The Experts below are selected from a list of 891 Experts worldwide ranked by ideXlab platform
Tae-sun Yu - One of the best experts on this subject based on the ideXlab platform.
-
Adaptive Scheduling of Cluster Tools With Wafer Delay Constraints and Process Time Variation
IEEE Transactions on Automation Science and Engineering, 2019Co-Authors: Tae-sun YuAbstract:A cluster tool consists of several single-Wafer processing chambers and a Wafer-handling robot. Cluster tools are widely used for Wafer fabrication in semiconductor manufacturing fabs. As the circuit width shrinks down to below 20 or even several nanometers, Wafer waiting within a chamber after processing becomes more critical to Wafer Quality due to residual gases and heat. Conventional tool scheduling rules, such as the swap sequence and the backward sequence, may not satisfy strict upper limits on Wafer delays, especially when process times fluctuate randomly. We examine a scheduling problem for cluster tools with strict upper limits on Wafer delays under process time variation. We propose a new class of schedules, which not only keeps timing patterns steady as possible but also adapts timing of tasks in response to process time variation so as to satisfy Wafer delay constraints robustly. We also derive conditions for which there exists such a schedule. We develop a mixed-integer programming model to find an optimal schedule among such adaptive schedules. By numerical experiments, we show that the proposed scheduling method can effectively cope with tight Wafer delay constraints even under large process time variations. Note to Practitioners —As the circuit widths shrink down, residual gases and particles within chambers after processing Wafers become more critical to Wafer Quality. In fact, leading fabs are now cleaning a chamber for each new Wafer in order to reduce such Quality risk. We propose a new practical method for scheduling tools that can significantly reduce such Quality risk caused by Wafer waiting within chambers after processing.
-
Wafer delay analysis and control of dual-armed cluster tools with chamber cleaning operations
International Journal of Production Research, 2019Co-Authors: Tae-sun YuAbstract:As the design of integrated circuits has become increasingly complicated and dense, serious Wafer Quality problems are observed in modern Wafer fabrication facilities. Therefore, in cluster tools o...
-
Minimization of Waiting Time Variation in a Generalized Two-Machine Flowshop With Waiting Time Constraints and Skipping Jobs
IEEE Transactions on Semiconductor Manufacturing, 2017Co-Authors: Tae-sun YuAbstract:Wafer Quality issues are becoming essential concerns in semiconductor manufacturing industry. It is becoming increasingly important for fab managers to raise the Wafer Quality level. Quality variation across Wafers and Wafer lots is also recognized as of vital importance. Wafer waiting times, which occur between consecutive Wafer processing steps, are critical for the Quality and Quality variation of Wafers. To resolve these Quality issues, we consider waiting time constraints and variation in a flowshop. To follow the actual operating features of the fab, we define a two-machine flowshop with jobs that can skip the first process step and are ready to enter the second step from the beginning of scheduling. This research thus examines a machine scheduling problem that minimizes the variation in job waiting times in a generalized two-machine flowshop with skipping jobs and waiting time constraints. The mathematical properties of the problem such as the dominance properties and feasibility conditions are vigorously analyzed. These analyses provide profound insights into reduction of the search space in the solution procedure. We also observe that the derived properties are intuitively consistent with the well-known principles of queueing theory. From these, we develop efficient approximation algorithms and present their computational performance.
-
Winter Simulation Conference - Two-stage lot scheduling with waiting time constraints and due dates
2013 Winter Simulations Conference (WSC), 2013Co-Authors: Tae-sun Yu, Chanhwi JungAbstract:We examine a two-stage lot scheduling problem with waiting time constraints and distinct due dates. Wafer lots in diffusion or etch processes generally have due dates specified for each process stage. Some lots even have more strict time constraints that their waiting times between two or multiple stages should not exceed specified limits. We also wish to minimize the variation of the waiting times at the intermediate buffer, which is detrimental to Wafer Quality variability. To solve such a scheduling problem, we develop a mixed integer programming model for small problems. Also, we suggest an efficient solution procedure for large problems by adopting the earliest due date policy and propose a timing control strategy.
-
Two-stage lot scheduling with waiting time constraints and due dates
2013 Winter Simulations Conference (WSC), 2013Co-Authors: Tae-sun Yu, Chanhwi JungAbstract:We examine a two-stage lot scheduling problem with waiting time constraints and distinct due dates. Wafer lots in diffusion or etch processes generally have due dates specified for each process stage. Some lots even have more strict time constraints that their waiting times between two or multiple stages should not exceed specified limits. We also wish to minimize the variation of the waiting times at the intermediate buffer, which is detrimental to Wafer Quality variability. To solve such a scheduling problem, we develop a mixed integer programming model for small problems. Also, we suggest an efficient solution procedure for large problems by adopting the earliest due date policy and propose a timing control strategy.
Kuang Ku Chen - One of the best experts on this subject based on the ideXlab platform.
-
integrating support vector machine and genetic algorithm to implement dynamic Wafer Quality prediction system
Expert Systems With Applications, 2010Co-Authors: Pao Hua Chou, Menq Jiun Wu, Kuang Ku ChenAbstract:The semiconductor and thin-film transistor liquid crystal display (TFT-LCD) industries are currently two of the most important high-tech industries in Taiwan and occupy over 40% of the global market share. Moreover, these two industries need huge investments in manufacture production equipments (PE) and own a large production scale of the global market. Therefore, how to increase the processing Quality of PE to raise the production capacity has become an important issue. The statistical process control technique is usually adopted to monitor the important process parameters in the current Fabs. Furthermore, a routine check for machine or a predictive maintenance policy is generally applied to enhance the stability of process and improve yields. However, manufacturing system cannot be obtained online Quality measurements during the manufacturing process. When the abnormal conditions occur, it will cause a large number of scrapped substrates and the costs will be seriously raised. In this research, a virtual metrology (VM) system is proposed to overcome those mentioned problems. It not only fulfills real-time Quality measurement of each Wafer, but also detects the performance degradation of the corresponding machines from the information of manufacturing processes. This paper makes four critical contributions: (1) The more principal component analysis (PCA) we used, the higher the accuracy we obtained by the kernel function approach; (2) the more support vector data description (SVDD) we used, the higher the accuracy we obtain in novelty detection module; (3) our empirical results show that genetic algorithm (GA) and incremental learning methods increase the training/learning of support vector machine (SVM) model; and (4) by developing a Wafer Quality prediction model, the SVM approach obtains better prediction accuracy than the radial basis function neural network (RBFN) and back-propagation neural network (BPNN) approaches. Therefore, this paper proposes that the artificial intelligent (AI) approach could be a more suitable methodology than traditional statistics for predicting the potential scrapped substrates risk of semiconductor manufacturing companies.
-
Integrating support vector machine and genetic algorithm to implement dynamic Wafer Quality prediction system
Expert Systems with Applications, 2010Co-Authors: Pao Hua Chou, Menq Jiun Wu, Kuang Ku ChenAbstract:The semiconductor and thin-film transistor liquid crystal display (TFT-LCD) industries are currently two of the most important high-tech industries in Taiwan and occupy over 40% of the global market share. Moreover, these two industries need huge investments in manufacture production equipments (PE) and own a large production scale of the global market. Therefore, how to increase the processing Quality of PE to raise the production capacity has become an important issue. The statistical process control technique is usually adopted to monitor the important process parameters in the current Fabs. Furthermore, a routine check for machine or a predictive maintenance policy is generally applied to enhance the stability of process and improve yields. However, manufacturing system cannot be obtained online Quality measurements during the manufacturing process. When the abnormal conditions occur, it will cause a large number of scrapped substrates and the costs will be seriously raised. In this research, a virtual metrology (VM) system is proposed to overcome those mentioned problems. It not only fulfills real-time Quality measurement of each Wafer, but also detects the performance degradation of the corresponding machines from the information of manufacturing processes. This paper makes four critical contributions: (1) The more principal component analysis (PCA) we used, the higher the accuracy we obtained by the kernel function approach; (2) the more support vector data description (SVDD) we used, the higher the accuracy we obtain in novelty detection module; (3) our empirical results show that genetic algorithm (GA) and incremental learning methods increase the training/learning of support vector machine (SVM) model; and (4) by developing a Wafer Quality prediction model, the SVM approach obtains better prediction accuracy than the radial basis function neural network (RBFN) and back-propagation neural network (BPNN) approaches. Therefore, this paper proposes that the artificial intelligent (AI) approach could be a more suitable methodology than traditional statistics for predicting the potential scrapped substrates risk of semiconductor manufacturing companies. © 2009 Elsevier Ltd. All rights reserved.
Chanhwi Jung - One of the best experts on this subject based on the ideXlab platform.
-
Winter Simulation Conference - Two-stage lot scheduling with waiting time constraints and due dates
2013 Winter Simulations Conference (WSC), 2013Co-Authors: Tae-sun Yu, Chanhwi JungAbstract:We examine a two-stage lot scheduling problem with waiting time constraints and distinct due dates. Wafer lots in diffusion or etch processes generally have due dates specified for each process stage. Some lots even have more strict time constraints that their waiting times between two or multiple stages should not exceed specified limits. We also wish to minimize the variation of the waiting times at the intermediate buffer, which is detrimental to Wafer Quality variability. To solve such a scheduling problem, we develop a mixed integer programming model for small problems. Also, we suggest an efficient solution procedure for large problems by adopting the earliest due date policy and propose a timing control strategy.
-
Two-stage lot scheduling with waiting time constraints and due dates
2013 Winter Simulations Conference (WSC), 2013Co-Authors: Tae-sun Yu, Chanhwi JungAbstract:We examine a two-stage lot scheduling problem with waiting time constraints and distinct due dates. Wafer lots in diffusion or etch processes generally have due dates specified for each process stage. Some lots even have more strict time constraints that their waiting times between two or multiple stages should not exceed specified limits. We also wish to minimize the variation of the waiting times at the intermediate buffer, which is detrimental to Wafer Quality variability. To solve such a scheduling problem, we develop a mixed integer programming model for small problems. Also, we suggest an efficient solution procedure for large problems by adopting the earliest due date policy and propose a timing control strategy.
Pao Hua Chou - One of the best experts on this subject based on the ideXlab platform.
-
integrating support vector machine and genetic algorithm to implement dynamic Wafer Quality prediction system
Expert Systems With Applications, 2010Co-Authors: Pao Hua Chou, Menq Jiun Wu, Kuang Ku ChenAbstract:The semiconductor and thin-film transistor liquid crystal display (TFT-LCD) industries are currently two of the most important high-tech industries in Taiwan and occupy over 40% of the global market share. Moreover, these two industries need huge investments in manufacture production equipments (PE) and own a large production scale of the global market. Therefore, how to increase the processing Quality of PE to raise the production capacity has become an important issue. The statistical process control technique is usually adopted to monitor the important process parameters in the current Fabs. Furthermore, a routine check for machine or a predictive maintenance policy is generally applied to enhance the stability of process and improve yields. However, manufacturing system cannot be obtained online Quality measurements during the manufacturing process. When the abnormal conditions occur, it will cause a large number of scrapped substrates and the costs will be seriously raised. In this research, a virtual metrology (VM) system is proposed to overcome those mentioned problems. It not only fulfills real-time Quality measurement of each Wafer, but also detects the performance degradation of the corresponding machines from the information of manufacturing processes. This paper makes four critical contributions: (1) The more principal component analysis (PCA) we used, the higher the accuracy we obtained by the kernel function approach; (2) the more support vector data description (SVDD) we used, the higher the accuracy we obtain in novelty detection module; (3) our empirical results show that genetic algorithm (GA) and incremental learning methods increase the training/learning of support vector machine (SVM) model; and (4) by developing a Wafer Quality prediction model, the SVM approach obtains better prediction accuracy than the radial basis function neural network (RBFN) and back-propagation neural network (BPNN) approaches. Therefore, this paper proposes that the artificial intelligent (AI) approach could be a more suitable methodology than traditional statistics for predicting the potential scrapped substrates risk of semiconductor manufacturing companies.
-
Integrating support vector machine and genetic algorithm to implement dynamic Wafer Quality prediction system
Expert Systems with Applications, 2010Co-Authors: Pao Hua Chou, Menq Jiun Wu, Kuang Ku ChenAbstract:The semiconductor and thin-film transistor liquid crystal display (TFT-LCD) industries are currently two of the most important high-tech industries in Taiwan and occupy over 40% of the global market share. Moreover, these two industries need huge investments in manufacture production equipments (PE) and own a large production scale of the global market. Therefore, how to increase the processing Quality of PE to raise the production capacity has become an important issue. The statistical process control technique is usually adopted to monitor the important process parameters in the current Fabs. Furthermore, a routine check for machine or a predictive maintenance policy is generally applied to enhance the stability of process and improve yields. However, manufacturing system cannot be obtained online Quality measurements during the manufacturing process. When the abnormal conditions occur, it will cause a large number of scrapped substrates and the costs will be seriously raised. In this research, a virtual metrology (VM) system is proposed to overcome those mentioned problems. It not only fulfills real-time Quality measurement of each Wafer, but also detects the performance degradation of the corresponding machines from the information of manufacturing processes. This paper makes four critical contributions: (1) The more principal component analysis (PCA) we used, the higher the accuracy we obtained by the kernel function approach; (2) the more support vector data description (SVDD) we used, the higher the accuracy we obtain in novelty detection module; (3) our empirical results show that genetic algorithm (GA) and incremental learning methods increase the training/learning of support vector machine (SVM) model; and (4) by developing a Wafer Quality prediction model, the SVM approach obtains better prediction accuracy than the radial basis function neural network (RBFN) and back-propagation neural network (BPNN) approaches. Therefore, this paper proposes that the artificial intelligent (AI) approach could be a more suitable methodology than traditional statistics for predicting the potential scrapped substrates risk of semiconductor manufacturing companies. © 2009 Elsevier Ltd. All rights reserved.
Menq Jiun Wu - One of the best experts on this subject based on the ideXlab platform.
-
integrating support vector machine and genetic algorithm to implement dynamic Wafer Quality prediction system
Expert Systems With Applications, 2010Co-Authors: Pao Hua Chou, Menq Jiun Wu, Kuang Ku ChenAbstract:The semiconductor and thin-film transistor liquid crystal display (TFT-LCD) industries are currently two of the most important high-tech industries in Taiwan and occupy over 40% of the global market share. Moreover, these two industries need huge investments in manufacture production equipments (PE) and own a large production scale of the global market. Therefore, how to increase the processing Quality of PE to raise the production capacity has become an important issue. The statistical process control technique is usually adopted to monitor the important process parameters in the current Fabs. Furthermore, a routine check for machine or a predictive maintenance policy is generally applied to enhance the stability of process and improve yields. However, manufacturing system cannot be obtained online Quality measurements during the manufacturing process. When the abnormal conditions occur, it will cause a large number of scrapped substrates and the costs will be seriously raised. In this research, a virtual metrology (VM) system is proposed to overcome those mentioned problems. It not only fulfills real-time Quality measurement of each Wafer, but also detects the performance degradation of the corresponding machines from the information of manufacturing processes. This paper makes four critical contributions: (1) The more principal component analysis (PCA) we used, the higher the accuracy we obtained by the kernel function approach; (2) the more support vector data description (SVDD) we used, the higher the accuracy we obtain in novelty detection module; (3) our empirical results show that genetic algorithm (GA) and incremental learning methods increase the training/learning of support vector machine (SVM) model; and (4) by developing a Wafer Quality prediction model, the SVM approach obtains better prediction accuracy than the radial basis function neural network (RBFN) and back-propagation neural network (BPNN) approaches. Therefore, this paper proposes that the artificial intelligent (AI) approach could be a more suitable methodology than traditional statistics for predicting the potential scrapped substrates risk of semiconductor manufacturing companies.
-
Integrating support vector machine and genetic algorithm to implement dynamic Wafer Quality prediction system
Expert Systems with Applications, 2010Co-Authors: Pao Hua Chou, Menq Jiun Wu, Kuang Ku ChenAbstract:The semiconductor and thin-film transistor liquid crystal display (TFT-LCD) industries are currently two of the most important high-tech industries in Taiwan and occupy over 40% of the global market share. Moreover, these two industries need huge investments in manufacture production equipments (PE) and own a large production scale of the global market. Therefore, how to increase the processing Quality of PE to raise the production capacity has become an important issue. The statistical process control technique is usually adopted to monitor the important process parameters in the current Fabs. Furthermore, a routine check for machine or a predictive maintenance policy is generally applied to enhance the stability of process and improve yields. However, manufacturing system cannot be obtained online Quality measurements during the manufacturing process. When the abnormal conditions occur, it will cause a large number of scrapped substrates and the costs will be seriously raised. In this research, a virtual metrology (VM) system is proposed to overcome those mentioned problems. It not only fulfills real-time Quality measurement of each Wafer, but also detects the performance degradation of the corresponding machines from the information of manufacturing processes. This paper makes four critical contributions: (1) The more principal component analysis (PCA) we used, the higher the accuracy we obtained by the kernel function approach; (2) the more support vector data description (SVDD) we used, the higher the accuracy we obtain in novelty detection module; (3) our empirical results show that genetic algorithm (GA) and incremental learning methods increase the training/learning of support vector machine (SVM) model; and (4) by developing a Wafer Quality prediction model, the SVM approach obtains better prediction accuracy than the radial basis function neural network (RBFN) and back-propagation neural network (BPNN) approaches. Therefore, this paper proposes that the artificial intelligent (AI) approach could be a more suitable methodology than traditional statistics for predicting the potential scrapped substrates risk of semiconductor manufacturing companies. © 2009 Elsevier Ltd. All rights reserved.