Detecting the defects in silicon wafers generated by semiconductor manufacturing is essential for quality assurance, and requires the acquisition and accurate classification of high-resolution images by scanning electron microscopy. However, owing to the difficulty of automation, the classification process is costly and its efficiency must be improved. To improve the classification accuracy and the cost of creating a classifier, which are the main bottlenecks of conventional technology, we propose a deep convolutional neural network (CNN) based on the VGG16 architecture, and perform appropriate data augmentations on training images. The CNN was successfully trained on a very small number of images, and achieved high defect classification accuracy.
{"title":"Minimization of CNN Training Data by using Data Augmentation for Inline Defect Classification","authors":"Akihiro Fujishiro, Yoshikazu Nagamura, Tatsuya Usami, Masao Inoue","doi":"10.1109/ISSM51728.2020.9377504","DOIUrl":"https://doi.org/10.1109/ISSM51728.2020.9377504","url":null,"abstract":"Detecting the defects in silicon wafers generated by semiconductor manufacturing is essential for quality assurance, and requires the acquisition and accurate classification of high-resolution images by scanning electron microscopy. However, owing to the difficulty of automation, the classification process is costly and its efficiency must be improved. To improve the classification accuracy and the cost of creating a classifier, which are the main bottlenecks of conventional technology, we propose a deep convolutional neural network (CNN) based on the VGG16 architecture, and perform appropriate data augmentations on training images. The CNN was successfully trained on a very small number of images, and achieved high defect classification accuracy.","PeriodicalId":270309,"journal":{"name":"2020 International Symposium on Semiconductor Manufacturing (ISSM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129539569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-15DOI: 10.1109/ISSM51728.2020.9377529
S. Majima, A. Hatano, S. Takada
Demand of heterogeneous integration has increased for high-performance computing devices, utilizing panel level packaging and high-resolution lithography. We have developed a flexible direct imaging tool and a high-speed chip position measurement tool for Fan-Out Panel Level Packaging (FO-PLP). The imaging tool is capable of 2/2μm Line/Space resolution, chip displacement exposure compensation and includes an Auto-Wiring function which can expose patterns to connect individual chips independent of position displacement. With measurement tool throughput of 30 Panel Per Hour (PPH), the combination of these tools enables high-throughput adaptive patterning for cost effective heterogeneous integration.
{"title":"High- Throughput Direct Adaptive Imaging System with Novel Measurement Tool for Heterogeneous Integration","authors":"S. Majima, A. Hatano, S. Takada","doi":"10.1109/ISSM51728.2020.9377529","DOIUrl":"https://doi.org/10.1109/ISSM51728.2020.9377529","url":null,"abstract":"Demand of heterogeneous integration has increased for high-performance computing devices, utilizing panel level packaging and high-resolution lithography. We have developed a flexible direct imaging tool and a high-speed chip position measurement tool for Fan-Out Panel Level Packaging (FO-PLP). The imaging tool is capable of 2/2μm Line/Space resolution, chip displacement exposure compensation and includes an Auto-Wiring function which can expose patterns to connect individual chips independent of position displacement. With measurement tool throughput of 30 Panel Per Hour (PPH), the combination of these tools enables high-throughput adaptive patterning for cost effective heterogeneous integration.","PeriodicalId":270309,"journal":{"name":"2020 International Symposium on Semiconductor Manufacturing (ISSM)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130774363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-15DOI: 10.1109/ISSM51728.2020.9377518
O. Sakai, Y. Mizui, Kyosuke Nobuto, S. Miyagi
It is quite frequent that a factorial fabrication process includes very complex systems, leading to difficulties in its regulation, estimation and prediction. To overcome these difficulties, causality in the complex systems is a key issue, which has not been frequently stressed but is of importance for effective performance of machine learning. One of the examples with such complexity is plasma and its chemistry, where they are in processes of dry etching and plasma chemical vapor deposition. So far, we successfully visualized the complexities using graphs or networks, where nodes represent elements and edges imply interactions between them. In this study, focusing on silane (SiH4) and methane (CH4) low-temperature molecular plasma chemistry, we clarify roles of species in the chemical reaction network, like reactants, intermediates and products, where a species is a node in this species network and a reactant-product pair is an edge. This distinction is straightforward for selection of reactants as input and products as output variables. We also show and discuss another network, reaction network, in which a reactant-product pair is an edge and its size is so huge that its network statistics is categorized by complex network science. By visualizing and analyzing a complex chemical reaction network in molecular plasma, we obtain useful information for parameter regulation in real processes and also identification of input/output variables for machine learning of a given process.
{"title":"Analysis of Visualized Complex Reaction Network in Low- Temperature Molecular Plasma","authors":"O. Sakai, Y. Mizui, Kyosuke Nobuto, S. Miyagi","doi":"10.1109/ISSM51728.2020.9377518","DOIUrl":"https://doi.org/10.1109/ISSM51728.2020.9377518","url":null,"abstract":"It is quite frequent that a factorial fabrication process includes very complex systems, leading to difficulties in its regulation, estimation and prediction. To overcome these difficulties, causality in the complex systems is a key issue, which has not been frequently stressed but is of importance for effective performance of machine learning. One of the examples with such complexity is plasma and its chemistry, where they are in processes of dry etching and plasma chemical vapor deposition. So far, we successfully visualized the complexities using graphs or networks, where nodes represent elements and edges imply interactions between them. In this study, focusing on silane (SiH4) and methane (CH4) low-temperature molecular plasma chemistry, we clarify roles of species in the chemical reaction network, like reactants, intermediates and products, where a species is a node in this species network and a reactant-product pair is an edge. This distinction is straightforward for selection of reactants as input and products as output variables. We also show and discuss another network, reaction network, in which a reactant-product pair is an edge and its size is so huge that its network statistics is categorized by complex network science. By visualizing and analyzing a complex chemical reaction network in molecular plasma, we obtain useful information for parameter regulation in real processes and also identification of input/output variables for machine learning of a given process.","PeriodicalId":270309,"journal":{"name":"2020 International Symposium on Semiconductor Manufacturing (ISSM)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131003746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-15DOI: 10.1109/ISSM51728.2020.9377502
Nicky Lu
After 60 years of development efforts since the 1960s to the current Giga-/Tera-Scale-Integration or System-on-a-Chip era [1]–[3], it is expected that Monolithic Silicon IC products using 2-nm CMOS devices will appear soon. The subsequent challenge is whether more novel device structures using heterogeneous materials and 3D-structures will be invented to realize manufacturable 1-nm ICs. On the other hand, through 20 years of efforts since 1999, many Heterogeneous Integration (HI) [4]–[6] products, each of which is composed of silicon and non-silicon materials/ dice/chiplets, diversified devices/circuits, innovative architectures and multi-dimensional arrangements of dice and other components inside either Chip-package or Module, have been increasingly emerging, especially recently benefiting from a strong driving force stimulated by the IEEE HI Roadmap unveiled in 2018 [5]. This paper presents an exciting, powerful and new Trend of Semiconductors, Intelligent Grand Scale Integration (IGSI), which is optimally utilizing Mixed Integration of Monolithic and HI Technologies (Si-4.0 [6]) with embedded 3A's (Algorithm, Architecture and AI) Design-Intelligences. A key target of IGSI technologies is to drive much higher energy efficiency of managing electronic information for more-effective/ intelligent future systems with better performance, lower power, higher reliability and smaller form-factor than those of our current systems. One effective way as proposed is to network multiple Self-Smart MicroSystems (S-SmS) each of which is designed with 3A's to a complete system level which can handle huge data processing smartly in its own compact multi-dimensional form factor like in a versatile solid-state micro-universe which has abundant self-contained intelligent functions with maximized speed-power efficiency due to close proximity of electronic/photonic/ micro-mechanical operations. It is projected that in such an S-SmS each Joule (energy unit) be able to operate more than 10^20 devices per die per joule allowed by thermodynamics (on the other hand, its performance can reach over hundreds of thousands of TOPS - Tera Operations Per Second) inside and/or across these MicroSystems to complete the final system need. Then how powerful a future system can be by networking enough S-SmS units and furthermore how many unprecedented and unexpected applications will be unleashed! To use AI computing systems as an example, it is expected that S-SmS be quickly applied to AI's edge, device or wearable applications. Moreover, just like the experiences of migrating from a Mainframe computer to networked PC Servers, Data servers used in AI Clouds may use such a networked S-SmS architecture to build large systems in order to optimize the energy efficiency and heat dissipation. The trend equally adds values to system's transformation and optimization in Autonomous Car areas, Industrial 4.0 Factory areas, Telecommunication and Computing areas and so forth.
{"title":"A New Smart-MicroSystems Age Enabled by Heterogeneous Integration of Silicon-Centric and AI Technologies-My Personal View","authors":"Nicky Lu","doi":"10.1109/ISSM51728.2020.9377502","DOIUrl":"https://doi.org/10.1109/ISSM51728.2020.9377502","url":null,"abstract":"After 60 years of development efforts since the 1960s to the current Giga-/Tera-Scale-Integration or System-on-a-Chip era [1]–[3], it is expected that Monolithic Silicon IC products using 2-nm CMOS devices will appear soon. The subsequent challenge is whether more novel device structures using heterogeneous materials and 3D-structures will be invented to realize manufacturable 1-nm ICs. On the other hand, through 20 years of efforts since 1999, many Heterogeneous Integration (HI) [4]–[6] products, each of which is composed of silicon and non-silicon materials/ dice/chiplets, diversified devices/circuits, innovative architectures and multi-dimensional arrangements of dice and other components inside either Chip-package or Module, have been increasingly emerging, especially recently benefiting from a strong driving force stimulated by the IEEE HI Roadmap unveiled in 2018 [5]. This paper presents an exciting, powerful and new Trend of Semiconductors, Intelligent Grand Scale Integration (IGSI), which is optimally utilizing Mixed Integration of Monolithic and HI Technologies (Si-4.0 [6]) with embedded 3A's (Algorithm, Architecture and AI) Design-Intelligences. A key target of IGSI technologies is to drive much higher energy efficiency of managing electronic information for more-effective/ intelligent future systems with better performance, lower power, higher reliability and smaller form-factor than those of our current systems. One effective way as proposed is to network multiple Self-Smart MicroSystems (S-SmS) each of which is designed with 3A's to a complete system level which can handle huge data processing smartly in its own compact multi-dimensional form factor like in a versatile solid-state micro-universe which has abundant self-contained intelligent functions with maximized speed-power efficiency due to close proximity of electronic/photonic/ micro-mechanical operations. It is projected that in such an S-SmS each Joule (energy unit) be able to operate more than 10^20 devices per die per joule allowed by thermodynamics (on the other hand, its performance can reach over hundreds of thousands of TOPS - Tera Operations Per Second) inside and/or across these MicroSystems to complete the final system need. Then how powerful a future system can be by networking enough S-SmS units and furthermore how many unprecedented and unexpected applications will be unleashed! To use AI computing systems as an example, it is expected that S-SmS be quickly applied to AI's edge, device or wearable applications. Moreover, just like the experiences of migrating from a Mainframe computer to networked PC Servers, Data servers used in AI Clouds may use such a networked S-SmS architecture to build large systems in order to optimize the energy efficiency and heat dissipation. The trend equally adds values to system's transformation and optimization in Autonomous Car areas, Industrial 4.0 Factory areas, Telecommunication and Computing areas and so forth.","PeriodicalId":270309,"journal":{"name":"2020 International Symposium on Semiconductor Manufacturing (ISSM)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134580813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-15DOI: 10.1109/ISSM51728.2020.9377497
Hitoshi Yamano, Hiroaki Shimizu, S. Kanaya, Tomoyuki Miyao, Aki Hirai, N. Ono
Polymer properties are usually more difficult to predict than those of small molecules due to them forming superstructures. In this work, we aimed at finding a versatile approach to predict multiple polymer properties using imperfect data with missing values. The dataset was hierarchically clustered on the basis of two independent factors: polymer properties and polymer structures. In polymer property-based clustering, visualizing relations of polymers was found to be an effective way of estimating the difficulty of polymer property prediction. In polymer structure-based clustering, each cluster could be formed based on the structural features. Thus, the clustering contributed to understanding structural characteristics of monomer unit structures. In addition to analyzing the data set in an unsupervised manner, we constructed polymer properties prediction models based solely on the information of monomer unit structures. Partial least squared (PLS) regression models could predict density, glass transition temperature and dissolution parameter with high accuracy. We also propose approach to evaluate obtained model using data already prepared.
{"title":"Predicting and considering properties of general polymers using incomplete dataset","authors":"Hitoshi Yamano, Hiroaki Shimizu, S. Kanaya, Tomoyuki Miyao, Aki Hirai, N. Ono","doi":"10.1109/ISSM51728.2020.9377497","DOIUrl":"https://doi.org/10.1109/ISSM51728.2020.9377497","url":null,"abstract":"Polymer properties are usually more difficult to predict than those of small molecules due to them forming superstructures. In this work, we aimed at finding a versatile approach to predict multiple polymer properties using imperfect data with missing values. The dataset was hierarchically clustered on the basis of two independent factors: polymer properties and polymer structures. In polymer property-based clustering, visualizing relations of polymers was found to be an effective way of estimating the difficulty of polymer property prediction. In polymer structure-based clustering, each cluster could be formed based on the structural features. Thus, the clustering contributed to understanding structural characteristics of monomer unit structures. In addition to analyzing the data set in an unsupervised manner, we constructed polymer properties prediction models based solely on the information of monomer unit structures. Partial least squared (PLS) regression models could predict density, glass transition temperature and dissolution parameter with high accuracy. We also propose approach to evaluate obtained model using data already prepared.","PeriodicalId":270309,"journal":{"name":"2020 International Symposium on Semiconductor Manufacturing (ISSM)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114565792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-15DOI: 10.1109/ISSM51728.2020.9377507
F. Chalvin, Y. Miyamae, K. Sakamoto
In this paper we propose a method to track the degradation of GaN transistors during high temperature switching operation. Using a Long Short-Term Memory (LSTM) based recurrent neural network (RNN) encoder decoder architecture we are able to determine whether the device is still working normally or if its behavior changed compared to the initial one.
{"title":"Ageing Monitoring of GaN Transistors using Recurrent Neural Networks","authors":"F. Chalvin, Y. Miyamae, K. Sakamoto","doi":"10.1109/ISSM51728.2020.9377507","DOIUrl":"https://doi.org/10.1109/ISSM51728.2020.9377507","url":null,"abstract":"In this paper we propose a method to track the degradation of GaN transistors during high temperature switching operation. Using a Long Short-Term Memory (LSTM) based recurrent neural network (RNN) encoder decoder architecture we are able to determine whether the device is still working normally or if its behavior changed compared to the initial one.","PeriodicalId":270309,"journal":{"name":"2020 International Symposium on Semiconductor Manufacturing (ISSM)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124296390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-15DOI: 10.1109/ISSM51728.2020.9377531
Y. Inaki, Hisamori Inagawa, S. Fujii, I. Masada, T. Nawata, Y. Kanechika
Aluminum nitride (AlN) powder has has high thermal conductivity and is expected as filler for heat dissipation materials. Fine AlN powder after removing coarse particles by classification is well dispersed into resin, and it is possible to achieve high filling rate and high thermal conductivity. Further by improving the affinity to the resin by surface treatment, voids at interface between AlN particles and resin would decrease, and thus AlN in cured resin composite is hardly hydrolyzed. Classification and surface treatment can improve the filling property of AlN into resin and increase the reliability of the resin materials containing AlN.
{"title":"AlN filler for high thermal conductive resin materials","authors":"Y. Inaki, Hisamori Inagawa, S. Fujii, I. Masada, T. Nawata, Y. Kanechika","doi":"10.1109/ISSM51728.2020.9377531","DOIUrl":"https://doi.org/10.1109/ISSM51728.2020.9377531","url":null,"abstract":"Aluminum nitride (AlN) powder has has high thermal conductivity and is expected as filler for heat dissipation materials. Fine AlN powder after removing coarse particles by classification is well dispersed into resin, and it is possible to achieve high filling rate and high thermal conductivity. Further by improving the affinity to the resin by surface treatment, voids at interface between AlN particles and resin would decrease, and thus AlN in cured resin composite is hardly hydrolyzed. Classification and surface treatment can improve the filling property of AlN into resin and increase the reliability of the resin materials containing AlN.","PeriodicalId":270309,"journal":{"name":"2020 International Symposium on Semiconductor Manufacturing (ISSM)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121316654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-15DOI: 10.1109/ISSM51728.2020.9377514
Y. Daigo, Toru Watanabe, A. Ishiguro, S. Ishii, M. Kushibe, Yoshikazu Moriyama
Homo-epitaxial 4H-SiC films were grown using high speed wafer rotation vertical CVD method, and the correlation between repeatability of the film properties and wafer temperature which is directly monitored by pyrometers was investigated. When the single zone control of the wafer temperature was performed, a large fluctuation of the thickness and doping concentration was observed in iteration of the epitaxial growth. This fluctuation of the thickness and doping concentration corresponded to that of the temperature distribution on wafers, although no significant fluctuation of apparent power introduced to the heaters was observed. On the other hand, when the double zone control of the wafer temperature was performed, the fluctuation of the thickness, doping concentration and temperature distribution was considerably decreased. The large fluctuation of the temperature distribution by the single zone control seems to be due to the variation of the crystalline quality of the 4H-SiC wafers.
{"title":"Impact of precise temperature control for 4H-SiC epitaxy on large diameter wafers","authors":"Y. Daigo, Toru Watanabe, A. Ishiguro, S. Ishii, M. Kushibe, Yoshikazu Moriyama","doi":"10.1109/ISSM51728.2020.9377514","DOIUrl":"https://doi.org/10.1109/ISSM51728.2020.9377514","url":null,"abstract":"Homo-epitaxial 4H-SiC films were grown using high speed wafer rotation vertical CVD method, and the correlation between repeatability of the film properties and wafer temperature which is directly monitored by pyrometers was investigated. When the single zone control of the wafer temperature was performed, a large fluctuation of the thickness and doping concentration was observed in iteration of the epitaxial growth. This fluctuation of the thickness and doping concentration corresponded to that of the temperature distribution on wafers, although no significant fluctuation of apparent power introduced to the heaters was observed. On the other hand, when the double zone control of the wafer temperature was performed, the fluctuation of the thickness, doping concentration and temperature distribution was considerably decreased. The large fluctuation of the temperature distribution by the single zone control seems to be due to the variation of the crystalline quality of the 4H-SiC wafers.","PeriodicalId":270309,"journal":{"name":"2020 International Symposium on Semiconductor Manufacturing (ISSM)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115539223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-15DOI: 10.1109/ISSM51728.2020.9377508
Peter Barar, K. K. Gan, Joe Lee
The evolution in manufacturing automation has helped manufacturers across all industries to become more efficient and profitable. Today, it is expected that many operations within a modern production plant to include some level of automation to drive production efficiency and to reduce human errors. As we step into the era of smart manufacturing, this expectation will continue to grow, not only in the scope of automation, but also its sophistication. With key enabling technologies such as Artificial Intelligence (AI), engineering applications on the factory floor are becoming more intelligent and autonomous. This paper highlights examples in the semiconductor manufacturing industry on how AI can further push the envelope in automation allowing manufacturers to achieve results faster and be even more efficient in process control.
{"title":"Taking Engineering Automation to the Next Level with Artificial Intelligence","authors":"Peter Barar, K. K. Gan, Joe Lee","doi":"10.1109/ISSM51728.2020.9377508","DOIUrl":"https://doi.org/10.1109/ISSM51728.2020.9377508","url":null,"abstract":"The evolution in manufacturing automation has helped manufacturers across all industries to become more efficient and profitable. Today, it is expected that many operations within a modern production plant to include some level of automation to drive production efficiency and to reduce human errors. As we step into the era of smart manufacturing, this expectation will continue to grow, not only in the scope of automation, but also its sophistication. With key enabling technologies such as Artificial Intelligence (AI), engineering applications on the factory floor are becoming more intelligent and autonomous. This paper highlights examples in the semiconductor manufacturing industry on how AI can further push the envelope in automation allowing manufacturers to achieve results faster and be even more efficient in process control.","PeriodicalId":270309,"journal":{"name":"2020 International Symposium on Semiconductor Manufacturing (ISSM)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115955875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：