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

Virtual Metrology (VM) refers to a technology that is able to conjecture product quality using important parameter data of production equipment and proper prediction schemes. In an automatic VM system (AVMS), VM Manager is the core of system's operations and the communication bridge among subsystems because it is responsible for distributing commands to each subsystem and possessing access privilege to the central database. This paper aims to develop a new kernel and several functional mechanisms for VM Manager so that the AVMS with refined VM Manager can have superior overall execution efficiency than the original one. A paradigm AVMS with the refined VM Manager for the TFT-LCD industry is constructed and tested. Integrated testing results validate that the developed new kernel and functional mechanisms of VM Manager can indeed achieve the design objectives.

Virtual metrology (VM) predicts on-wafer properties, such as thickness and uniformity, using equipment data (e.g., sensors, constants) and potentially on-wafer properties or predictions from previous steps. While much literature is devoted to developing VM models, maintaining them (e.g., so they can be used for months in production) presents a different set of challenges. Behavior of equipment can change over time, causing degradation of VM models. Maintenance events can abruptly reset sensors and process conditions, invalidating VM models. In addition, sensor noise, sensor imperfection and aging parts can disturb performance of VM models. While some of these issues can be addressed during modeling by incorporating certain variables that capture the dynamics associated with these issues, others are harder to foresee. Resolving these issues may require tuning the models as they age or manually rebuilding the models after they become ineffective. To mitigate these problems, techniques including monitoring residual error and tool degradation, compensating for sensor reset and residual error, and auto-retraining models can significantly help VM models maintain their performance during deployment.

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.

Decision-based virtual metrology for advanced process control to empower smart production and an empirical study for semiconductor manufacturing

Quality monitoring is an essential element of defect detection in semiconductor manufacturing processes, but semiconductor companies use virtual metrology (VM) in addition to actual metrology to prevent productivity degradation due to the time and costs required to obtain measurements. Past VM studies aimed to predict average wafer measurement values via equipment sensor data and focused on achieving improved predictive performance by selecting or extracting important variables among high-dimensional variables such as equipment sensor data. However, the management of wafer chip quality requires not only average measurement values but also measurement value predictions for chips located at the edges, which are vulnerable to defects. In this paper, we therefore propose a graph attention (GAT) network-based VM model that predicts the measurement values of chips located at wafer edges by constructing graph data with measurement data (i.e., the measurement location information in wafers and the measurement values). To verify the performance of the proposed model, we conduct a comparative experiment with conventional machine learning methods. The experimental results show that the proposed VM model contributes to a predictive performance improvement in terms of the measurement values of chips located at wafer edges.

This paper discussed the virtual metrology (VM) modelling of multi-class quality to describe the relationship between the variables of a production machine's condition and the estimated/forecasted product quality soon after finishing the machine processing. Applications of PCA and LASSO technique of the Sparse modelling were introduced to define the multi-dimensional quality. Because the high accuracy and quick computations are required for the VM modelling, in this study, the PCA-LASSO combination was applied before building the VM models based on the kernel SVM (kSVM), particularly the linear kernel for real-time use. As the result of evaluation of a CVD (Chemical vapor deposition) process in an actual semiconductor factory, LASSO and linear-SVM could reduce the scale of the machine variable's set and calculation time by almost 57% and 95% without deterioration of accuracy even without PCA. In addition, as the PCA-LASSO, the multi-dimensional quality was rotated to the orthogonality space by PCA to summarize the extracted variables responding to the primary independent hyperspace. As the result of the PCA-LASSO combination, the scale of machine variables extracted was improved by 83%, besides the accuracy of the linear-SVM is 98%. It is also effective as the pre-process of Partial Least Square (PLS).

Virtual metrology (VM) is often applied in semiconductor manufacturing when process measurements cannot be obtained without delay or without impacting the cycle time. When the process condition is varying, the modeling results can be inaccurate if a single VM model is adopted. Also, the large number of variables in the process data increases the difficulty of obtaining good predictions. To improve the accuracy of the metrology value prediction, it is necessary to select and apply only the significant variables in modeling. This paper proposes a just-in-time approach for VM modeling, along with a variable shrinkage and selection method that uses Gaussian process regression. The proposed method is validated using semiconductor process data and found to be superior compared to conventional methods.

This paper proposes to develop a data-driven via's depth estimator of the deep reactive ion etching process based on statistical identification of key variables. Several feature extraction algorithms are presented to reduce the high-dimensional data and effectively undertake the subsequent virtual metrology (VM) model building process. With the available on-line VM model, the model-based controller is hence readily applicable to improve the quality of a via's depth. Real operational data taken from a industrial manufacturing process are used to verify the effectiveness of the proposed method. The results demonstrate that the proposed method can decrease the MSE from 2.2 × 10−2 to 9 × 10−4 and has great potential in improving the existing DRIE process.

In this paper, a Virtual Metrology (VM) model is proposed to predict etch rate which is one of the most important etching profile in etch process. Error Back Propagation (EBP) neural network is used to make the VM for etch rate prediction.

Background: E-beam metrologies, both critical dimension scanning electron microscope metrology and defect scan metrology, have been playing a very critical role in gating patterning quality. SEM images can provide rich visual information for engineers to do qualitative and quantitative analyses. However, the low e-beam metrology tool throughput makes it impossible to obtain SEM images for larger area. Monte Carlo-based SEM image simulations or other SEM image simulations require postlithography or postetch pattern three-dimensional structures as prerequisite, and the simulation speed is not sufficiently fast for full chip implementation. Aim: We aim to develop machine learning SEM models with sufficient accuracy and speed for full chip application in semiconductor manufacturing environment. Approach: We have proposed a virtual SEM metrology solution based on U-Net neural network with physics-based feature maps as model input. With information in aerial image space encoded properly, SEM images of both postlithography and postetch can be predicted accurately enough for practical applications using our proposed virtual SEM metrology models. Equipped with GPUs, the machine learning-based SEM image models are fast enough to make it possible to realize full chip SEM generation from post-OPC data. Results: Our machine learning SEM image models can predict SEM images with normalized cross correlation around 0.95 in reference to ground truth SEM images, each SEM image (512 × 512 in size) takes about 800 ms using single CPU, and the speed can be accelerated to about 10 ms with single GPU. Conclusions: Using U-Net structure and physics-based feature maps as model inputs, machine learning-based SEM image models can be developed. The models are sufficiently accurate and fast to find their applications in semiconductor manufacturing, and they can be used as independent model for OPC data verification or generate SEM images as reference for SEM defect scan metrology.

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 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1.6~\mu \text{m}$ </tex-math></inline-formula> and a standard deviation is <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$0.7~\mu \text{m}$ </tex-math></inline-formula> . By contrast, the samples produced using the traditional L-PBF approach have an average surface roughness of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$13.45~\mu \text{m}$ </tex-math></inline-formula> and a standard deviation of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2.5~\mu \text{m}$ </tex-math></inline-formula> . 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 Note to Practitioners—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.

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.

Virtual metrology (VM) is an enabling technology capable of performing virtual inspection on the metrology quality of wafers. Instead of physically acquiring the metrology measurements, VM applies conjecture models on the process data of wafers to estimate the measurements of the targeted metrology variables. Prior works on overlay VM system utilized fault detection and classification (FDC) data as the process data for the conjecture models. Hence, when FDC data are unavailable owing to FDC system enhancement works, FDC-based VM models would be rendered inefficacious. During such events, a competent VM system using a different modeling approach is required to sustain the production line until FDC data resumes availability and FDC-based VM reaches production state. Motivated by a real-world production environment of a 200mm semiconductor manufacturing plant (fab), a novel wafer lot-level modeling approach for overlay VM was proposed in our prior work. Using the proposed modeling, a smart sampling scheme was also designed in the same work. The smart sampling scheme consists of two conjecture tasks, with the first task classifies the overlay quality of the wafers, and the second task estimates the overlay errors of the wafers classified with normal overlay quality. The abnormal ones are diverted to the physical metrology station. In this paper, the implementation of a smart sampling system, C2O, using the designed scheme and its experimental results are presented. The experimental results showed that C2O is capable to achieve a true positive rate (TPR) of 71.34% for the classification task and mean absolute scaled error (MASE) of 9.59 for the regression task. The obtained results set the baseline to measure the efficacy of future enhancement works, which have been enlisted and underway to augment the performance of the system so that its competency meets the requirements of real fab.

In semiconductor manufacturing, metrology operations are expensive and time-consuming, for this reason only a certain sample of wafers is measured. With the need of highly reliable processes, the semiconductor industry is interested in developing methodologies covering the gap of missing metrology information. Virtual Metrology (VM) turns out to be a promising method; it aims to predict wafer and/or site fine metrology results in real time and free of costs. Using virtual measurements as the input of a sampling decision system (SDS), an optimal strategy for measuring productive wafers can be suggested. Since sampling decisions strongly depend on the accuracy of the VM system, it is a key requirement to monitor the reliability of the obtained predictions. In this paper, we present approaches for dynamically assessing VM reliability using real metrology data. A Bayesian dynamical linear model (BDLM) handles increasing VM model uncertainty over time. Model parameters are updated whenever new real measurements become available. VM prediction quality is monitored applying a probability integral transform (PIT) and scoring rules for predictive probability distributions. Inferring equipment health factors (EHF), unreliable predictions can be detected before being delivered to the SDS. Based on the likelihood of the predicted measurements, VM trust factors are introduced. A Bayesian model for the prediction precision matrix allows updating the virtual measurements' uncertainty whenever real measurements are available. Taking account of the proposed methods, one is led to an improved accuracy of the SDS.

In TSV fabrication process, TSV depth measurement of all wafers is essential to maintain high yield and wafer quality. However, there are limits such as high cost and (low throughput using an actual metrology, i.e. scanning electron microscope (SEM), and only few wafers in a lot are monitored in practice. In this research, we presented a virtual metrology (VM) system for TSV depth measurement after etching process. The proposed VM system is based on PLS regression (PLSR) and neural networks (NN) using OES data to predict TSV depth. Real operational data taken during TSVs etching process along with 80 and 25 μm diameter TSVs are used in order to verify the quality of the prediction accuracy of the proposed VM model.