Automatic Virtual Metrology Research Articles

Developing the Keep-Important-Samples Scheme for Training the Advanced CNN-Based Automatic Virtual Metrology Models

Developing the Keep-Important-Samples Scheme for Training the Advanced CNN-Based Automatic Virtual Metrology Models

Intelligent Additive Manufacturing Architecture for Enhancing Uniformity of Surface Roughness and Mechanical Properties of Laser Powder Bed Fusion Components

In the Laser Powder Bed Fusion (L-PBF) process, 3D components with complex geometries are fabricated in a layer-by-layer fashion by using a controlled laser beam to selectively melt particular regions of the metal powder bed. However, due to the stochastic nature of the L-PBF process, the top surface roughness of each solidified layer tends to be different even when the optimal processing conditions for the different positions on the build plate are employed. As a result, the mechanical properties of the built components frequently vary from one component to the next. Accordingly, this study proposes an Intelligent Additive Manufacturing Architecture (IAMA) for controlling the surface roughness of each build layer through an appropriate adjustment of the laser re-melting parameters. The IAMA architecture comprises five modules, namely In-Situ Metrology (ISM), Ex-Situ Metrology (ESM), Automatic Virtual Metrology (AVM), Additive Manufacturing Simulation (AMS) and Intelligent Compensator (IC). The feasibility of the proposed architecture is demonstrated by comparing the top surface roughness of cubic and mechanical strengths of tensile test samples built using the proposed method with those built using a traditional L-PBF approach without surface roughness control. It is found that the samples fabricated using the IAMA approach have an average top surface roughness of 1.6 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mu$</tex-math> </inline-formula> m and a standard deviation is 0.7 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mu$</tex-math> </inline-formula> m. By contrast, the samples produced using the traditional L-PBF approach have an average surface roughness of 13.45 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mu$</tex-math> </inline-formula> m and a standard deviation of 2.5 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mu$</tex-math> </inline-formula> m. In addition, the specimens produced with the assistance of IAMA architecture have an average tensile strength of 1013 MPa with a standard deviation of 69.5 MPa, while those printed without surface roughness control have an average tensile strength of 903 MPa with a standard deviation of 101.4 MPa <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —As L-PBF produce part in a layer-by-layer manner, therefore, the roughness on the top surface of previous layer have a strong influence on the printing quality of current layer. The variations of surface roughness will lead to the fluctuation of mechanical properties of the fabricated components. Additionally, to the best of author’s knowledge, current commercial L-PBF machines can not actively control the surface roughness of samples during the process. The proposed IAMA in this work can predict and control the roughness on the top surface of each layer during L-PBF process. Therefore, the constructed architecture has strong potential for integrating into the commercial L-PBF machine for controlling the surface roughness on the top of the parts during the manufacturing process. As a result, the quality of the fabricated components is expected to be in consistent. Accordingly, L-PBF machine equipped with IAMA will have a strong potential in applying for mass production of the components in aerospace and automobile industries.

Convolutional Autoencoder and Transfer Learning for Automatic Virtual Metrology

To ensure stable processing and high-yield production, high-tech factories (e.g., semiconductor, TFT-LCD) demand product quality total inspection. Generally speaking, sampling inspection only measures a few samples and comes with metrology delay, thus it usually cannot achieve the goal of real-time and online total inspection. Automatic Virtual Metrology (AVM) was developed to tackle such problem. It can collect the data from the process tools to conjecture the virtual metrology (VM) values in the prediction model for realizing the goal of online and real-time total inspection. With the advancement of technology, the processes become more and more precise, and better accuracy of VM value prediction is demanded. The CNN-based AVM (denoted as AVM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CNN</sub> ) scheme can not only enhance the accuracy of the original AVM prediction, but also perform better on the extreme values. Nevertheless, two advanced capabilities need to be addressed for its practical applications: 1) effective initial-model-creation approach with insufficient metrology data; and 2) intelligent self-learning capability for on-line model refreshing. To possess these two advanced capabilities, the Advanced AVM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CNN</sub> System based on convolutional autoencoder (CAE) and transfer learning (TL) is proposed in this work. It is verified that the Advanced AVM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CNN</sub> System is more feasible for the onsite applications of the actual production lines.

Golden Path Search Algorithm for the KSA Scheme

The concepts of Industry 4.1 for achieving Zero-Defect (ZD) manufacturing were disclosed in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IEEE Robotics and Automation Letters</i> in January 2016. ZD of all the deliverables can be achieved by discarding the defective products via a real-time and online total inspection technology, such as Automatic Virtual Metrology (AVM). Further, the Key-variable Search Algorithm (KSA) of the Intelligent Yield Management (IYM) system developed by our research team can be utilized to find out the root causes of the defects for continuous improvement on those defective products. As such, nearly ZD of all products may be achieved. However, in a multistage manufacturing process (MMP) environment, a workpiece may randomly pass through one of the manufacturing devices with the same function in each stage. Different devices of the same type perform differently in each stage, where the performances will be accumulated through the designated manufacturing process and affect the final yield. KSA can only identify the influence of univariate variables (i.e., single devices) on the yield, yet it cannot detect the manufacturing paths that have significant influence on the yield. In order to cope with this deficiency such that the golden path with a better yield amongst all the MMP paths can be found, this research proposes the Golden Path Search Algorithm (GPSA), which can plan golden paths with high yield under the condition of the number of variables being much larger than that of samples. As a result, it makes the improvement of manufacturing yield be more comprehensive. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Traditional scheduling only considers the capacity of the manufacturing devices for allocation; while, the impact on the yield is rarely considered. In fact, in a production process, the production deviations will be gradually accumulated and affect the product quality along with the processing influence of each device. Therefore, the purpose of this paper is to propose the GPSA scheme to quickly search for high-yield manufacturing paths before the production. Manufacturers can then configure production devices based on these paths. According to the experimental results of real manufacturers’ data, GPSA can not only quickly nail down the high-yield paths from a large amount of historical data, but also alert the users to avoid paths that are prone to defective rates for their reference.

Convolutional Neural Networks for Automatic Virtual Metrology

To ensure stable manufacturing and high yield of production, factories (e.g., semiconductor or TFT-LCD fabs) conduct quality inspection on workpieces. They tend to adopt sampling inspection in consideration of reducing cost and cycle time, yet that fails to achieve real-time and online total inspection because of the sampling strategy and metrology delay. Automatic Virtual Metrology (AVM) is the best solution to tackle the problem mentioned above, due to the fact that it can convert sampling inspection with metrology delay into on-line and real-time total inspection. However, with the advancement of science and technology, the processes become more and more sophisticated, and the requirement for the accuracy of virtual metrology becomes higher. The current AVM prediction algorithm is the traditional machine learning method, Back-Propagation Neural Networks (BPNN). However, even if the amount of data in this method increases, the performance improvement has its limits, and it requires a strict and time-consuming feature selection process. To improve the prediction accuracy, this work proposes the deep learning method, Convolutional Neural Networks (CNN), for the AVM server. The accuracy of CNN improves as the amount of data grows. In other words, if there are sufficient data, the current accuracy limit of machine learning can be enhanced. Experimental results reveal that CNN can automatically extract highly informative features from the data and improves the original AVM accuracy.

Process Prediction for Compound Screws by Using Virtual Measurement and Recognizable Performance Evaluation

One of the important values of Industry 4.0 is to integrate people’s needs into the manufacture of enhanced products, systems, and services to achieve greater levels of product customization. This paper presents a prediction method for predicting screw process parameters; taking crystalline and non-crystalline polymers as the molding material, when there is a lack of sufficient historical screw process data to establish a data-driven method, using various screws and polymer materials to predict tool life under different cutting conditions is a challenge. A screw life prediction method is proposed based on the mixed compound screw process parameters method using a dynamic iteration work. To meet the requirements of mass production, this work proposes the combined application of the automatic virtual metrology (AVM) system with the recognizable performance evaluation (RPE) program. The method predicts the injection of compound screws by extracting given cutting conditions and related process parameters characteristics from the senor data by converting sampling inspections with measurement delays from real-time and online routine inspections to automatically and quickly complete method creation production goals.

An Online AM Quality Estimation Architecture From Pool to Layer

Quality control is the key for the widespread adoption of metal additive manufacturing (AM). However, online quality estimation is challenging because high-frequency stream data derived from in situ metrology have to be processed in a timely manner to figure out the complicated interactions among material, machine, and part. To tackle such issue, this article proposes an intelligent AM metrology (IAMM) architecture to decouple and evaluate quality variations caused by material properties, machine issues, and process parameters when building an AM part. The IAMM architecture can also estimate the online layer-to-layer quality (e.g., roughness and density of an AM part) by applying the robust parameters derived from the uniform design (UD) method via the enhanced automatic virtual metrology technology in a parallel computing environment, as soon as the microfeatures of melt-pools and the macrofeatures of each layer are extracted. In addition, the associated indices and features in the IAMM architecture can also be used to evaluate the defects caused by machine issues in the given process parameters. The results of case studies validate the applicability of the IAMM architecture and show that the proposed estimation models are prospective for future closed-loop control in an AM process. Note to Practitioners —The proposed intelligent AM metrology (IAMM) architecture can be implemented modularly in a metal additive manufacturing (AM) machine that possesses the capability of estimating the coating and printing qualities of the AM process by extracting features from the optical data of the melt pools and chamber layer by layer. The estimated indices and qualities can be derived online using parallel computation to timely diagnose the machine issues and control the process of the next layer. Hence, when an AM machine is equipped with the IAMM architecture, it can efficiently manufacture a 3-D part with reduced defects in real time.

Automated Classification Scheme plus AVM for Wafer Sawing Processes

For the current wafer sawing process, the wafers in the same lot are inspected at the end of the entire process. Therefore, a defect, such as chipping, occurs during processing will only be detected until the end of the process, which is too late and may cause massive defects. If Automatic Virtual Metrology (AVM) is implemented in the wafer sawing process, when chippings occur and are detected, its chipping amount can be predicted by AVM on-line and in real time. Also, AVM's individual similarity index (ISI) analysis can be applied to identify the root cause of chipping. As a result, this root cause can be fixed to avoid generating defects in the subsequent wafers. However, chipping won't happen to all wafers. Since the AVM system deals mainly with the regression problem, it cannot classify whether a wafer is chipped or not. Hence, there is a need to predict wafer-chipping occurrence before applying AVM to the wafer sawing process. To solve the above mentioned problem, the wafer sawing quality monitoring is divided into two stages. An Automated Classification Scheme (ACS) based on ensemble learning is developed in Stage I to pre-determine whether a wafer is chipped. If chipping is detected, then proceed to Stage II for the AVM system to predict the chipping amount and identify the root cause that results in this chipping. With the so-called ACS-plus-AVM scheme, the AVM application in the wafer sawing process can be realized.

Automatic Virtual Metrology for Carbon Fiber Manufacturing

Carbon fiber is currently one of the most popular composite materials in the world, with its wide applications ranging from bikes to space shuttles. However, there is no comprehensive method for the total quality inspection of carbon fiber products so far due to its feature of continuous production and destructive examination of quality inspection. Through years of development, the Automatic Virtual Metrology (AVM) technology has been applied to various industries to turn the offline sampling inspection with metrology delay into online and real-time total inspection. With AVM, every workpiece of the carbon fiber products can be examined to ensure total quality inspection. The biggest issue of continuous production is that it can neither accurately define each unit nor label on the products. To solve this problem, a production data traceback (PDT) mechanism is proposed in this letter. The PDT mechanism can provide a virtual label to each unit for referring back to the process parameters of the production. With PDT, the process data of each workpiece of a complete spin can be acquired so as to accomplish the work-in-process (WIP) tracking requirement of applying AVM. Also, the Advanced Manufacturing Cloud of Things (AMCoT) platform is adopted in this letter to fulfill all the smart manufacturing requirements for achieving the goal of zero defects of carbon fiber manufacturing.

An Intelligent Metrology Architecture With AVM for Metal Additive Manufacturing

The capability of measuring melt pool variation is the key evaluating metal additive manufacturing quality. To measure the variation, a metrology architecture with in situ melt pool measurement and an estimation module is required. However, it is a challenge to effectively extract significant features from the huge data collected by the in situ metrology for quality estimation requirement. The purpose of this letter is to propose an intelligent metrology architecture with an in situ metrology (ISM) module and an enhanced automatic virtual metrology (AVM) system. The ISM module can extract the melt pool features with a coaxial camera and a pyrometer. On the other hand, the AVM system is improved with a feature selection method to solve the issue of limited samples in the component modeling quality. The examples with different metals are adopted to illustrate how the system works for estimating surface roughness and density of components, and, in the future, the system can even serve as the feedback signal for adaptive control of the process parameters by layering in an additive manufacturing system.

A Novel Automated Construction Scheme for Efficiently Developing Cloud Manufacturing Services

Cloud manufacturing (CMfg) has emerged as a next-generation manufacturing paradigm that has potential to revolutionize the manufacturing industry. In further promotion of CMfg, how to build CMfg services in an automatic and efficient manner is an essential and challenging subject. Currently, there is no literature addressing such issue. Aimed at facilitating rapid construction of CMfg services, this letter proposes a novel automated construction scheme for developing CMfg services, called Manufacturing Service Automated Construction Scheme (MSACS). First, we develop a three-phase workflow of MSACS to address the issues of how to construct CMfg services automatically using standalone software library package (SSLP). Next, we design a system architecture of MSACS to delineate how to implement MSACS. Then, we depict the designs of MSACS's core components. Finally, we apply MSACS to conduct industrial case studies to build the automatic virtual metrology cloud service and intelligent yield management cloud service for an intelligent manufacturing platform. Testing results demonstrate that MSACS can automatically construct the target CMfg services in a very efficient manner after uploading the required SSLPs. Thus, MSACS can significantly alleviate the burden of engineers in building CMfg services, and in turn can facilitate the promotion of CMfg.

Automatic Virtual Metrology and Deformation Fusion Scheme for Engine-Case Manufacturing

Industry 4.0 paves the way to smart factory through integrating Internet of Things, cyber-physical systems, cloud manufacturing, and big data analytics for various industrial fields. Especially, the machinery industry significantly benefits from these automation techniques in machine-tool quality inspection, cutting-tool remaining-useful-life, surface roughness prediction, etc. However, these innovation technologies are still not executable in the aerospace-component production due to their complex machining conditions, which result in long metrology delays and severe component deformations. To overcome these two challenges of the aerospace industry, this letter proposes to apply the automatic virtual metrology (AVM) system to successfully convert sampling inspections with metrology delay into real-time and online total inspection and to utilize the so-called deformation fusion (DF) scheme for dealing with the component-deformation problem. The application of the flange operation of aerospace engine-case manufacturing is adopted to illustrate the performance of the AVM-plus-DF approach.

Automatic Virtual Metrology and Target Value Adjustment for Mass Customization

One of the core values of Industry 4.0 targets to integrate people's demand into manufacturing for enhanced products, systems, and services for a wider variety of increasingly personalized customization of products. Thus, Industry 4.0 advances the traditional manufacturing techniques from mass production toward mass customization (MC). Take wheel machining automation (WMA) as an example. To meet MC expectations, manufacturers should offer customized wheels at a large scale with low cost, short lead-time, and high quality. Thus, WMA cells with MC capability are requested to be designed to have a high degree of quick responsiveness to accurately react on machining-condition changes for manufacturing different wheel types. To meet the requirements of MC production, this work proposes to apply the automatic virtual metrology (AVM) system together with the so-called target-value-adjustment (TVA) scheme. The AVM system was developed by the authors to convert sampling inspections with metrology delay into real-time and on-line total inspection, while the TVA scheme is designed to enhance AVM's adaptive customization capability for automatically and rapidly accomplishing the goals of MC production. To demonstrate the versatility of the AVM-plus-TVA approach, the other example in semiconductor etching process is also illustrated.

Development of a novel cloud-based multi-tenant model creation service for automatic virtual metrology

AVM (Automatic Virtual Metrology) is the highest-level technology for VM (Virtual Metrology) applications from the perspective of automation. Its various automatic capabilities could facilitate fast factory-wide deployment and operations of VM systems. AVM systems have been successfully applied to the semiconductor, TFT-LCD, solar-cell, and machining industries for on-line monitoring the production quality of workpieces. However, in its past industrial applications, the model creation (MC) functionality of the existing AVM system encountered several limitations, such as being a standalone application and confined to be used in situ in a factory, no support for multiuser model creation, wasting computing resources, etc., which could diminish the applicability of the existing AVM system in current global and distributed manufacturing environments. Thus, this paper is dedicated to tackling the problem of how to systematically and effectively overcome MC-related limitations of the existing AVM system so that it can robustly support multiple users across factories to create their VM models simultaneously in distributed manufacturing settings. By leveraging the advantages of cloud computing and several IT technologies (including virtualization software, XML, Web Service, Multi-tenancy technique, and HTML5), this paper proposes a novel cloud-based multi-tenant model creation service (i.e., CMMCS) for AVM. The proposed CMMCS contains a cloud-based system architecture, functional frameworks of its key components, several functional mechanisms, and HTML5-based Web GUIs. Testing results in an industrial case study that creates VM models using the CMMCS for CNC machine tools in machining wheel rims of automobiles in a factory in Taiwan demonstrate that the CMMCS can allow multiple users from different tenants to simultaneously create their VM models, while enabling the MC cloud services to be more robust for processing MC requests, having higher CPU-usage rates in the underlying virtual machines, and achieving better cross-platform usage, compared to the original MC functionality. This paper has provided a feasible solution to systematically and effectively remedying the MC-related limitations of the existing AVM system. The existing VM-related literature mainly focused on the development of VM models. To our knowledge, no papers have coped with issues addressed in this paper by leveraging cloud computing. The results of this paper can be a useful reference for industrial practitioners to construct AVM systems which support multi-tenant or multiuser model creation. A novel cloud-based multi-tenant model creation service (CMMCS) for automatic virtual metrology (AVM) has been proposed.Designs of key components and mechanisms have been presented to effectively address the existing AVM's MC limitations.CMMCS can support multi-tenant/user model creation for AVM, being applicable to the distributed manufacturing context.A case study of creating VM models for machine tools in machining wheel rims of autos demonstrates the efficacy of CMMCS.Results can be useful references for industrial practitioners to construct AVM systems supporting multi-tenant MC.

Industry 4.1 for Wheel Machining Automation

Industry 4.0 is set to be one of the new manufacturing objectives. The technologies involved to achieve Industry 4.0 are Internet of Things (IoT), cyber physical systems (CPS), and cloud manufacturing (CM). However, the current objectives defined by Industry 4.0 do not include zero defects; it only keeps the faith of achieving nearly zero-defects state. The purpose of this paper is to propose a platform denoted advanced manufacturing cloud of things (AMCoT) to not only achieve the objectives of Industry 4.0 but also accomplish the goal of zero defects by applying the technology of automatic virtual metrology (AVM). As such, by applying Industry 4.0 together with AVM to achieve the goal of zero defects, the era of Industry 4.1 is taking place. The application of wheel machining automation is adopted in this letter to illustrate how AMCoT and Industry 4.1 work.

Automatic virtual metrology for wheel machining automation

Total inspection after wheel machining becomes essential for safety consideration and continuous improvement. However, conducting wheel-by-wheel actual metrology is very expensive and time-consuming. A novel idea is to use virtual metrology (VM) that predicts wheel quality based on process data collected from machine tool with a slight supplement of actual metrology data. The technology of automatic virtual metrology (AVM) has been proposed by the authors and successfully deployed in hi-tech industries, such as semiconductor, display and solar cell. The purpose of this study was to propose an approach to apply the AVM system factory-wide to wheel machining automation (WMA) for achieving total inspection of all the precision items of WMA under mass production environment.

Automated sampling decision scheme for the AVM system

Reducing the sampling rate to as low as possible is a high priority for many factories to reduce production cost. Automatic virtual metrology based intelligent sampling decision (ISD) scheme had been previously developed for reducing the sampling rate and sustaining the virtual metrology (VM) accuracy. However, the desired sampling rate of the ISD scheme is fixed and set manually. Hence, whenever the VM accuracy gets worse, it cannot adaptively increase the default sampling rate in the ISD scheme. As a consequence, it would take more time to collect enough samples for improving the VM accuracy. Moreover, when the VM accuracy performs well all the time, it cannot automatically decrease the default sampling rate in ISD, which may result in unnecessary waste. Accordingly, this paper proposes an automated sampling decision (ASD) scheme to adaptively and automatically modify the sampling rate online and in real time for continuous improvement. The ASD scheme can monitor the VM accuracy online as well as update the VM models in real time for maintaining the VM accuracy when the VM accuracy becomes poor. Also, the ASD scheme can automatically reduce the sampling rate while the VM accuracy performs well.

Development of cloud-based automatic virtual metrology system for semiconductor industry

Automatic virtual metrology (AVM) is the highest-level technology for virtual metrology (VM) applications from the perspective of automation, which could facilitate fast factory-wide deployment of VM systems. However, the existing AVM system suffered several limitations during its practical deployment and operation in a fab for semiconductor manufacturing. In this paper, by leveraging the advantages of cloud computing, we propose an approach of building cloud-based AVM systems, which can effectively resolve these limitations. First, a cloud-based architecture is designed based on a private cloud to virtualize all servers of the AVM system for resolving the limitations of using physical servers, such as incurring high hardware cost, occupying a lot of shop-floor space, and needing complex efforts in managing VM servers. Then, three automatic functional mechanisms (i.e., automatic-deployment mechanism, automatic-scaling mechanism, and automatic-serving mechanism) are developed in an extra server (i.e., the virtual machine administrator server) to automate the deployment of VM servers, to automatically scale out/in the number of VM servers on demand, and to automatically dispatch VM servers to serve the requested VM tasks in parallel. Such an architecture design could significantly reduce the efforts of migrating the original AVM system to the cloud. Integrated testing results show that the proposed cloud-based AVM system could successfully overcome the limitations of the existing AVM system, while demonstrating a significant performance improvement over the existing AVM system in predicting the production quality of wafers. Most existing VM-related literature focused on the development of the VM models. To our knowledge, no papers have coped with the issues of plant-wide deployment and operation of VM systems by using cloud computing. This paper could be a useful reference for industrial practitioners to construct cloud-based AVM systems. An approach of building cloud-based AVM systems is proposed.A cloud-based AVM architecture is designed based on private cloud.The AVM system can be transformed into a cloud-based version with small efforts.The limitations of the existing AVM system are addressed and overcome.This paper could be a useful reference for constructing cloud-based AVM systems.

Intelligent sampling decision scheme based on the AVM system

Wafer inspection plays a significant role in monitoring the quality of wafers production for continuous improvement. However, it requires measuring tools and additional cycle time to do real metrology, which is costly and time-consuming. Therefore, reducing sampling rate to as low as possible is a high priority to reduce production cost. Several sampling methods in the literature were proposed to achieve this goal. They utilised real sampling inspections as the representatives for the other related wafers to monitor the whole production process. Under the condition of stable manufacturing process, virtual metrology (VM) may be applied to monitor the quality of wafers, while real metrology is unavailable. Therefore, the sampling rate may further be reduced with a sampling decision scheme being designed according to reliable VM. Nevertheless, once a new production variation occurs between planned samplings and no real metrology is available during this period for updating the VM models, un-reliable VM predictions may be produced. The authors have developed the automatic virtual metrology (AVM) system for various VM applications. Therefore, this paper focuses on applying various indices of the AVM system to develop an intelligent sampling decision scheme for reducing sampling rate, while VM accuracy is still sustained.

Advanced ART2 scheme for enhancing metrology-data-quality evaluation

The metrology-data-quality-index (DQIy) algorithm was proposed to perform metrology-data-quality evaluation of the automatic virtual metrology system developed by the authors. The DQIy algorithm is based on the adaptive-resonance-theory 2 (ART2). ART2 divides data into different patterns according to the similarity of process data, and then calculates the corresponding DQIy value and its threshold, DQIyT, for evaluation and judgment. However, in practical applications, the classical ART2 technique still could not cluster process data very precisely. Since some samples with dissimilar process parameters might be sorted into the same cluster, two or more groups could be found in the corresponding metrology-data cluster. This phenomenon may cause invalid DQIy detection. To solve the problem above, the advanced ART2 scheme is proposed in this paper to enhance the accuracy of the DQIy algorithm. A large industrial data-set showing both a shift in metrology measurements without a process shift and a process shift that was not captured by the metrology of the actual photo and color-filter production tools of a TFT-LCD factory were adopted as illustrative examples to verify the practicality of the proposed scheme. Experimental results show that the performance of the advanced ART2 is indeed better than that of the original ART2.