A virtual metrology system for semiconductor manufacturing

Nowadays, the semiconductor manufacturing becomes very complex, consisting of hundreds of individual processes. If a faulty wafer is produced in an early stage but detected at the last moment, unnecessary resource consumption is unavoidable. Measuring every wafer’s quality after each process can save resources, but it is unrealistic and impractical because additional measuring processes put in between each pair of contiguous processes significantly increase the total production time. Metrology, as is employed for product quality monitoring tool today, covers only a small fraction of sampled wafers. Virtual metrology (VM), on the other hand, enables to predict every wafer’s metrology measurements based on production equipment data and preceding metrology results. A well established VM system, therefore, can help improve product quality and reduce production cost and cycle time. In this paper, we develop a VM system for an etching process in semiconductor manufacturing based on various data mining techniques. The experimental results show that our VM system can not only predict the metrology measurement accurately, but also detect possible faulty wafers with a reasonable confidence.     

A new state estimation method for high-mix semiconductor manufacturing processes

In semiconductor manufacturing upstream processes may affect the wafer substrate in a manner that alters performance in downstream operations, and the context within which a process is run may fundamentally change the way the process behaves. Incorporating these influences into a control method ultimately leads to better predictability and improved control performance, because one lot of a specific product may take a very different processing path through the fabrication facility than the next lot of that same product. This paper provides a new method for state estimation in a high-mix manufacturing scenario, based on a random walk model. This model, combined with a moving window approach and least squares solution, provides better estimates for simulated processes with a high-mix of tools and products with many low-runners as compared to alternative methods. An approach combining the Kalman filter and the least squares solution is also developed, with improved results in some cases. In the case of manufacturing data, we modify the model parameters and the weights on processing contexts to get better results.     

A multi-agent system using iterative bidding mechanism to enhance manufacturing agility

The global market has become increasingly dynamic, unpredictable and customer-driven. This has led to rising rates of new product introduction and turbulent demand patterns across product mixes. As a result, manufacturing enterprises were facing mounting challenges to be agile and responsive to cope with market changes, so as to achieve the competitiveness of producing and delivering products to the market timely and cost-effectively. This paper introduces a currency-based iterative agent bidding mechanism to effectively and cost-efficiently integrate the activities associated with production planning and control, so as to achieve an optimised process plan and schedule. The aim is to enhance the agility of manufacturing systems to accommodate dynamic changes in the market and production. The iterative bidding mechanism is executed based on currency-like metrics; each operation to be performed is assigned with a virtual currency value and agents bid for the operation if they make a virtual profit based on this value. These currency values are optimised iteratively and so does the bidding process based on new sets of values. This is aimed at obtaining better and better production plans, leading to near-optimality. A genetic algorithm is proposed to optimise the currency values at each iteration. In this paper, the implementation of the mechanism and the test case simulation results are also discussed.     

Defective wafer detection using a denoising autoencoder for semiconductor manufacturing processes

Defective wafer detection is essential to avoid loss of yield due to process abnormalities in semiconductor manufacturing. For most complex processes in semiconductor manufacturing, various sensors are installed on equipment to capture process information and equipment conditions, including pressure, gas flow, temperature, and power. Because defective wafers are rare in current practice, supervised learning methods usually perform poorly as there are not enough defective wafers for fault detection (FD). The existing methods of anomaly detection often rely on linear excursion detection, such as principal component analysis (PCA), k-nearest neighbor (kNN) classifier, or manual inspection of equipment sensor data. However, conventional methods of observing equipment sensor readings directly often cannot identify the critical features or statistics for detection of defective wafers. To bridge the gap between research-based knowledge and semiconductor practice, this paper proposes an anomaly detection method that uses a denoise autoencoder (DAE) to learn a main representation of normal wafers from equipment sensor readings and serve as the one-class classification model. Typically, the maximum reconstruction error (MaxRE) is used as a threshold to differentiate between normal and defective wafers. However, the threshold by MaxRE usually yields a high false positive rate of normal wafers due to the outliers in an imbalanced data set. To resolve this difficulty, the Hampel identifier, a robust method of outlier detection, is adopted to determine a new threshold for detecting defective wafers, called MaxRE without outlier (MaxREwoo). The proposed method is illustrated using an empirical study based on the real data of a wafer fabrication. Based on the experimental results, the proposed DAE shows great promise as a viable solution for on-line FD in semiconductor manufacturing.     

A G&P EWMA algorithm for high-mix semiconductor manufacturing processes

In mixed run processes, typical in semiconductor manufacturing and other automated assembly-line type process, products with different recipes will be produced on the same tool. Product based run-to-run control can be applied to improve the process capability. The effect of product-based controller on low frequency products is, however, minimal, due to inability to track tool variations. In this work, we propose a group and product based EWMA control scheme which combines adaptive k-means cluster method and run-to-run EWMA control to improve the performance of low frequency products in the mixed run process. Similar products could be classified into the same group adaptively and controlled by a group EWMA controller. The group controller is updated by both low frequency products and similar high frequency products; so that low frequency products can be improved by shared information from similar large frequency products. However, the high frequency products are controlled by individual product-based EWMA to avoid interference of the low frequency products. The advantages of proposed control scheme are demonstrated by benchmark simulation and reversed engineered industrial applications.     

A Kalman filter-based R2R control system with parallel stochastic disturbance models for semiconductor manufacturing processes

A Kalman filter-based run-to-run control system has been proposed for minimum variance control of semiconductor manufacturing process. In the proposed control system, both gain- and bias-varying process models combined with different stochastic disturbance models were considered and identified in parallel. The best-fit model is selected and used for the R2R controller design. Sub-models of the ARIMA(1,1,1) process were considered for stochastic modeling of the bias and gain variation, and the Kalman filters are used to find the optimum model parameter estimation. The control performance was analyzed for each case of the disturbance model to investigate the expected benefit from the control system in comparison with the EWMA filter-based controller.     

Evaluating investment-return-based design for AMHS in semiconductor manufacturing system

An effective automated material handling system (AMHS) design improves production performance. Investment return is a primary concern for high technology companies when purchasing production equipment. This study demonstrates that when profit gained from investing in non-production equipment investment can be estimated, investment return can be evaluated and used as an investment index for non-production equipment. An effective approach based on Little’s law for AMHS design is proposed. This approach quantifies system improvement resulting from a specific AMHS design. Then, an activity and theory of constraints based (ABC/TOC) costing model is used to capitalize the improvement. Finally, the investment-return time length for that specific design can be evaluated. An investor can easily decide among several designs when using the proposed approach.     

Scheduling of an unreliable manufacturing system with nonresumable setups

This paper considers the scheduling of a manufacturing system with nonresumable setup changes. The system considered involves an unreliable machine that can produce two part types. The switchover from one part type to the other incurs a given constant setup time. The setups are nonresumable, i.e. after a machine repair completion, a setup decision has to be made. The parts have specified constant processing time and constant demand rate. We give a continuous dynamic programming formulation of the problem, which is solved numerically. The optimal setup switching policies are shown to be hedging corridors. Two heuristics, for the determination of the hedging levels, are provided. We show, through simulation, that the two heuristics exhibit good performance.     

Multiple-objective scheduling and real-time dispatching for the semiconductor manufacturing system

Implementing efficient scheduling and dispatching policies is a critical means to gain competitiveness for modern semiconductor manufacturing systems. In contemporary global market, a successful semiconductor manufacturer has to excel in multiple performance indices, consequently qualified scheduling approaches should provide efficient and holistic management of wafer products, information and manufacturing resources and make adaptive decisions based on real-time processing status to reach an overall optimized system performance. To cope with this challenge, a timed extended object-oriented Petri nets (EOPNs) based multiple-objective scheduling and real-time dispatching approach is proposed in this paper. Four performance objectives pursued by semiconductor manufacturers are integrated into a priority-ranking algorithm that serves as the initial scheduling guidance, and then all wafer lots will be dynamically dispatched by the hybrid real-time dispatching control system. A set of simulation experiments validate the proposed multiple-objective scheduling and real-time dispatching algorithm may achieve satisfactory performances.     

基于Petri网的柔性制造系统调度控制模型

给出了自顶向下构造柔性制造系统(FMS)Petri网模型的方法,提出了随机创建指定数目满足指定条件的测试模型的算法,并给出程序仿真运行的演算规则。在此基础上实现了基于Petri网FMS分析与调度仿真软件平台,该平台可配置性强,容易维护,降低了柔性制造系统方针研究的复杂性。最后给出了该模型实现的模块结构。     

A practical approach to a process planning expert system for manufacturing processes

In this paper the methodical techniques applied by the human process planning expertise is simulated. It considers the process plans design, or process selection. Software modules are designed to generate a process plan or several plans for a new part according to the input data from its engineering drawing. A specific module for each surface type, to match the surface parametric data and the required quantities with respect to the capability matrices, in order to locate the most eligible process plan is identified and used.     

Virtual metrology and feedback control for semiconductor manufacturing processes using recursive partial least squares

Virtual metrology (VM) is the prediction of metrology variables (either measurable or non-measurable) using process state and product information. In the past few years VM has been proposed as a method to augment existing metrology and has the potential to be used in control schemes for improved process control in terms of both accuracy and speed. In this paper, we propose a VM based approach for process control of semiconductor manufacturing processes on a wafer-to-wafer (W2W) basis. VM is realized by utilizing the pre-process metrology data and more importantly the process data from the underlying tools that is generally collected in real-time for fault detection (FD) purposes. The approach is developed for a multi-input multi-output (MIMO) process that may experience metrology delays, consistent process drifts, and sudden shifts in process drifts. The partial least squares (PLS) modeling technique is applied in a novel way to derive a linear regression model for the underlying process, suitable for VM purposes. A recursive moving-window approach is developed to update the VM module whenever metrology data is available. The VM data is then utilized to develop a W2W process control capability using a common run-to-run control technique. The proposed approach is applied to a simulated MIMO process and the results show considerable improvement in wafer quality as compared to other control solutions that only use lot-to-lot metrology information.     

An intelligent virtual metrology system with adaptive update for semiconductor manufacturing

Virtual metrology involves the estimation of metrology values using a prediction model instead of metrological equipment, thereby providing an efficient means for wafer-to-wafer quality control. Because wafer characteristics change over time according to the influence of several factors in the manufacturing process, the prediction model should be suitably updated in view of recent actual metrology results. This gives rise to a trade-off relationship, as more frequent updates result in a higher accuracy for virtual metrology, while also incurring a heavier cost in actual metrology. In this paper, we propose an intelligent virtual metrology system to achieve a superior metrology performance with lower costs. By employing an ensemble of artificial neural networks as the prediction model, the prediction, reliability estimation, and model update are successfully integrated into the proposed virtual metrology system. In this system, actual metrology is only performed for those wafers where the current prediction model cannot perform reliable predictions. When actual metrology is performed, the prediction model is instantly updated to incorporate the results. Consequently, the actual metrology ratio is automatically adjusted according to the corresponding circumstances. We demonstrate the effectiveness of the method through experimental validation on actual datasets.     

The future of semiconductor manufacturing

This paper addresses the evolving requirements for factory integration and automation solutions that are being targeted to address the scale and complexity of the factories of the future. These requirements drive the need for real breakthrough solutions. More than ever before, there must be a strong focus on developing integrated solutions, using mainstream computer communications standards and protocols, so that development and implementation time is minimized and the software solutions are extendible as information technology evolves over time. The volume of manufacturing, process, yield, inspection, quality, and other critical data continues to exponentially increase with each new technology; therefore, its collection, storage, access, sharing, analysis, and retention methods have become a major challenge as well as a strategic competitive advantage for each company. Developing a flexible information systems architecture, with security features taking center stage to thwart possible virus infections, has also become an absolute necessity. Reduction of factory cycle times has become an important priority, as increased inventory (due to larger wafers) of the 'wrong" products in an everchanging marketplace results in a high risk of product obsolescence and loss of revenue. Other equally important business drivers facing the new generation of fabs also will be covered in this article     

ERCN* merged nets for modeling degraded behavior and parallel processes in semiconductor manufacturing systems

This paper presents a new class of "well-behaved" Petri nets called extended resource control net (ERCN*) merged nets that generalize the class of ERCN merged nets proposed in a previous paper by Xie and Jeng. ERCN merged nets can model parallel and synchronized processes in semiconductor manufacturing such as lot split and lot merging, which occurs frequently in a research and development (R&D) semiconductor fab (semiconductor plant) for engineering purposes. However, processing cycles for each resource type must include the initial state of the resource type. In other words, no local processing cycles are allowed. This makes the modeling of degraded behavior in semiconductor manufacturing such as rework, failure, and maintenance difficult. In the current work, this constraint is relaxed under the "extended free-choice (EFC)" or "asymmetric choice (AC)" condition. Specifically, for each operation place with degrading outgoing arcs, the FC or AC condition is satisfied. In addition, degraded behavior is modeled as blocks within ERCNs. We show that conditions for liveness and reversibility of an ERCN* merged net correspond to the absence of unmarked siphons. The "well-behaved" conditions can be transformed into inequalities of the initial marking. Examples are shown to illustrate the proposed methodology.     

Dynamic vehicle allocation control for automated material handling system in semiconductor manufacturing

The current study examines the dynamic vehicle allocation problems of the automated material handling system (AMHS) in semiconductor manufacturing. With the uncertainty involved in wafer lot movement, dynamically allocating vehicles to each intrabay is very difficult. The cycle time and overall tool productivity of the wafer lots are affected when a vehicle takes too long to arrive. In the current study, a Markov decision model is developed to study the vehicle allocation control problem in the AMHS. The objective is to minimize the sum of the expected long-run average transport job waiting cost. An interesting exhaustive structure in the optimal vehicle allocation control is found in accordance with the Markov decision model. Based on this exhaustive structure, an efficient algorithm is then developed to solve the vehicle allocation control problem numerically. The performance of the proposed method is verified by a simulation study. Compared with other methods, the proposed method can significantly reduce the waiting cost of wafer lots for AMHS vehicle transportation.     

Scheduling one-part-type serial manufacturing system under periodic demand: a solvable case

The paper studies one-part type, multiple-stage production system with periodic demands. A buffer of infinite capacity is placed after each machine. Inventory flow through buffers is controlled by machine production rates. The objective is to find a cyclic production rate, which minimizes all inventory-related expenses over an infinite planning horizon. With the aid of the maximum principle, optimal production policies are derived and the continuous-time scheduling problem is reduced to a discrete timing problem. As a result, a polynomial-time algorithm is suggested to calculate the optimal production rate. A numerical example is used to illustrate the algorithm.Scope and purposeNumerical and heuristic approaches have been suggested for production control of automated-serial-manufacturing systems. These approaches try to derive production control policies that would minimize overall costs related to inventory, backlog, and production. The quality of these approaches is often difficult to assess, and they can be time-consuming to implement. Therefore, increasing attention has been directed to optimal control policies of production systems that can be derived precisely and quickly. This paper addresses a special case of the production system manufacturing a single product type to meet a periodic demand. Given a certain assumption on cost relationship, we derive a fast and simple scheduling algorithm that calculates the optimal policy.     

A combined dispatching criteria approach to scheduling semiconductor manufacturing systems

The scheduling problem of semiconductor manufacturing systems has multiple responses of interest. The objective is to simultaneously optimize these different responses or to find the best-compromised solution. Most previous research in the area of semiconductor manufacturing systems has focused on optimizing a single performance measure. Dabbas and Fowler proposed a modified dispatching approach that combines multiple dispatching criteria into a single rule with the objective of simultaneously optimizing multiple objectives. In this paper, we validate their proposed approach using two different fab models at different levels of complexity: a hypothetical six stage-five machines Mini-Fab model and a full scale wafer fab model adapted from an actual Motorola wafer fab. We also discuss the actual implementation of the proposed dispatching algorithm into a scheduler for daily operation at a Motorola wafer fabrication facility. Results show an average 20% improvement for all responses when using the proposed dispatching approach.     

Automatic defect classification for semiconductor manufacturing

Visual defect inspection and classification are important parts of most manufacturing processes in the semiconductor and electronics industries. Defect classification provides relevant information to correct process problems, thereby enhancing the yield and quality of the product. This paper describes an automated defect classification (ADC) system that classifies defects on semiconductor chips at various manufacturing steps. The ADC system uses a golden template method for defect re-detection, and measures several features of the defect, such as size, shape, location and color. A rule-based system classifies the defects into pre-defined categories that are learnt from training samples. The system has been deployed in the IBM Burlington 16 M DRAM manufacturing line for more than a year. The system has examined over 100 000 defects, and has met the design criteria of over 80% classification rate and 80% classification accuracy. Issues involving system design tradeoff, implementation, performance, and deployment are closely examined.