The FLR–PCFI–RBF approach for accurate and precise WIP level forecasting

Precise and accurate prediction of future level of work in process (WIP) is an important task for factory control. To this end, a fuzzy linear regression (FLR)–partial consensus fuzzy intersection (PCFI)–radial basis function network (RBF) approach is proposed in this study. In the proposed methodology, a virtual expert committee is formed, instead of calling a number of experts in the field. For each virtual expert, a corresponding FLR equation is constructed to predict the level of WIP. Each FLR equation can be fitted by solving two equivalent nonlinear programming problems, based on the opinions of virtual experts. In order to aggregate these fuzzy WIP level forecasts, a two-step aggregation mechanism is used. First, PCFI is applied to aggregate the fuzzy forecasts into a polygon-shaped fuzzy number, in order to improve precision. Then, an RBF is constructed to defuzzify the polygon-shaped fuzzy number, and generate a representative/crisp value, resulting in improved accuracy. To evaluate the effectiveness of the proposed methodology, an actual case is discussed. According to the experimental results, the proposed methodology improved the precision and accuracy of the WIP level forecasting by 68% and 27%, respectively.

[1]  Toly Chen,et al.  Lot cycle time prediction in a ramping-up semiconductor manufacturing factory with a SOM–FBPN-ensemble approach with multiple buckets and partial normalization , 2009 .

[2]  Toly Chen,et al.  A SOM-FBPN-ensemble approach with error feedback to adjust classification for wafer-lot completion time prediction , 2008 .

[3]  Robert Gatland,et al.  Simulating the effects of work-in-process on customer satisfaction in a manufacturing environment , 1995, WSC '95.

[4]  Toly Chen,et al.  Applying a Fuzzy and Neural Approach for Forecasting the Foreign Exchange Rate , 2011, Int. J. Fuzzy Syst. Appl..

[5]  Ronald R. Yager,et al.  On Possibilistic and Probabilistic Information Fusion , 2011, Int. J. Fuzzy Syst. Appl..

[6]  A. Bárdossy.  Note on fuzzy regression , 1990 .

[7]  Toly Chen,et al.  A Fuzzy-Neural System Incorporating Unequally Important Expert Opinions for semiconductor Yield Forecasting , 2008, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[8]  E. M. Voorhees.  A work-in-process tracking system for experimental manufacturing , 1989, Proceedings. Second International Conference on Data and Knowledge Systems for Manufacturing and Engineering.

[9]  T. Chen,et al.  A fuzzy-neural knowledge-based system for job completion time prediction and internal due date assignment in a wafer fabrication plant , 2009, Int. J. Syst. Sci..

[10]  Omar López-Ortega,et al.  Object-oriented optimal controller for a batch dryer system , 2012 .

[11]  Toly Chen,et al.  A Hybrid SOM-BPN Approach to Lot Output Time Prediction in a Wafer Fab , 2006, Neural Processing Letters.

[12]  Taho Yang,et al.  An evolutionary-simulation approach for the optimization of multi-constant work-in-process strategy--A case study , 2007 .

[13]  Toly Chen.  An online collaborative semiconductor yield forecasting system , 2009, Expert Syst. Appl..

[14]  Selwyn Piramuthu,et al.  Financial credit-risk evaluation with neural and neurofuzzy systems , 1999, Eur. J. Oper. Res..

[15]  Chih-Ming Liu,et al.  Standard WIP Determination and WIP Balance Control with Time Constraints in Semiconductor Wafer Fabrication , 2008 .

[16]  Erkan Besdok,et al.  A Comparison of RBF Neural Network Training Algorithms for Inertial Sensor Based Terrain Classification , 2009, Sensors.

[17]  Ali Azadeh,et al.  A unique fuzzy multi-criteria decision making: computer simulation approach for productive operators’ assignment in cellular manufacturing systems with uncertainty and vagueness , 2011 .

[18]  J. Little.  A Proof for the Queuing Formula: L = λW , 1961 .

[19]  Xinwang Liu,et al.  Parameterized defuzzification with maximum entropy weighting function - Another view of the weighting function expectation method , 2007, Math. Comput. Model..

[20]  Toly Chen,et al.  A bi-criteria nonlinear fluctuation smoothing rule incorporating the SOM–FBPN remaining cycle time estimator for scheduling a wafer fab—a simulation study , 2010 .

[21]  Toly Chen,et al.  Job cycle time estimation in a wafer fabrication factory with a bi-directional classifying fuzzy-neural approach , 2011 .

[22]  Toly Chen,et al.  A hybrid fuzzy and neural approach for forecasting the book-to-bill ratio in the semiconductor manufacturing industry , 2011 .

[23]  Toly Chen,et al.  A fuzzy-neural approach for estimating the monthly output of a semiconductor manufacturing factory , 2008 .

[24]  Shang Zhi,et al.  A proof of the queueing formula: L=λW , 2001 .

[25]  W. Fuller,et al.  LIKELIHOOD RATIO STATISTICS FOR AUTOREGRESSIVE TIME SERIES WITH A UNIT ROOT , 1981 .

[26]  Carlos Cordon.  Quality defaults and work-in-process inventory , 1995 .

[27]  Toly Chen,et al.  Incorporating fuzzy c-means and a back-propagation network ensemble to job completion time prediction in a semiconductor fabrication factory , 2007, Fuzzy Sets Syst..

[28]  Toly Chen,et al.  A hybrid neural network and selective allowance approach for internal due date assignment in a wafer fabrication plant , 2008 .

[29]  E. Hannan,et al.  Recursive estimation of mixed autoregressive-moving average order , 1982 .

[30]  Toly Chen,et al.  FUTURE WIP LEVEL FORECASTING IN A WAFER FABRICATION FACTORY WITH A HYBRID FUZZY AND NEURAL APPROACH , 2011 .