Search

In manufacturing industries, it is of fundamental importance to detect anomalies in production in order to meet the required quality goals and to limit the number of defective products that are accidentally delivered to the customers. Nevertheless, monitoring systems currently employed in production are typically very simple and rely on a set of univariate control charts that fail to capture the multivariate and complex nature of real-world industrial systems. In such context, Machine Learning (ML)-based approaches for Anomaly Detection (AD) have proven to be extremely effective in increasing anomalies detectability and, in general, in enhancing monitoring procedures. However, industrial data are typically very complex and not suitable to be fed directly to classical ML-based AD tools making feature extraction procedures a necessary step that unfortunately may lead to information loss and low scalability. Deep Learning, has proven very effective at learning useful representations of complex data in an automatic way. In this paper, we propose an AD pipeline that makes use of convolutional autoencoders to extract useful features from two-dimensional, non-image, data. We test our approach on real world Optical Emission Spectroscopy data that are typical of semiconductor manufacturing and we achieve improved performance over classical monitoring methods. Note to Practitioners—Advanced monitoring is one of the most important task in the context of Industry 4.0. Some of the main issues in developing Machine Learning-based solutions in industrial environment are: (i) the lack of reliable tagged data; (ii) the complexity of data structures present in real-world scenarios. In this paper we investigate unsupervised anomaly detection for 2-dimensional data in manufacturing environment: we provide an approach that exploit Deep Learning-based architecture for handling the data at hand. We show the effectiveness of the proposed approach in a real world case study related to optical emission spectroscopy data in semiconductor manufacturing process providing satisfactory classification accuracy. [ABSTRACT FROM AUTHOR]

Metrology, which plays an important role in ensuring production quality in modern manufacturing industries, incurs substantial costs both in terms of the infrastructure required and the time needed to perform measurements. In particular, in the semiconductor manufacturing industry, measuring fundamental quantities on different sites of a wafer surface is associated with increased production time. To increase metrology efficiency, a typical strategy is to limit the number of sites measured and to exploit statistical models (soft sensing) to reconstruct the wafer profile. Moreover, for quality reasons, spatial dynamic sampling strategies may be employed to ensure that all regions of a wafer surface are checked periodically during production. In this paper, we propose a new sampling strategy, called induced start dynamic sampling (ISDS), which adapts greedy feature selection algorithms to the spatial dynamic sampling problem, such that the number of measured sites at each process run is minimized while achieving good wafer profile reconstruction accuracy and process visibility. The superiority of the proposed strategy with respect to the state of the art is demonstrated using both simulated data and an industrial chemical vapor deposition case study. Note to Practitioners—In this paper, we tackle a practical metrology problem encountered in semiconductor manufacturing, namely, the design of a dynamic wafer measurement plan to monitor the accuracy of a process across the whole wafer surface. The measurement plan is called “dynamic,” since the measurement locations, which are drawn from a candidate set that provides coverage of the whole wafer, change at each process iteration. Our methodology addresses the challenge of finding an optimized tradeoff between the number of measurements performed on each wafer and the reconstruction accuracy that can be achieved for the unmeasured areas on the wafer while, at the same time, for quality assurance purposes, ensuring that all locations on a wafer are visited in a finite number of process runs. The major benefit of the methodology is that it can significantly reduce the number of sites that need to be measured on each wafer enabling greater throughput on metrology tools without sacrificing process monitoring and anomaly detection capability. [ABSTRACT FROM AUTHOR]

• A Deep Learning approach for feature extraction in industrial big data is proposed. • DeepVM is completely plug-n-play and naturally deals with 2d data. • An extensive comparison of different autoencoders and regression methods is provided. • DeepVM efficacy is tested on a real Semiconductor Manufacturing dataset. • DeepVM outperforms classical feature extraction procedures in the Virtual Metrology task. Industry 4.0 encapsulates methods, technologies, and procedures that transform data into informed decisions and added value in an industrial context. In this regard, technologies such as Virtual Metrology or Soft Sensing have gained much interest in the last two decades due to their ability to provide valuable knowledge for production purposes at limited added expense. However, these technologies have struggled to achieve wide-scale industrial adoption, largely due to the challenges associated with handling complex data structures and the feature extraction phase of model building. This phase is generally hand-engineered and based on specific domain knowledge, making it time consuming, difficult to automate, and prone to loss of information, thus ultimately limiting portability. Moreover, in the presence of complex data structures, such as 2-dimensional input data, there are no established procedures for feature extraction. In this paper, we present a Deep Learning approach for Virtual Metrology, called DeepVM, that exploits semi-supervised feature extraction based on Convolutional Autoencoders. The proposed approach is demonstrated using a real world Semiconductor Manufacturing dataset where the Virtual Metrology input data is 2-dimensional Optical Emission Spectrometry data. The feature extraction method is tested with different types of state-of-the-art autoencoder. [ABSTRACT FROM AUTHOR]

Various unsupervised greedy selection methods have been proposed as computationally tractable approximations to the NP-hard subset selection problem. These methods rely on sequentially selecting the variables that best improve performance with respect to a selection criterion. Theoretical results exist that provide performance bounds and enable 'lazy greedy' efficient implementations for selection criteria that satisfy a diminishing returns property known as submodularity. Recently, the authors introduced Forward Selection Component Analysis (FSCA) which uses variance explained as its selection criterion. While variance explained is not a submodular criterion, FSCA has been shown to be highly effective for applications such as measurement plan optimization. Motivated by the desire to achieve a more computationally efficient and scalable algorithm implementation, in this paper a 'lazy' implementation of FSCA (L-FSCA) is proposed, which, although not equivalent to FSCA due to the absence of submodularity, has the potential to yield comparable performance while being up to an order of magnitude faster to compute. The efficacy of L-FSCA is demonstrated by performing a systematic comparison with FSCA and five other unsupervised variable selection methods from the literature using simulated and real-world case studies. Experimental results confirm that L-FSCA yields almost identical performance to FSCA while reducing computation time by between 22% and 94% for the case studies considered. [ABSTRACT FROM AUTHOR]

The rise of industry 4.0 and data-intensive manufacturing makes advanced process control (APC) applications more relevant than ever for process/production optimization, related costs reduction, and increased efficiency. One of the most important APC technologies is virtual metrology (VM). VM aims at exploiting information already available in the process/system under exam, to estimate quantities that are costly or impossible to measure. Machine learning (ML) approaches are the foremost choice to design VM solutions. A serious drawback of traditional ML methodologies is that they require a features extraction phase that generally limits the scalability and performance of VM solutions. Particularly, in presence of multi-dimensional data, the feature extraction process is based on heuristic approaches that may capture features with poor predictive power. In this paper, we exploit modern deep learning (DL)-based technologies that are able to automatically extract highly informative features from the data, providing more accurate and scalable VM solutions. In particular, we exploit DL architectures developed in the realm of computer vision to model data that have both spatial and time evolution. The proposed methodology is tested on a real industrial dataset related to etching, one of the most important semiconductor manufacturing processes. The dataset at hand contains optical emission spectroscopy data and it is paradigmatic of the feature extraction problem in VM under examination. [ABSTRACT FROM AUTHOR]

Learning useful representations of complex data has been the subject of extensive research for many years. In particular, with the diffusion of complex Deep Learning-based approaches in engineering applications, the possibility to interpret, to a certain degree, model predictions is of fundamental importance for both the model users and developers. In the context of Deep Neural Networks, Variational Autoencoders have gained lots of attention since they provide an explicit model of the data distribution based on an encoder/decoder architecture which is able to both generate images and encode them in a low-dimensional subspace. However, the latent space is not easily interpretable and the generation capabilities show some limitations since images typically look blurry and lack details. In this paper, we propose the Introspective Variational Classifier (IntroVAC), a model that learns interpretable latent subspaces by exploiting information from an additional label and provides improved image quality thanks to an adversarial training strategy. We show that IntroVAC is able to learn meaningful directions in the latent space enabling fine-grained manipulation of image attributes. We validated our approach on the CelebA dataset. When compared with standard Variational Autoencoder Classifiers, the proposed approach outperform them by achieving a Frechét Inception Distance of 25.5 versus a value of 63.9. [ABSTRACT FROM AUTHOR]

Embedding household appliances with smart capabilities is becoming common practice among major fabric-care producers that seek competitiveness on the market by providing more efficient and easy-to-use products. In Vertical Axis Washing Machines (VA-WM), knowing the laundry composition is fundamental to setting the washing cycle properly with positive impact both on energy/water consumption and on washing performance. An indication of the load typology composition (cotton, silk, etc.) is typically provided by the user through a physical selector that, unfortunately, is often placed by the user on the most general setting due to the discomfort of manually changing configurations. An automated mechanism to determine such key information would thus provide increased user experience, better washing performance, and reduced consumption; for this reason, we present here a data-driven soft sensor that exploits physical measurements already available on board a commercial VA-WM to provide an estimate of the load typology through a machine-learning-based statistical model of the process. The proposed method is able to work in a resource-constrained environment such as the firmware of a VA-WM. [ABSTRACT FROM AUTHOR]

Deep Learning approaches have revolutionized in the past decade the field of Computer Vision and, as a consequence, they are having a major impact in Industry 4.0 applications like automatic defect classification. Nevertheless, additional data, beside the image/video itself, is typically never exploited in a defect classification module: this aspect, given the abundance of data in data-intensive manufacturing environments (like semiconductor manufacturing) represents a missed opportunity. In this work we present a use case related to Scanning Electron Microscope (SEM) images where we exploit a Bayesian approach to improve defect classification. We validate our approach on a real-world case study and by employing modern Deep Learning architectures for classification. [ABSTRACT FROM AUTHOR]