Gian Antonio Susto, A. Schirru, S. Pampuri, D. Pagano, S. McLoone, A. Beghi
{"title":"A predictive maintenance system for integral type faults based on support vector machines: An application to ion implantation","authors":"Gian Antonio Susto, A. Schirru, S. Pampuri, D. Pagano, S. McLoone, A. Beghi","doi":"10.1109/COASE.2013.6653952","DOIUrl":"https://doi.org/10.1109/COASE.2013.6653952","url":null,"abstract":"In semiconductor fabrication processes, effective management of maintenance operations is fundamental to decrease costs associated with failures and downtime. Predictive Maintenance (PdM) approaches, based on statistical methods and historical data, are becoming popular for their predictive capabilities and low (potentially zero) added costs. We present here a PdM module based on Support Vector Machines for prediction of integral type faults, that is, the kind of failures that happen due to machine usage and stress of equipment parts. The proposed module may also be employed as a health factor indicator. The module has been applied to a frequent maintenance problem in semiconductor manufacturing industry, namely the breaking of the filament in the ion-source of ion-implantation tools. The PdM has been tested on a real production dataset.","PeriodicalId":191166,"journal":{"name":"2013 IEEE International Conference on Automation Science and Engineering (CASE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123038735","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}
{"title":"Wireless wearable multi-sensory system for monitoring of sleep apnea and other cardiorespiratory disorders","authors":"Woranat Wongdhamma, T. Le, S. Bukkapatnam","doi":"10.1109/CoASE.2013.6654074","DOIUrl":"https://doi.org/10.1109/CoASE.2013.6654074","url":null,"abstract":"This paper reports the development of a wireless, wearable, multi-sensor suite and its integration as part of a smart garment for point-of-care diagnosis of cardiorespiratory disorders with a particular focus on sleep apnea screening. The suite is designed to synchronously gather 3-lead vectorcardiogram signals sampled at 250 Hz from a custom-designed hardware, heart sound signals gathered at 250 Hz from a MEMs sound sensor (model MT-201 from ADinstrument), digitized oxygen saturation (SPO2) signals at 250 Hz (model PC-60B from St. Alban Medical), and respiratory signals. The signals are transmitted to a nearby processing and graphical visualization unit via a Bluetooth module (model RN-800S-CB from Roving Network). The system can serve as an out-of-center Type III sleep apnea screening device. Extensive tests suggest that the quality of the signals is comparable to that of commercial and standard recording systems. While this unit offers enhanced functionality in terms of simultaneous electro- and phonocardiorespiratory analysis, the power consumption rates and diagnostic performance are comparable to those of commercial point-of-care wireless medical devices for cardiorespiratory diagnosis.","PeriodicalId":191166,"journal":{"name":"2013 IEEE International Conference on Automation Science and Engineering (CASE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124260733","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}
Masashi Okuma, T. Emaru, Y. Hoshino, Yukinori Kobayashi
{"title":"A novel nonlinear compensator based on digital acceleration control","authors":"Masashi Okuma, T. Emaru, Y. Hoshino, Yukinori Kobayashi","doi":"10.1109/CoASE.2013.6653889","DOIUrl":"https://doi.org/10.1109/CoASE.2013.6653889","url":null,"abstract":"In this paper, we propose two nonlinear compensators for controlling mechanical systems. The high nonlinearity of typical multi-body mechanical systems arises form the effects of gravity, friction, joint interactions, and other factors. Such non-linearity limits the accuracy of the proportional-integral-derivative (PID) control, but does not affect the integrity of the digital acceleration control (DAC). Previously, we proposed a control system combining PID and DAC (PID-DAC) and confirmed its validity. However, PID-DAC is of limited accuracy when controlling an object with high acceleration. To solve this problem, we modified DAC to compensate for nonlinear effects only. Essentially, the new compensators compensate for nonlinearity while PID controls the object position. The effectiveness of the proposed methods is investigated through experiments on a two-link robot manipulator. The controller performs well in the presence of nonlinear forces, and is easily applied to PID to enhance object control.","PeriodicalId":191166,"journal":{"name":"2013 IEEE International Conference on Automation Science and Engineering (CASE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125064079","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}
{"title":"Improved knot-tying methods for autonomous robot surgery","authors":"Der-Lin Chow, W. Newman","doi":"10.1109/CoASE.2013.6653955","DOIUrl":"https://doi.org/10.1109/CoASE.2013.6653955","url":null,"abstract":"Robot Assisted Minimally Invasive Surgery has been successfully used in many surgical procedures. With merits of fast recovery and reduced risk of infection, it has gained favor among patients and surgeons. However, due to the confined workspace for dexterity, poor endoscopic 2D vision, and sensorless instruments, robotic surgical procedures such as suture-pulling, knot-tying and needle-driving are tedious and time consuming. Ideally, these operations would be automated, leading to faster, more efficient robotic surgery. This paper presents two knot-tying methods suitable for automation. Experimental performance is comparable to human speeds with the potential for significant speed-up.","PeriodicalId":191166,"journal":{"name":"2013 IEEE International Conference on Automation Science and Engineering (CASE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116145898","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}
{"title":"Storage yard management for transshipment ports","authors":"Xinjia Jiang, L. Lee, E. P. Chew, K. Tan","doi":"10.1109/CoASE.2013.6653898","DOIUrl":"https://doi.org/10.1109/CoASE.2013.6653898","url":null,"abstract":"In transshipment ports, the loading and unloading activities are both concentrated and inevitably happen at the same time. Thus the storage yard management is more challenging than that in a general import-export container terminal. Our studies on storage yard management can be divided into three phases, namely yard sectioning, yard template planning and space allocation. This paper focuses on the short-term space allocation from an integrated perspective, where all yard resources are considered. A flexible space-sharing strategy is used in this study to improve the space utilization while storing the containers according to their destination vessel for a faster loading process. A MIP model is formulated for space allocation considering the storage space, yard cranes and prime movers. Numerical experiments show that the MIP model can effectively control violations in short-term space allocation. And the flexible space-sharing strategy can increase the storage capacity and make the storage yard more adaptable to fluctuations caused by vessel delay.","PeriodicalId":191166,"journal":{"name":"2013 IEEE International Conference on Automation Science and Engineering (CASE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122784639","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}
{"title":"The information framework for material behavior representation","authors":"U. Roy, Bicheng Zhu, Daniel J. Rice","doi":"10.1109/CoASE.2013.6654034","DOIUrl":"https://doi.org/10.1109/CoASE.2013.6654034","url":null,"abstract":"The paper provides details on the information structure and implementation of the material's behavioral model. An example has been included that illustrates the suggested approach to model the behavior. The intent of the paper is to provide an informational tool to the designers and other stakeholders at different lifecycle phases of a product to assist them in making rational decisions about material behavior and its usage.","PeriodicalId":191166,"journal":{"name":"2013 IEEE International Conference on Automation Science and Engineering (CASE)","volume":"79 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114040183","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}
{"title":"Learning to locomote: Action sequences and switching boundaries","authors":"Rowland O'Flaherty, M. Egerstedt","doi":"10.1109/CoASE.2013.6653937","DOIUrl":"https://doi.org/10.1109/CoASE.2013.6653937","url":null,"abstract":"This paper presents a hybrid control strategy for learning the switching boundaries between primitive controllers that maximize the translational movements of complex locomoting systems. Through this abstraction, the algorithm learns an optimal action for each boundary condition instead of one for each discretized state and action of the system, as is typically in the case of machine learning. This hybridification of the problem mitigates the “curse of dimensionality”. The effectiveness of the learning algorithm is demonstrated on both a simulated system and on a physical robotic system. In both cases, the algorithm is able to learn the hybrid control strategy that maximizes the forward translational movement of the system without the need for human involvement.","PeriodicalId":191166,"journal":{"name":"2013 IEEE International Conference on Automation Science and Engineering (CASE)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117094487","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}
{"title":"Decentralized failure diagnosis of stochastic discrete event systems","authors":"Jun Chen, Ratnesh Kumar","doi":"10.1109/CoASE.2013.6653924","DOIUrl":"https://doi.org/10.1109/CoASE.2013.6653924","url":null,"abstract":"In decentralized diagnosis the system behavior is monitored at multiple local sites, each possessing its own sensors and making its own local diagnosis decision without communicating with other sites. In this paper we formalize the decentralized diagnosis for stochastic DESs by introducing S-Codiagnosability, supplementing the notion of SS-Codiagnosability first introduced by Liu, et al. We also give polynomial algorithms for checking (i) necessity and sufficiency of SS-Codiagnosability, (ii) sufficiency of S-Codiagnosability, and (iii) necessity as well as sufficiency of S-Codiagnosability, which requires an additional notion of equivalence of probabilistic automata.","PeriodicalId":191166,"journal":{"name":"2013 IEEE International Conference on Automation Science and Engineering (CASE)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128750139","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}
{"title":"Assembly planning for planar structures of a brick wall pattern with rectangular modular robots","authors":"Jungwon Seo, Mark H. Yim, Vijay R. Kumar","doi":"10.1109/CoASE.2013.6653996","DOIUrl":"https://doi.org/10.1109/CoASE.2013.6653996","url":null,"abstract":"We present an assembly planning algorithm for constructing planar structures out of rectangular modular robots which can dock to each other to form a brick wall pattern. The algorithm is provably correct and complete, and efficiently computes an assembly sequence in O(m2) time, where m is the number of robots needed to be assembled in a goal structure. The assembly plan incorporates reachability and collision constraints and supports distributed assembly so that multiple robots can be docked to a growing structure without centralized coordination. Simulations and experiments will be also presented.","PeriodicalId":191166,"journal":{"name":"2013 IEEE International Conference on Automation Science and Engineering (CASE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128716615","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}
Yan Lu, Dezhen Song, Yiliang Xu, A. G. Amitha Perera, Sangmin Oh
{"title":"Automatic building exterior mapping using multilayer feature graphs","authors":"Yan Lu, Dezhen Song, Yiliang Xu, A. G. Amitha Perera, Sangmin Oh","doi":"10.1109/CoASE.2013.6653887","DOIUrl":"https://doi.org/10.1109/CoASE.2013.6653887","url":null,"abstract":"We develop algorithms that can assist robot to perform building exterior mapping, which is important for building energy retrofitting. In this task, a robot needs to identify building facades in its localization and mapping process, which in turn can be used to assist robot navigation. Existing localization and mapping algorithms rely on low level features such as point clouds and line segments and cannot be directly applied to our task. We attack this problem by employing a multiple layer feature graph (MFG), which contains five different features ranging from raw key points to planes and vanishing points in 3D, in an extended Kalman filter (EKF) framework. We analyze how errors are generated and propagated in the MFG construction process, and then apply MFG data as observations for the EKF to map building facades. We have implemented and tested our MFG-EKF method at three different sites. Experimental results show that building facades are successfully constructed in modern urban environments with mean relative errors of plane depth less than 4.66%.","PeriodicalId":191166,"journal":{"name":"2013 IEEE International Conference on Automation Science and Engineering (CASE)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124607492","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}