Semiconductor Wafer Fabrication System Research Articles

An adaptive Copula function-based framework for fault detection in semiconductor wafer fabrication

Wafer fabrication is a complex manufacturing system. Timely identification of the key influencing factors associated with the cause of defects is critical to wafer yield enhancement. However, the massive wafer fabrication process dataset has various data types, uncertain data distribution, and complex correlation relationships. These issues make the statistical sense of correlation association measures, and fault detection (FD) methods face many challenges. Therefore, this study proposes an adaptive Copula function-based framework for FD in semiconductor wafer fabrication. Firstly, the marginal distribution of the wafer fabrication process data was determined. After that, a joint distribution model based on the Copula function was designed for the nonlinear relationship and the nonnormal distribution characteristics. Based on the model mentioned above, the traditional Copula function selection method has a high-dimensional spatial failure problem based on the Euclidean distance theory. Therefore, a high-dimensional spatial distance measurement method based on improved kernel distance measurement (IKDM) is designed to realize the adaptive selection of Copula functions. Afterward, the key influencing factors associated with wafer yield are identified through feature sensitivity analysis and validated with multiple prediction models for comparison. Finally, a case study using actual data from a semiconductor wafer fabrication system is used to validate the effectiveness of the proposed methodological framework.

A Copula network deconvolution-based direct correlation disentangling framework for explainable fault detection in semiconductor wafer fabrication

Wafer fabrication is a highly complex manufacturing system. Using complex network models to portray the correlation between parameters is an effective tool for finding the key influencing factors associated with the cause of wafer defects. However, the complex network in a wafer fabrication system has many nonlinearities, non-normal distributions, coupling, and spurious correlations. Quantitative clarification of direct and indirect correlations in the complex network is the prerequisite for achieving explainable fault detection in smart manufacturing. Therefore, a Copula network deconvolution-based direct correlation disentangling framework is proposed in the context of explainable fault detection in semiconductor wafer fabrication. Firstly, The complex network correlation diagram of the parameters in the wafer fabrication process is constructed with each parameter as a node and the correlation coefficients between parameters as connected edges. Then, a nonlinear correlation metric model based on adaptive Copula function selection is designed to deal with the nonlinear correlation of complex network models. The adaptive selection of the Copula function is realized by the goodness-of-fit test method based on Euclidean distance. After that, considering the coupling and spurious correlation in the complex network model, a network deconvolution-based fault detection method is designed to identify direct correlation. Finally, a case study using the actual data from semiconductor wafer fabrication systems is conducted to compare the existing mainstream fault detection methods and validate the effectiveness of the proposed method.

A Dynamic Dispatching Method for Large-Scale Interbay Material Handling Systems of Semiconductor FAB

Interbay Automated Material Handling Systems (AMHS) are widely adopted especially in Semiconductor Wafer Fabrication Systems (SWFS). The dispatching method plays a major role in the control of AMHS. This paper proposes an efficient multi-objective dynamic dispatching method which will dynamically adjust vehicle-load assignments according to the real-time situation of the system. A multi-objective cost function with variable weights is established, taking into account various performance indices (i.e., transport time, throughput, cycle time, vehicle utilization, movement, and waiting time), and the corresponding mathematical model is formulated. Then, in order to obtain the suitable weights according to the real-time condition, an advanced method is developed based on fuzzy theory. After that, a Hungarian algorithm is adopted to solve the model. Finally, simulations are conducted to validate the proposed method. The results demonstrate that it has better comprehensive performance compared to the previous dispatching methods.

Dynamic dispatching for interbay automated material handling with lot targeting using improved parallel multiple-objective genetic algorithm

With the growth of wafer size from 200 mm to 300 mm and then to 450 mm in recent years, automatic material handling system (AMHS) has played an indispensable role in semiconductor wafer fabrication systems, and improving the overall efficiency of interbay AMHS has therefore received considerable attention. This study investigates the integrated scheduling problem in an interbay AMHS that combines vehicle scheduling with lot targeting. However, the large-scale, dynamic, and stochastic production environment significantly substantiates the complexity of the scheduling problem. To meet the demands of adaptive adjusting, efficient scheduling, and multiple-objective optimization, this study develops an improved parallel multiple-objective genetic algorithm with full use of parallel strategy, multi-objective evolutionary process, and local search strategy. Simulation experiments have been conducted and the numerical results illustrate the superiority of the algorithm in terms of comprehensive performance of multiple sub-objectives.

A performance model of automated material handling systems with double closed-loops and shortcuts in 300 mm semiconductor wafer fabrication systems

Automated material handling systems (AMHSs) with double closed-loops and shortcuts have been widely adopted by general 300mm semiconductor fabrication enterprises due to their higher transportation efficiency, more flexible vehicle routing, and lower vehicle congestion compared with those traditional ones with single-loop. An accurate and efficient performance analysis model is crucial to quickly and effectively evaluate the schemes in the early stage of AMHS design. This paper proposes an extended Markov chain model (EMCM) to rapidly and effectively analyze performances of the AMHS with double closed-loops and shortcuts. In the modeling process, the inner closed-loop and shortcuts are abstracted as virtual stations to discretely express the running process of overhead hoist transporters (OHTs) on them. OHT’s running process in AMHS is discretized and equivalent to the state change of Markov chain and a triple-structure model is presented to describe the Markov states, so that the system characteristics, including OHT blockage, system’s double closed-loops, and shortcuts configuration, can be fully considered. The complex Markov process with multiple OHTs is transformed into the process with multiple independent OHTs so as to effectively eliminate the model’s state space explosion. System state probabilities models and blocking probability models are built to effectively represent its state and blocking properties. The stability state equations of EMCM are built so that its steady-state visit ratio can be identified. With production data from a semiconductor fabrication enterprise, the proposed performance analysis model is compared with a simulation model. The result shows that two models have a small relative error in the aspect of empty OHT’s mean arrival time interval, interbay throughput capacity, and OHT’s mean utilization ratio. However, the computing efficiency of the EMCM is significantly higher than that of the simulation model. It demonstrates that the proposed EMCM is effective and efficient for performance analysis in the early stage of AMHS design.

Big data analytics for cycle time related feature selection in the semiconductor wafer fabrication system

The dynamic wafer workshop gives rise to strong fluctuations of cycle time (CT) followed by earliness or tardiness penalty. Comprehending these fluctuations is a major challenge as the cycle time intricately interacts with massive parameters. This paper proposes a big data analytics method for feature selection to obtain all explanatory factors of CT that would shed light on the fluctuation of CT. Firstly, the correlative analysis is performed between each two candidate factors with mutual information metric to construct the observed network. Secondly, the network deconvolution is investigated to infer the direct dependence between the candidate factor and the CT by removing the effects of transitive relationships from the network. Additionally, a factor selection algorithm is designed to reduce the dimension of candidate factors to form the CT explanatory network, which contains the key factors interacting with the CT of wafer lots. The experimental results demonstrate the proposed method outperforms the references in term of classification and prediction accuracy. A case study is conducted with real data from a semiconductor wafer fabrication system, the big data captured for feature selection is analyzed, and the identified key factors are proved to be effective in forecasting and fluctuation interpretation of CT.

AdaBalGAN: An Improved Generative Adversarial Network With Imbalanced Learning for Wafer Defective Pattern Recognition

Identification of the defective patterns of the wafer maps can provide insights for the quality control in the semiconductor wafer fabrication systems (SWFSs). In real SWFSs, the collected wafer maps are usually imbalanced from the defective types, which will result in misidentification. In this paper, a novel deep learning model called adaptive balancing generative adversarial network (AdaBalGAN) is proposed for the defective pattern recognition (DPR) of wafer maps with imbalanced data. In addition, a categorical generative adversarial network is improved to generate simulated wafer maps in high fidelity and classify the patterns with high accuracy for all defective categories. Taking consideration of the various learning abilities of the DPR model for different patterns into account, an adaptive generative controller is designed to balance the number of samples of each defective type according to the classification accuracy. The experiment results indicated that the proposed AdaBalGAN model outperforms conventional models with higher accuracy and stability for the DPR of wafer maps. Further results of comparative experiments revealed that the proposed adaptive generative mechanism can enhance and balance the recognition accuracy for all categories in the DPR of wafer maps.

A Hybrid Vehicle Dispatching Approach for Unified Automated Material Handling System in 300mm Semiconductor Wafer Fabrication System

The automation of unified automated material handling system (UAMHS) in 300mm semiconductor wafer fabrication system (SWFS) is complex due to complicated product mixes, numerous and dynamic transportation demands, transportation deadlock, and vehicle blockages. Vehicle dispatching has become one of crucial means to improve the overall operating efficiency of UAMHS. Currently, many vehicle dispatching studies have been devoted to the optimization of the performance indexes of UAMHS. However, more important performance indexes related to SWFS, such as cycle time, throughput, and due date satisfaction, were seldom considered. To bridge this gap, a fuzzy logical and Hungarian algorithm-based (FLHA) vehicle dispatching approach is proposed to obtain better comprehensive performance of UAMHS and SWFS simultaneously. In the proposed approach, candidate wafer lots' transport priority is identified and sorted by fuzzy logic method firstly. Then the wafer lots with higher priority are selected as candidate lots, and it is assigned to the idle transport vehicles based on Hungarian method. After the optimized assigning solution is found, a greedy vehicle transport policy is design to execute it, which can reduce temporary transportation deadlock and vehicles' waste movement effectively. With experimental data from an UAMHS of 300 mm SWFS and running simulation experiments, the results demonstrated that the proposed approach is feasible and effective. Further comparisons with other traditional vehicle dispatching approaches show that the proposed approach has better comprehensive performance in terms of cycle time, throughput, due date satisfaction, delivery time, transport time, and OHT vehicle utilization.

An Operation-Group Based Soft Scheduling Approach for Uncertain Semiconductor Wafer Fabrication System

This paper tackles a large-scale and uncertain scheduling problem of semiconductor wafer fabrication system. Two kinds of uncertainties are considered here, including the machine breakdowns and the fluctuations of processing times. Instead of using the traditional rigid schedule, we propose a novel concept of operation-group-based soft schedule which is used as the new decision variable of the studied problem. The inherent idea of this concept is to make some critical scheduling decisions at the beginning of the scheduling horizon, and allow the remaining decisions to be made during the execution of the initial soft schedule. Furthermore, an operation-group-based soft scheduling approach (OGSSA) is proposed to deal with the uncertainties, which contains an offline optimization layer and an online dispatching layer. In the offline optimization layer, a prediction-based decomposition scheduling method is proposed to generate a soft schedule, and a global scheduling objective prediction model is constructed to evaluate the soft schedule. Then, the initial soft schedule is released to the online dispatching layer, and an online heuristic rule is designed to decide in real time, which operations and when to process. The computational results on the practical production data demonstrate the effectiveness of OGSSA under uncertain production environments.

Big data driven cycle time parallel prediction for production planning in wafer manufacturing

ABSTRACTCycle time forecasting (CTF) is one of the most crucial issues for production planning to keep high delivery reliability in semiconductor wafer fabrication systems (SWFS). This paper proposes a novel data-intensive cycle time (CT) prediction system with parallel computing to rapidly forecast the CT of wafer lots with large datasets. First, a density peak based radial basis function network (DP-RBFN) is designed to forecast the CT with the diverse and agglomerative CT data. Second, the network learning method based on a clustering technique is proposed to determine the density peak. Third, a parallel computing approach for network training is proposed in order to speed up the training process with large scaled CT data. Finally, an experiment with respect to SWFS is presented, which demonstrates that the proposed CTF system can not only speed up the training process of the model but also outperform the radial basis function network, the back-propagation-network and multivariate regression methodology based CTF methods in terms of the mean absolute deviation and standard deviation.

A Data Driven Cycle Time Prediction With Feature Selection in a Semiconductor Wafer Fabrication System

Accurate prediction of cycle time (CT) plays an important role in the promises of a good delivery-time for semiconductor manufacturers. However, the CTs of wafer lots are difficult to forecast since they are influent by a lot factors (e.g., workload for every machine). The identification of key factors (called CT-related) can not only improve the prediction performance but also facilitate the control of CT, which is of particular significance. This paper focuses on gathering subtle variables into the candidate variables set along with the further analysis which is required in the correlation analysis between various candidate factors and CTs of wafer lots. The candidates set is first constructed to collect all factors that may affect wafer lots’ CT. Then, a regression-based model is proposed to select CT-related variables, which consists of three parts: 1) discretization; 2) adaptive logistic regression-based correlation analysis; and 3) CT-related factor selection. Subsequently, a parallel computation model is implemented to forecast the CTs of wafer lots. In the numerical experiments, 108 CT-related factors stood out from 774 candidates and replaced six global factors (used as reference) to predict CTs of wafer lots. The results indicated that the proposed approach had higher accuracy than linear regression and back propagation network in CT forecasting in large scale data analysis.

Big Data Driven Key Factor Identification for Cycle-time Forecasting of Wafer Lots in Semiconductor Wafer Fabrication System

Big Data Driven Key Factor Identification for Cycle-time Forecasting of Wafer Lots in Semiconductor Wafer Fabrication System

A slack optimization unified model of regrouping and sequencing batches for β1 → β2 manufacturing system

It is challenging to schedule batch processing machine in the semiconductor wafer fabrication system. Based on the rolling horizon scheme, the overall horizon is decomposed into many time windows. ...

Minimizing total earliness and tardiness on re-entrant batch processing machine with time windows

ABSTRACTThe time window (TW) generalizes the concept of due date. The semiconductor wafer fabrication system is currently one of the most complex production processes, which has typical re-entrant batch processing machine (RBPM). RBPM is a bottleneck. This paper addresses a scheduling of RBPM with job-dependent TWs. According to a general modelling, an improved and new job-family-oriented modelling of the decomposition method that is based on the slack mixed integer linear programming is proposed. First, the complicated scheduling problem of RBPM is divided into sub-problems, which are executed circularly. Then, each one consists of updating, sequencing and dispatching. The objective is to minimize the total earliness and tardiness for job-dependent TWs. In order to evaluate the proposed modelling, the experiments are implemented on the real-time scheduling simulation platform and optimization toolkit ILOG CPLEX. The results show that the improved modelling obtains better solutions in less computation time.

Real-time OHT Dispatching Mechanism for the Interbay Automated Material Handling System with Shortcuts and Bypasses

As a key to improve the performance of the interbay automated material handling system (AMHS) in 300 mm semiconductor wafer fabrication system, the real-time overhead hoist transport (OHT) dispatching problem has received much attention. This problem is first formulated as a special form of assignment problem and it is proved that more than one solution will be obtained by Hungarian algorithm simultaneously. Through proposing and strictly proving two propositions related to the characteristics of these solutions, a modified Hungarian algorithm is designed to distinguish these solutions. Finally, a new real-time OHT dispatching method is carefully designed by implementing the solution obtained by the modified Hungarian algorithm. The experimental results of discrete event simulations show that, compared with conventional Hungarian algorithm dispatching method, the proposed dispatching method that chooses the solution with the maximum variance respectively reduces on average 4 s of the average waiting time and average lead time of wafer lots, and its performance is rather stable in multiple different scenarios of the interbay AMHS with different quantities of shortcuts. This research provides an efficient real-time OHT dispatching mechanism for the interbay AMHS with shortcuts and bypasses.

Big data analytics for forecasting cycle time in semiconductor wafer fabrication system

In order to improve the prompt delivery reliability of the semiconductor wafer fabrication system, a big data analytics (BDA) is designed to predict wafer lots’ cycle time (CT), which is composed by four parts: data acquisition, data pre-processing, data analysing and data prediction. Firstly, the candidate feature set is constructed to collecting all features by analysing the material flow of wafer foundry. Subsequently, a data pre-processing technique is designed to extract, transform and load data from wafer lot transactions data-set. In addition, a conditional mutual information-based feature selection process is proposed to select key feature subset to reduce the dimension of data-set through data analysing without pre-knowledge. To handle the large volumes of data, a concurrent forecasting model is designed to predict the CT of wafer lots in parallel as well. According to the numerical analysis, the predict accuracy of the presented BDA improves clearly with the increase in data size. And, in the large-scale data-set, the BDA has higher accuracy than linear regression and back-propagation network in CT forecasting.

A performance analytical model of automated material handling system for semiconductor wafer fabrication system

To effectively analyse and evaluate the performances of closed-loop automated material handling system (AMHS) with shortcut and blocking in semiconductor wafer fabrication system, a modified Markov chain model (MMCM) has been proposed. The system characteristics, such as vehicle blockage and system’s shortcut configuration, are well considered in the MMCM. The state space explosion problem and computational challenge due to the increase of AMHS scale can be effectively eliminated. With production data from Interbay material handling system of a 300-mm semiconductor wafer fabrication line, the proposed MMCM is compared with simulation analysis model. The results demonstrate that the proposed MMCM is an effective modelling methodology for AMHS’s performance analysis at system design stage.

Robust Production Capacity Planning of a Wafer Fabrication System with Uncertain Wafer Lots Transfer Probabilities

Production capacity planning is an important problem in the design of a semiconductor wafer fabrication system, which means to optimize the number of tools in the system so that expected production rate, work-in-process level can be satisfied and the cost of building the wafer fab can be minimized. However, a wafer fab usually produces multiple types of wafers, different types of wafers have different and complicated processing routes, and the work-in-process quantities of different types of wafers changes frequently due to the fluctuation of demands. Therefore, the transfer probabilities of wafer lots among tools, material handle devices and bays in the wafer fab are uncertain. To deal with this uncertainty, it is necessary to improve the robustness of he production capacity planning of a wafer fab. In this paper, we construct an open queueing network-based model of a wafer fab and developed a mathematical model of the robust production capacity planning problem with the objective of maximizing the probability of satisfying expected performance requirements. To solve this problem, a heuristic algorithm is proposed and numerical experiments are conducted to evaluate the robustness of the solution.

Combined scheduling algorithm for re-entrant batch-processing machines in semiconductor wafer manufacturing

In this paper, a new combined scheduling algorithm is proposed to address the problem of minimising total weighted tardiness on re-entrant batch-processing machines (RBPMs) with incompatible job families in the semiconductor wafer fabrication system (SWFS). The general combined scheduling algorithm forms batches according to parameters from the real-time scheduling simulation platform (ReS2), and then sequences batches through slack-based mixed integer linear programming model (S-MILP), which is defined as batch-oriented combined scheduling algorithm. The new combined scheduling algorithm obtains families’ parameters from ReS2 and then sequences these families through modified S-MILP, which is defined as family-oriented combined scheduling algorithm. With rolling horizon control strategy, two combined scheduling algorithms can update RBPMs scheduling continually. The experiments are implemented on ReS2 of SWFS and ILOG CPLEX, respectively. The results demonstrate the effectiveness of our proposed methods.

An Order Release Control Mechanism Based on self-Adaptive Neural Fuzzy Inference System and Theory of Constraints

Order release is the key premise for the semiconductor wafer fabrication system to perform well, which is also one of the paramount significant components in the scheduling strategies. Most order release strategies merely have focused on the workloadbut failed in considering the remarkable influence oncycletime of common orders that is brought by unexpectedrushones.In this paper an on-linemechanismbased on Theory of Constraintsfor lot releaseusingself-Adaptive Neural Fuzzy Inference System modelswas presentedwhich is able to adjust the release rhythmdynamicallyaccording to dynamics of fabs.In our approach, an ANFIS model was established to predict the ratiobetweenhotand common lotsin wafer fabto perform adjustments on the order release schedule in advance.Simulated experimentsbased on the HP24 model were carefully performed and experimental results proved a better performance of common lotsthan original TOC on a large scale, especially when it comes to the situation of disturbance. DOI: http://dx.doi.org/10.11591/telkomnika.v11i11.3488 Full Text: PDF