
8 Citations2002Chih-Yuan Yu, Han‐Pang Huang
A production learning system (PLS) based on the tool model was constructed as a decision support and real-time information update system to forecast the cycle time and shows that the forecasting ability of the PLS has an error rate below 8% on average.