Pub Date : 2011-10-13DOI: 10.1109/CASE.2011.6042412
B. Addad, S. Amari, J. Lesage, B. Denis
In this paper, we present a study that deals with response time of Networked Automation Systems (NAS). The main aim is to verify experimentally the validity of an analytic formulation of NAS response time, obtained in our past investigations [12]. To that purpose, we carried out, under different conditions, a lot of measurements on a laboratory facility. Each time, we compared the observed measures to the predicted values. Overall, the study reveals clear agreement between the real observations and the theoretic predictions of our formula. It therefore promotes the formula to be used confidently for NAS response time evaluation while avoiding tedious and onerous experiments.
{"title":"Measures vs. analytic evaluation of response time of Networked Automation Systems","authors":"B. Addad, S. Amari, J. Lesage, B. Denis","doi":"10.1109/CASE.2011.6042412","DOIUrl":"https://doi.org/10.1109/CASE.2011.6042412","url":null,"abstract":"In this paper, we present a study that deals with response time of Networked Automation Systems (NAS). The main aim is to verify experimentally the validity of an analytic formulation of NAS response time, obtained in our past investigations [12]. To that purpose, we carried out, under different conditions, a lot of measurements on a laboratory facility. Each time, we compared the observed measures to the predicted values. Overall, the study reveals clear agreement between the real observations and the theoretic predictions of our formula. It therefore promotes the formula to be used confidently for NAS response time evaluation while avoiding tedious and onerous experiments.","PeriodicalId":236208,"journal":{"name":"2011 IEEE International Conference on Automation Science and Engineering","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121523927","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 : 2011-10-13DOI: 10.1109/CASE.2011.6042506
Jinchao Liu, Z. Fan, S. Olsen, K. H. Christensen, J. K. Kristensen
Visual sensing in arc welding has become more and more important, but still remains challenging because of the harsh environment with extremely strong illumination from the arc. This paper presents a low-cost camera-based sensor system, without using external Illumination, but nevertheless able to sense and model the weld pool. Central is a carefully selected optical filtering as well as an active contour-based tracking of the weld pool boundary. The system is able to extract the 2D shape of the weld pool in real time. The reported experiments show the feasibility of this approach.
{"title":"Weld pool visual sensing without external illumination","authors":"Jinchao Liu, Z. Fan, S. Olsen, K. H. Christensen, J. K. Kristensen","doi":"10.1109/CASE.2011.6042506","DOIUrl":"https://doi.org/10.1109/CASE.2011.6042506","url":null,"abstract":"Visual sensing in arc welding has become more and more important, but still remains challenging because of the harsh environment with extremely strong illumination from the arc. This paper presents a low-cost camera-based sensor system, without using external Illumination, but nevertheless able to sense and model the weld pool. Central is a carefully selected optical filtering as well as an active contour-based tracking of the weld pool boundary. The system is able to extract the 2D shape of the weld pool in real time. The reported experiments show the feasibility of this approach.","PeriodicalId":236208,"journal":{"name":"2011 IEEE International Conference on Automation Science and Engineering","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126327782","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 : 2011-10-13DOI: 10.1109/CASE.2011.6042529
Lalit Patil, L. Srinivas, K. Murthy, D. Dutta, Rachuri Sudarsan
Corporations view sustainable manufacturing as a mandate for competitiveness to put them at an advantage with consumers all over the world. This paper focuses on the need for a decision support solution that transforms the current time-consuming and reactive (post-design) sustainability assessment into a proactive approach available in the early phases of product design. Such a solution should focus primarily on the key area of target cascading, evaluation, and management, which does not exist for sustainability metrics, such as carbon footprint. It is important that the handling of sustainability be compatible with handling of these traditional attributes. The emphasis on traditional attributes, such as weight, is necessary, because it is one of the most important and cost-effective ways to improve fuel efficiency and reduce greenhouse gases. In this paper, we discuss several challenges in addressing this problem and propose the major components of an approach to enable target cascading of sustainability attributes. We describe the the multiple requirements on the development of the approach and raise important research questions that need to be addressed.
{"title":"Requirements for the development of a decision-support solution for sustainability target cascading","authors":"Lalit Patil, L. Srinivas, K. Murthy, D. Dutta, Rachuri Sudarsan","doi":"10.1109/CASE.2011.6042529","DOIUrl":"https://doi.org/10.1109/CASE.2011.6042529","url":null,"abstract":"Corporations view sustainable manufacturing as a mandate for competitiveness to put them at an advantage with consumers all over the world. This paper focuses on the need for a decision support solution that transforms the current time-consuming and reactive (post-design) sustainability assessment into a proactive approach available in the early phases of product design. Such a solution should focus primarily on the key area of target cascading, evaluation, and management, which does not exist for sustainability metrics, such as carbon footprint. It is important that the handling of sustainability be compatible with handling of these traditional attributes. The emphasis on traditional attributes, such as weight, is necessary, because it is one of the most important and cost-effective ways to improve fuel efficiency and reduce greenhouse gases. In this paper, we discuss several challenges in addressing this problem and propose the major components of an approach to enable target cascading of sustainability attributes. We describe the the multiple requirements on the development of the approach and raise important research questions that need to be addressed.","PeriodicalId":236208,"journal":{"name":"2011 IEEE International Conference on Automation Science and Engineering","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116490182","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 : 2011-10-13DOI: 10.1109/CASE.2011.6042518
Hyun-Jung Kim, Tae-Eog Lee
We examine a scheduling problem regarding cluster tools for small lot production. Most work on scheduling of cluster tools assumed large identical wafer lots, and examined cyclic scheduling that repeats identical work cycles. However, nowadays, the lot size tends to be extremely small, even being only 5–8 wafers whereas conventional lots have 25 identical wafers. It is not reasonable to use cyclic scheduling for such small lot production because the number of identical work cycles is too small as compared to the lengths of the starting and closing transient periods. We therefore examine a new scheduling method for cluster tools with ready time constraints on the chambers and the robot, from which the resources are freed from processing the preceding lot. To solve this scheduling problem, we develop a Petri net model which is a graphical and mathematical method for a discrete event dynamic system. Based on the Petri net model, we develop a mixed integer programming (MIP) model and a branch & bound (B&B) algorithm for determining an optimal schedule that minimizes the makespan. For a single-armed tool, the algorithm can efficiently solve the scheduling problem for lots with up to 25 wafers. However, for a dual-armed tool, the computation time grows quickly as the number of wafers increases. Therefore, we propose an approximate method that schedules only the first few wafers non-cyclically and the remaining wafers cyclically. From experiments, we conclude that the approximate method provides good solutions with less than a 1% error. The proposed methods can be used even when full lots of 25 wafers are frequently switched.
{"title":"Scheduling of cluster tools with ready time constraints for small lot production","authors":"Hyun-Jung Kim, Tae-Eog Lee","doi":"10.1109/CASE.2011.6042518","DOIUrl":"https://doi.org/10.1109/CASE.2011.6042518","url":null,"abstract":"We examine a scheduling problem regarding cluster tools for small lot production. Most work on scheduling of cluster tools assumed large identical wafer lots, and examined cyclic scheduling that repeats identical work cycles. However, nowadays, the lot size tends to be extremely small, even being only 5–8 wafers whereas conventional lots have 25 identical wafers. It is not reasonable to use cyclic scheduling for such small lot production because the number of identical work cycles is too small as compared to the lengths of the starting and closing transient periods. We therefore examine a new scheduling method for cluster tools with ready time constraints on the chambers and the robot, from which the resources are freed from processing the preceding lot. To solve this scheduling problem, we develop a Petri net model which is a graphical and mathematical method for a discrete event dynamic system. Based on the Petri net model, we develop a mixed integer programming (MIP) model and a branch & bound (B&B) algorithm for determining an optimal schedule that minimizes the makespan. For a single-armed tool, the algorithm can efficiently solve the scheduling problem for lots with up to 25 wafers. However, for a dual-armed tool, the computation time grows quickly as the number of wafers increases. Therefore, we propose an approximate method that schedules only the first few wafers non-cyclically and the remaining wafers cyclically. From experiments, we conclude that the approximate method provides good solutions with less than a 1% error. The proposed methods can be used even when full lots of 25 wafers are frequently switched.","PeriodicalId":236208,"journal":{"name":"2011 IEEE International Conference on Automation Science and Engineering","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133771234","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 : 2011-10-13DOI: 10.1109/CASE.2011.6042515
Denis C. Pinha, M. H. D. Queiroz, J. Cury
Supervisory Control Theory (SCT) allows for the automatic synthesis of non-blocking supervisors capable of ensuring all and only those sequences of events that meet the specifications for discrete event systems. For a job shop problem, it's possible to obtain an optimal supervisor capable of satisfying resource, production routine and deadline specifications, as well as of providing all viable scheduling solutions, by using a timed SCT extension. This paper investigates the feasibility of applying SCT to production planning and logistics modeling - applications rendered possible through a method for synthesizing schedules via an innovative approach to resource modeling; through the incremental synthesis of production routines and deadlines; and through a bisection method for minimizing total production time and job-specific lead times. The method is applied to the scheduling of activities at a repair shipyard, namely, the activities of the five main resources involved in the execution of ten job orders. The paper concludes with the presentation of a computational tool developed to integrate production planning and a tool for automatic supervisory synthesis so as to facilitate handling of the interface by users not familiar with SCT.
{"title":"Optimal scheduling of a repair shipyard based on Supervisory Control Theory","authors":"Denis C. Pinha, M. H. D. Queiroz, J. Cury","doi":"10.1109/CASE.2011.6042515","DOIUrl":"https://doi.org/10.1109/CASE.2011.6042515","url":null,"abstract":"Supervisory Control Theory (SCT) allows for the automatic synthesis of non-blocking supervisors capable of ensuring all and only those sequences of events that meet the specifications for discrete event systems. For a job shop problem, it's possible to obtain an optimal supervisor capable of satisfying resource, production routine and deadline specifications, as well as of providing all viable scheduling solutions, by using a timed SCT extension. This paper investigates the feasibility of applying SCT to production planning and logistics modeling - applications rendered possible through a method for synthesizing schedules via an innovative approach to resource modeling; through the incremental synthesis of production routines and deadlines; and through a bisection method for minimizing total production time and job-specific lead times. The method is applied to the scheduling of activities at a repair shipyard, namely, the activities of the five main resources involved in the execution of ten job orders. The paper concludes with the presentation of a computational tool developed to integrate production planning and a tool for automatic supervisory synthesis so as to facilitate handling of the interface by users not familiar with SCT.","PeriodicalId":236208,"journal":{"name":"2011 IEEE International Conference on Automation Science and Engineering","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131662306","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 : 2011-10-13DOI: 10.1109/CASE.2011.6042462
Hao Ding, G. Reissig, Dominic Gross, O. Stursberg
One of the fundamental problems in the field of robotic motion planning is to safely and efficiently drive the end effector of a robotic manipulator to a specified goal position. Here, safety refers to the requirement that the robotic manipulator must have no collision with surrounding obstacles, and efficiency requires that some predefined cost function is minimized. In addition, kinematic and dynamic constraints have to be satisfied. These requirements lead to non-convex optimization problems, which may be approximated by mixed-integer linear programs (MILPs). The solution of the latter, however, is often intolerably complex due to a huge number of binary decision variables. In the present paper, we consider motion planning scenarios with polyhedral obstacles and velocity constraints for the joint positions of the robotic manipulator. We provide a geometric result whose application leads to MILPs with drastically reduced numbers of binary decision variables. Computational efficiency is demonstrated for two- and three-link manipulators interacting with obstacles, where the number of simplex steps during the MILP solution is reduced by a factor of roughly 200 over previous methods. We also demonstrate the application of the proposed method to an industrial robot.
{"title":"Mixed-integer programming for optimal path planning of robotic manipulators","authors":"Hao Ding, G. Reissig, Dominic Gross, O. Stursberg","doi":"10.1109/CASE.2011.6042462","DOIUrl":"https://doi.org/10.1109/CASE.2011.6042462","url":null,"abstract":"One of the fundamental problems in the field of robotic motion planning is to safely and efficiently drive the end effector of a robotic manipulator to a specified goal position. Here, safety refers to the requirement that the robotic manipulator must have no collision with surrounding obstacles, and efficiency requires that some predefined cost function is minimized. In addition, kinematic and dynamic constraints have to be satisfied. These requirements lead to non-convex optimization problems, which may be approximated by mixed-integer linear programs (MILPs). The solution of the latter, however, is often intolerably complex due to a huge number of binary decision variables. In the present paper, we consider motion planning scenarios with polyhedral obstacles and velocity constraints for the joint positions of the robotic manipulator. We provide a geometric result whose application leads to MILPs with drastically reduced numbers of binary decision variables. Computational efficiency is demonstrated for two- and three-link manipulators interacting with obstacles, where the number of simplex steps during the MILP solution is reduced by a factor of roughly 200 over previous methods. We also demonstrate the application of the proposed method to an industrial robot.","PeriodicalId":236208,"journal":{"name":"2011 IEEE International Conference on Automation Science and Engineering","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130653935","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 : 2011-10-13DOI: 10.1109/CASE.2011.6042508
M. P. Cabasino, A. Giua, C. Seatzu, Antonio Solinas, Katiuscia Zedda
In this paper we consider the brake system of a vehicle whose wheels are equipped with Anti-lock Braking Systems (ABS). We assume that the sensors that are responsible of the activation of the ABS are subject to faults. We first show how such a system can be modeled using labeled Petri nets and the notion of concurrent composition. Then, we show how fault diagnosis and diagnosability analysis can be performed on such a system using appropriate techniques based on Petri nets.
{"title":"Fault diagnosis of an ABS system using Petri nets","authors":"M. P. Cabasino, A. Giua, C. Seatzu, Antonio Solinas, Katiuscia Zedda","doi":"10.1109/CASE.2011.6042508","DOIUrl":"https://doi.org/10.1109/CASE.2011.6042508","url":null,"abstract":"In this paper we consider the brake system of a vehicle whose wheels are equipped with Anti-lock Braking Systems (ABS). We assume that the sensors that are responsible of the activation of the ABS are subject to faults. We first show how such a system can be modeled using labeled Petri nets and the notion of concurrent composition. Then, we show how fault diagnosis and diagnosability analysis can be performed on such a system using appropriate techniques based on Petri nets.","PeriodicalId":236208,"journal":{"name":"2011 IEEE International Conference on Automation Science and Engineering","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131994609","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 : 2011-10-13DOI: 10.1109/CASE.2011.6042453
F. Serna, C. Catalán, A. Blesa, J. M. Rams, J. Colom
This work presents a case study showing the design of a glass cutting machine tool. This design is the first technological demonstrator of the COSME platform, its guidelines and tools. It represents an approach to simplify the design of control software in the manufacturing context, allowing to shorten time-to-market and aggregating value-added features.
{"title":"Control software design for a cutting glass machine tool based on the COSME platform. Case study","authors":"F. Serna, C. Catalán, A. Blesa, J. M. Rams, J. Colom","doi":"10.1109/CASE.2011.6042453","DOIUrl":"https://doi.org/10.1109/CASE.2011.6042453","url":null,"abstract":"This work presents a case study showing the design of a glass cutting machine tool. This design is the first technological demonstrator of the COSME platform, its guidelines and tools. It represents an approach to simplify the design of control software in the manufacturing context, allowing to shorten time-to-market and aggregating value-added features.","PeriodicalId":236208,"journal":{"name":"2011 IEEE International Conference on Automation Science and Engineering","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132199605","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 : 2011-10-13DOI: 10.1109/CASE.2011.6042399
Quanshen Mai, Dongzhi He, Yibin Hou, Zhangqin Huang
The speech enhancement is one of the effective techniques to solve speech degraded by noise. In this paper a fast speech enhancement method for noisy speech signals is presented, which is based on improved Kalman filtering. The conventional Kalman filter algorithm for speech enhancement needs to calculate the parameters of AR (auto-regressive) model, and perform a lot of matrix operations, which usually is non-adaptive. The speech enhancement algorithm proposed in this paper eliminates the matrix operations and reduces the calculating time by only constantly updating the first value of state vector X(n). We design a coefficient factor for adaptive filtering, to automatically amend the estimation of environmental noise by the observation data. Simulation results show that the fast adaptive algorithm using Kalman filtering is effective for speech enhancement.
{"title":"A fast adaptive Kalman filtering algorithm for speech enhancement","authors":"Quanshen Mai, Dongzhi He, Yibin Hou, Zhangqin Huang","doi":"10.1109/CASE.2011.6042399","DOIUrl":"https://doi.org/10.1109/CASE.2011.6042399","url":null,"abstract":"The speech enhancement is one of the effective techniques to solve speech degraded by noise. In this paper a fast speech enhancement method for noisy speech signals is presented, which is based on improved Kalman filtering. The conventional Kalman filter algorithm for speech enhancement needs to calculate the parameters of AR (auto-regressive) model, and perform a lot of matrix operations, which usually is non-adaptive. The speech enhancement algorithm proposed in this paper eliminates the matrix operations and reduces the calculating time by only constantly updating the first value of state vector X(n). We design a coefficient factor for adaptive filtering, to automatically amend the estimation of environmental noise by the observation data. Simulation results show that the fast adaptive algorithm using Kalman filtering is effective for speech enhancement.","PeriodicalId":236208,"journal":{"name":"2011 IEEE International Conference on Automation Science and Engineering","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132490540","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 : 2011-10-13DOI: 10.1109/CASE.2011.6042425
S. Pampuri, A. Schirru, G. Fazio, G. Nicolao
In semiconductor manufacturing, the state of the art for wafer quality control is based on product monitoring and feedback control loops; the related metrology operations, that usually involve scanning electron microscopes, are particularly cost-intensive and time-consuming. It is therefore not possible to evaluate every wafer: commonly, a small subset of a productive lot is measured at the metrology station and delegated to represent the whole lot. Virtual Metrology (VM) methodologies aim to obtain reliable estimates of metrology results without actually performing measurement operations; this goal is usually achieved by means of statistical models, linking process data and context information to target measurements. In this paper, we tackle two of the most important issues in VM: (i) regression in high dimensional spaces where few variables are meaningful, and (ii) data heterogeneity caused by inhomogeneous production and equipment logistics. We propose a hierarchical framework based on ℓ1-penalized machine learning techniques and solved by means of multitask learning strategies. The proposed methodology is validated on actual process and measurement data from the semiconductor manufacturing industry.
{"title":"Multilevel Lasso applied to Virtual Metrology in semiconductor manufacturing","authors":"S. Pampuri, A. Schirru, G. Fazio, G. Nicolao","doi":"10.1109/CASE.2011.6042425","DOIUrl":"https://doi.org/10.1109/CASE.2011.6042425","url":null,"abstract":"In semiconductor manufacturing, the state of the art for wafer quality control is based on product monitoring and feedback control loops; the related metrology operations, that usually involve scanning electron microscopes, are particularly cost-intensive and time-consuming. It is therefore not possible to evaluate every wafer: commonly, a small subset of a productive lot is measured at the metrology station and delegated to represent the whole lot. Virtual Metrology (VM) methodologies aim to obtain reliable estimates of metrology results without actually performing measurement operations; this goal is usually achieved by means of statistical models, linking process data and context information to target measurements. In this paper, we tackle two of the most important issues in VM: (i) regression in high dimensional spaces where few variables are meaningful, and (ii) data heterogeneity caused by inhomogeneous production and equipment logistics. We propose a hierarchical framework based on ℓ1-penalized machine learning techniques and solved by means of multitask learning strategies. The proposed methodology is validated on actual process and measurement data from the semiconductor manufacturing industry.","PeriodicalId":236208,"journal":{"name":"2011 IEEE International Conference on Automation Science and Engineering","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114995291","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：