Browsing by Author "Su, CT"

Now showing 1 - 20 of 54

A comparison of search techniques for minimizing assembly time in printed wiring assembly
(2000-01-05)
Fu, HP
;
Su, CT
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
In the robotics assembly of DPP model, the coordinates of assembly point and magazine are dynamically changed during robotics assembly so that evaluation of the assembly efficiency is extremely complicated. To route the robotics travel, most related investigations have utilized the fixed coordinate of insertion points and magazine using the Traveling Salesman Problems (TSP) method to sequence the insertion points after arbitrarily assigning the magazine. However, robotics travel routing should be based on a relative coordinate to obtain a better solution because the robotics, board and magazine are simultaneously moved at different speeds during assembly. To resolve such a dynamically combinatorial problem, this study presents the Genetic Algorithm (GA), Simulated Annealing (SA), and Tabu Search (TS) based algorithms. These approaches can simultaneously arrange the insertion sequence and assign the magazine slots by the computer and yield a better performance compared to the conventional approach. Results presented herein also demonstrate that the larger the number of insertion points and/or part numbers the better the performance. These approaches are also compared. (C) 2000 Elsevier Science B.V. All rights reserved.
A manufacturer's optimal quantity discount strategy and return policy through game-theoretic approach
(2002-08-01)
Su, CT
;
Shi, CS
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
This study generalised the traditional quantity discount problem with return contracts, in which a manufacturer promises to refund some fraction of the retailer's wholesale price if an item is returned, as a two-stage game. In the first stage the manufacturer and retailer determine the inventory level cooperatively. In the second stage, the manufacturer bargains with the retailer for quantity discount and return schemes to maintain channel efficiency. A menu of discount-return combinations is proposed for the manufacturer to make inventory decisions. The model developed will demonstrate that the return policy can be considered as mirror images of quantity discount strategy. That is, options with more generous return privileges are coupled with higher wholesale prices, whereas the lowest wholesale price comes with very strict limits on returns and a restocking fee for any returned goods.
A neural network based information granulation approach to shorten the cellular phone test process
(2006-06-01)
Su, CT
;
Chen, LS
;
Chiang, TL
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
In the cellular phone OEM/ODM industry, reducing test time and cost are crucial due to fierce competition, short product life cycle, and a low margin environment. Among the inspection processes, the radio frequency (RF) function test process requires more operation time than any other. Hence, manufacturers need an effective method to reduce the RF test items so that the inspection time can be reduced while maintaining the quality of the RF function test. However, traditional feature selection methods such as neural networks and genetic algorithm lead to a high level of Type II error in the situation of imbalanced data where the amount of good products is far greater than the defective products. In this study, we propose a neural network based information granulation approach to reduce the RF test items for the finished goods inspection process of a cellular phone. Implementation results show that the RF test items were significantly reduced, and that the inspection accuracy remains very close to that of the original testing process. In addition, the Type II errors decreased as well. (C) 2006 Elsevier B.V. All rights reserved.
A neural network-based adaptive algorithm on the single EWMA controller
(2004-04-01)
Hsu, CC
;
Su, CT
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
The single EWMA controller has been proven to have excellent performance for small disturbances in the run-to-run process. However, incorrect selection of the EWMA parameter can have the opposite effect on the controlled process output. An adaptive system is necessary to automatically adjust the controller parameters on-line in order to have better performance. In this study, a simple and efficient algorithm based on neural networks (NN) is proposed to minimise the inflation of the output variance on line. The authors have shown that the sequence of EWMA gains, generated by a NN-based adaptive approach, converges close to the optimal controller value under IMA (1, 1), step and trend disturbance models. The paper also shows that the NN-based adaptive EWMA controller has a superior performance than its predecessors.
A neural network-based procedure for the process monitoring of clustered defects in integrated circuit fabrication
(1997-12-01)
Su, CT
;
Tong, LI
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
In integrated circuit (IC) fabrication, a wafer's defects tend to cluster. As the wafer size increases, the clustering phenomenon of the defects becomes increasingly apparent. When the conventional control chart (c chart) is used, the clustered defects frequently cause many false alarms. In this study, we propose a neural network-based procedure for the process monitoring of clustered defects in IC fabrication. The proposed procedure can reduce the phenomenon of the false alarms caused by the clustered defects. A case study is also presented to show the effectiveness of the proposed procedure. (C) 1997 Elsevier Science B.V.
A neural network-based procedure for the process monitoring of clustered defects in integrated circuit fabrication
(1997-12-01)
Su, CT
;
Tong, LI
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
In integrated circuit (IC) fabrication, a wafer's defects tend to cluster. As the wafer size increases, the clustering phenomenon of the defects becomes increasingly apparent. When the conventional control chart (c chart) is used, the clustered defects frequently cause many false alarms. In this study, we propose a neural network-based procedure for the process monitoring of clustered defects in IC fabrication. The proposed procedure can reduce the phenomenon of the false alarms caused by the clustered defects. A case study is also presented to show the effectiveness of the proposed procedure. (C) 1997 Elsevier Science B.V.
A neural-network approach for semiconductor wafer post-sawing inspection
(2002-05-01)
Su, CT
;
Yang, T
;
Ke, CM
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
Semiconductor wafer post-sawing requires full inspection to assure defect-free outgoing dies. A defect problem is usually identified through visual judgment by the aid of a scanning electron microscope. By this means, potential misjudgment may be introduced into the inspection process due to human fatigue. In addition, the full inspection process can incur significant personnel costs. This research proposed a neural-network approach for semiconductor wafer post-sawing inspection. Three types of neural networks: backpropagation, radial basis function network, and learning vector quantization, were proposed and tested. The inspection time by the proposed approach was less than one second per die, which is efficient enough for a practical application purpose. The pros and cons for the proposed methodology in comparison with two other inspection methods, visual inspection and feature extraction inspection, are discussed. Empirical results showed promise for the proposed approach to solve real-world applications. Finally, we proposed a neural-network-based automatic inspection system framework as future research opportunities.
A novel approach for optimizing the optical performance of the broadband tap coupler
(2003-02-20)
Hsu, CM
;
Su, CT
;
Liao, D
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
An integrated approach using neural networks, exponential desirability functions and genetic algorithms to optimize parameter design problems with multiple responses is presented. The proposed approach aims to identify the input parameter settings to maximize the overall minimal satisfaction level with respect to all the responses. The proposed approach is illustrated by optimizing the fused process parameters created during fused biconic taper coupler development to improve the performance and reliability of a 1% (1/99) single-window broadband tap coupler. The proposed solution procedure was implemented on a Taiwanese manufacturer of fibreoptic passive components. The implementation results demonstrate the practicability of the method. Comparison analysis revealed that the proposed procedure outperformed the traditional Taguchi method in resolving multi-response parameter design problems.
A production inventory model which considers the dependence of production rate on demand and inventory level
(2001-01-01)
Su, CT
;
Lin, CW
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
This study presents a production inventory model for deteriorating products in which the production rate at any instant depends on the demand and the inventory level. While the demand rate is assumed to decrease exponentially, shortages are allowed and excess demand is backlogged as well. Optimal expressions are obtained for the production scheduling period, maximum inventory level, unfilled order backlog and the total average cost. Some cases of the model are briefly discussed. A numerical example illustrates the practicality of the model. The sensitivity of these solutions to changes in underlying parameter values is also discussed.
A simulated annealing heuristic for robotics assembly using the dynamic pick-and-place model
(1998-12-01)
Su, CT
;
Fu, HP
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
Products assembled by robots are typical in present day manufacturing. The traditional type of automatic assembly is Fixed Picked and Place (FPP) mode. The development of the Dynamic Picked-and-Place (DPP) model is an important issue in robotics travel. Until now, to route robotics travel, the authors usually have utilized the fixed coordinate of insertion points and magazine of the Travelling Salesman Problems (TSP) method to sequence the insertion points. However, robotics travel routing should be based on a relative coordinate because the coordinates of insertion point and magazine are constantly changing. That is, the robotics, board and magazine are simultaneously moved at different speeds. This study presents a Simulated Annealing (SA)-based algorithm that can arrange the insertion sequence and assign the magazine slots to obtain a performance better than in the traditional approach.
A time-varying weights tuning method of the double EWMA controller
(2004-12-01)
Su, CT
;
Hsu, CC
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
In recent years, the exponential-weighted-moving-average (EWMA) statistic based controllers are popular in semiconductor manufacturing. However, the single EWMA controller is not sufficient for compensating for the wear-out process. Thus, a double EWMA controller was proposed to enhance the capability for controlling the drifting process. In the literatures, in the solution of the double EWMA controller, only the "trade-off" solution weights are used to tune the controller. However, it is a fixed weight tuning method, and it is known that a time-varying weight will produce a superior performance over that of a fixed one (J. Quality Technol. 29 (1997) 184). Therefore, this study aims to develop a heuristic time-varying weights tuning method for the double EWMA controller. The numerical results showed that the proposed time-varying tuning method possesses an improvement of least 10% over that of the fixed weight scheme. (C) 2004 Elsevier Ltd. All rights reserved.
An activity-based predicate/transition net model of operational control planning for a flexible manufacturing system
(2004-04-01)
Hsu, HP
;
Chen, JY
;
Su, CT
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
An effective flexible manufacturing system (FMS) relies on a hierarchy of decisions, including the control of the FMS operation. The FMS operation usually is dynamically constrained by the limited resources such as pallets, machines, tools, carts, etc. Most analytical models make many assumptions and oversimplify the complicated decision problems. This study proposes the predicate/transition (Pr/Tr) net, a high level petri net, as a model for operational control planning. Firstly, the activities (modes) and their resources usage in FMS were analysed and aggregated into activity sets. Then, the flow of parts among activities was traced to obtain the "mode transition diagram", and then the Pr/Tr net model was introduced. We incrementally defined the predicates and transitions into this model. Finally, a comprehensive FMS Pr/Tr net model was derived. By implementing it into a rule-based simulation model, it is well suited for FMS operational control planning because of its inclusiveness and high flexibility.
An empirical study of the Taiwan National Quality Award causal model
(2003-10-01)
Su, CT
;
Li, SC
;
Su, CH
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
In this study, the Taiwan National Quality Award (TNQA) is discussed in terms of a modelling approach for the first time since it was founded in 1990. A survey instrument involving 105 questions extracted from the 2001 TNQA criteria serves to measure the content of the TNQA. A causal model is proposed to reveal the relationships among TNQA categories. Structural equation modelling (SEM) is used to analyse the model and estimate path coefficients among TNQA categories. The statistical results show that many of the hypothesized causal relationships in the TNQA model are statistically significant. From path coefficients, the category of Leadership has a strong influence on that of Information Management. Simultaneously, Information Management has impacts on other TNQA system categories. Information Management is confirmed as an internal driver of TNQA system categories. Both Leadership and Innovation and Strategic Management show direct influence on Business Results. Generally, several conclusions are made as follows. First, the assumption that the TNQA model is recursive is supported by statistical results. Secondly, the prior theory of this causal model that Leadership is a driver of the system, which creates results is confirmed. Thirdly, the final causal model also represents an excellent model of business performance, which can predict expected results through system paths. Other conclusions and findings are discussed in the study.
An enhanced knowledge representation for decision-tree based learning adaptive scheduling
(2003-01-01)
Shiue, YR
;
Su, CT
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
The classical decision tree (DT) learning approach to constructing DT knowledge bases is usually not considered if there exist some irrelevant and redundant attributes in the problem domain. Since the essential attributes are uncertain in manufacturing systems, how to select important manufacturing attributes to improve the generalization ability of knowledge bases and avoid overfitting training data in DT-based learning is a crucial research issue for the adaptive scheduling problem domain. In this study, we will first develop an attribute selection algorithm based on the weights of artificial neural networks (ANNs) to identify the importance of system attributes. Next, we will use the C4.5 DT learning algorithm to learn the whole set of training examples with important attributes in order to enhance knowledge representation. This hybrid ANN/DT approach is called an attribute selection DT (ASDT) based learning adaptive scheduling system. The results from the case study show that the use of an attribute selection algorithm to build scheduling knowledge bases delivers better generalization ability than in the absence of the attribute selection procedure in terms of the size of DTs under various performance criteria. Consistent conclusions are drawn from the resulting prediction accuracy of unseen data. The resulting prediction accuracy of unseen data also reveals that scheduling knowledge bases by the proposed attribute selection approach to constructing DTs can avoid overfitting the training data compared with the classical DT learning approach.
An extended Chi2 algorithm for discretization of real value attributes
(2005-03-01)
Su, CT
;
Hsu, JH
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
The Variable Precision Rough Sets (VPRS) model is a powerful tool for data mining, as it has been widely applied to acquire knowledge. Despite its diverse applications in many domains, the VPRS model unfortunately cannot be applied to real-world classification tasks involving continuous attributes. This requires a discretization method to preprocess the data. Discretization is an effective technique to deal with continuous attributes for data mining, especially for the classification problem. The modified Chi2 algorithm is one of the modifications to the Chi2 algorithm, replacing the inconsistency check in the Chi2 algorithm by using the quality of approximation, coined from the Rough Sets Theory (RST), in which it takes into account the effect of degrees of freedom. However, the classification with a controlled degree of uncertainty, or a misclassification error, is outside the realm of RST. This algorithm also ignores the effect of variance in the two merged intervals. In this study, we propose a new algorithm, named the extended Chi2 algorithm, to overcome these two drawbacks. By running the software of See5, our proposed algorithm possesses a better performance than the original and modified Chi2 algorithms.
An inventory model with deteriorating items under inflation when a delay in payment is permissible
(2000-01-15)
Liao, HC
;
Tsai, CH
;
Su, CT
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
This study develops an inventory model for initial-stock-dependent consumption rate when a delay in payment is permissible. In the inventory model, shortages are not allowed. The effect of the inflation rate, deterioration rate, initial-stock-dependent consumption rate and delay in payment are discussed. In the study, mathematical models are also derived under two different circumstances, i.e., Case I: The credit period is less than or equal to the cycle time for settling the account; and Case II: The credit period is greater than the cycle time for settling the account. Besides, expressions for an inventory system's total cost are derived for these two cases. Moreover, a computational procedure and GINO (Lasdon et al., ACM Transactions Mathematical Software 4 (1978) 34-50) are proposed to obtain the optimal order size and cycle time. The results can help managers determine the optimal total cost. Finally, a numerical example demonstrates the applicability of the proposed model. (C) 2000 Elsevier Science B.V. All rights reserved.
An optimal yield mapping approach for the small and medium sized liquid crystal displays
(2006-02-01)
Wang, PS
;
Su, CT
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
The ability to improve yield in the manufacturing process is an important competitiveness determinant for LCD factories. The TFT-LCD contains three major manufacturing sectors: the array, cell, and module assembly processes. The yield loss from the cell process is one of the most critical steps. To increase the cell process yield, more conforming LCD panels must be produced from one glass substrate. The sorter is a robot used in LCD manufacturing systems to achieve higher yield for matching TFT and CF plates. This sorter contains several ports that can transfer CF glasses from CF cassettes to match TFT glasses. In this paper, the Hungarian method is applied to solve the yield-mapping problem with the sorter. This method provides an optimal solution to improve the cell process yield.
Applying robust multi-response quality engineering for parameter selection using a novel neural-genetic algorithm
(2003-01-01)
Li, TS
;
Su, CT
;
Chiang, TL
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
This study presents a neural-genetic algorithm to solve the selection problem of manufacturing process parameters. The proposed algorithm is a combination of artificial neural network (ANN) and genetic algorithms (GAs). In addition, the neural network is used to formulate a fitness function for predicting the value of the response based on the parameter settings. GAs then take the fitness function from the trained neural network to search for the optimal parameter combination. Owing to the most of manufactured products have more than one quality characteristic and the quality characteristics are generally correlated with each other, this study also proposes a desirability function to obtain a compromise, composite solution. A case study of how the silicon manufacturing process parameters are selected offline demonstrates the effectiveness of the proposed approach. (C) 2002 Elsevier Science B.V. All rights reserved.
Attribute selection for neural network-based adaptive scheduling systems in flexible manufacturing systems
(2002)
Shiue, YR
;
Su, CT
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
System attribute selection is an integral part of adaptive scheduling systems. Owing to the existence of irrelevant and redundant attributes in manufacturing systems, by selecting the important attributes, better performance or accuracy in prediction can be expected in scheduling knowledge bases. In this study, we first propose an attribute selection algorithm based on the weights of neural networks to measure the importance Of system attributes in a neural network-based adaptive scheduling (NNAS) system. Next, the NNAS system is combined with the attribute selection algorithm to build scheduling knowledge bases. This hybrid approach is called an attribute selection neural network-based adaptive scheduling (ASNNAS) system. The experimental results show that the proposed ASNNAS system works very well, when measured by a variety of performance criteria, as opposed to the traditional NNAS system and a single dispatching strategy. Furthermore, the scheduling knowledge bases in the ASNNAS system can provide a stronger generalisation ability compared with NNAS systems under various performance criteria.
Computer-aided optimization of multi-pass turning operations for continuous forms on CNC lathes
(1999-06-01)
Su, CT
;
Chen, MC
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
The Computer Numerical Control (CNC) machine is one of the most effective production facilities used in manufacturing industry. Determining the optimal machining parameters is essential in the machining process planning since the machining parameters significantly affect production cost and quality of machined parts. Previous studies involving machining optimization of turning operations concentrated primarily on developing machining models for bar components. Machined parts on the CNC lathes, however, typically have continuous forms. In this study, we formulate an optimization model for turned parts with continuous forms. Also, a stochastic optimization method based on the simulated annealing algorithm and the pattern search is applied to solve this machining optimization problem. Finally, the applications of the developed machining model and the proposed optimization algorithm are established through the numerical examples.