A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Filters
Learning in the Model Space for Cognitive Fault Diagnosis
2014
IEEE Transactions on Neural Networks and Learning Systems
The framework enables us to construct a fault library when unknown faults occur, which can be regarded as cognitive fault isolation. ...
In this paper, we develop an innovative cognitive fault diagnosis framework that tackles the above challenges. ...
ACKNOWLEDGMENT The authors would like to thank the anonymous reviewers for their constructive comments which helped improve this paper significantly. ...
doi:10.1109/tnnls.2013.2256797
pmid:24806649
fatcat:xikemvdti5aoxcc6cnxwmcip7i
Learning in the Model Space for Fault Diagnosis
[article]
2012
arXiv
pre-print
The framework enables us to construct fault library when unknown faults occur, which can be regarded as cognitive fault isolation. ...
In this paper, we have developed an innovative cognitive fault diagnosis framework that tackles the above challenges. ...
This paper will investigate fault detectability and fault isolationability using a number of approaches. ...
arXiv:1210.8291v1
fatcat:jovelaaq3rbvzhy3guqhwhcfq4
Cognitive fault diagnosis in Tennessee Eastman Process using learning in the model space
2014
Computers and Chemical Engineering
Our approach is not only applicable to fault detection, but also to fault isolation without knowing the prior information about the fault signature. ...
This approach firstly employs deterministic reservoir models to fit the multiple-input and multiple-output signals in the TE process, which map the signal space to the (reservoir) model space. ...
This paper investigates fault detectability and fault isolationability using a number of approaches. ...
doi:10.1016/j.compchemeng.2014.03.015
fatcat:n45uc4nr7rdpjbniy6zmwkemee
Disaggregated Cloud Memory with Elastic Block Management
2018
IEEE transactions on computers
The hypervisor-integrated design has several new contributions in its disaggregated memory design and implementation. ...
Second, it restructures the memory management procedures and relieves the scalability concern for supporting large virtual machines. ...
ACKNOWLEDGMENTS This work was supported by Institute for Information & communications Technology Promotion (IITP) (No.2017-0-00051) and by the R&D program of NST (grant B551179-12-04-00) and ETRI R&D program ...
doi:10.1109/tc.2018.2851565
fatcat:vcsfsqaun5ambksa32s5hixlty
Fault-Adaptive Autonomy in Systems with Learning-Enabled Components
2021
Sensors
The paper presents a novel Behavior Tree-based autonomy architecture that includes a Fault Detection and Isolation Learning-Enabled Component (FDI LEC) with an Assurance Monitor (AM) designed based on ...
The architecture implements real-time contingency-management functions using fault detection, isolation and reconfiguration subsystems. ...
The autonomy manager includes an LEC for fault detection and isolation (FDI). ...
doi:10.3390/s21186089
pmid:34577296
pmcid:PMC8470782
fatcat:ioulgmhv6vgwtlu5yp4mxubne4
Communications for Integrated Modular Avionics
2007
2007 IEEE Aerospace Conference
This network creates a command and data path between avionics modules with the software and network defining the active virtual links over an integrated physical network. ...
scalability, from a few to potentially thousands of smart and legacy sensors. 12 ...
The AFDX switch is therefore a key element in containing fault propagation in an AFDX network, by detecting and isolating babbling end stations. ...
doi:10.1109/aero.2007.352639
fatcat:vzqzyh32hrevrmah525huckgzy
Vessel-guided airway tree segmentation: A voxel classification approach
2010
Medical Image Analysis
A vessel orientation similarity measure is introduced, which indicates how similar the orientation of an airway candidate is to the orientation of the neighboring vessel. ...
We propose a voxel classification approach for the appearance model, which uses a classifier that is trained to differentiate between airway and non-airway voxels. ...
for Scientific Research (NWO), and AstraZeneca, Lund, Sweden. ...
doi:10.1016/j.media.2010.03.004
pmid:20395163
fatcat:smo77sq7bvhdpjuygbkog6alha
The symbiosis of concurrency and verification: teaching and case studies
2017
Formal Aspects of Computing
as an advanced discipline for later study. ...
Our approach lets these skills be developed without requiring students to be trained in the underlying formal mathematics. ...
We would also like to thank generations of students at Kent and, more recently, at CMU and UNLV for choosing to attend our courses and providing exceptional and constructive feedback. ...
doi:10.1007/s00165-017-0447-x
fatcat:bgcb2kyy6zfkfmek5e4cvqyuve
Model-checking CSP-Z: strategy, tool support and industrial application
2001
Science of Computer Programming
We also present a modular approach for model-checking complex CSP-Z speciÿcations, speciÿcally to verify deadlock-freedom. ...
Model-checking is now widely accepted as an e cient method for analysing computer system properties, such as deadlock-freedom. ...
We also thank Clemens Fischer and Paulo Borba for discussions about CSP-Z and FDR, and for suggestions and criticisms which helped us to improve our approach to model-checking CSP-Z. ...
doi:10.1016/s0167-6423(00)00023-x
fatcat:hj56sf522fcd5dmbynoq2znqky
A State-of-Art-Review on Machine-Learning Based Methods for PV
2021
Applied Sciences
Concentrating PV (CPV) system design parameters' optimization and efficiency improvement, anomaly detection and energy management of PV's storage systems. ...
The paper gives an overview of the most recent and promising applications of machine learning used in the field of photovoltaic systems. ...
Faults considered detectable with the proposed approach are PS, LL, OC, arc-fault and faults (LL and OC) in PS. ...
doi:10.3390/app11167550
fatcat:h2nd35zp6ngonlbyo5a3cdo2zi
Implementing cloud-based parallel metaheuristics: an overview
2018
Journal of Computer Science and Technology
Moreover, the pervasive presence of cloud computing and the emergence of programming models like MapReduce or Spark have given rise to an increasing interest in porting HPC workloads to the cloud, as is ...
Their parallel im- plementation applying HPC techniques is a common approach for efficiently using available resources to re- duce the time needed to get a good enough solution to hard-to-solve problems ...
In [5, 6] extensive analysis to detect the more critical issues and bottlenecks are presented. ...
doi:10.24215/16666038.18.e26
fatcat:lmeuxkf3lvaktg44ppahmrrzlm
A CRITICAL ANALYSIS OF METHODOLOGIES FOR DETECTION AND CLASSIFICATION OF POWER QUALITY EVENTS IN SMART GRID
2021
IEEE Access
The authors in [52] , present work focused on quantitative model based approach to FDIR (fault detection, isolation and reconfiguration). ...
For classification of voltage dip events and their causes, i.e., fault induced, transformer energization and induction motor starting and transients ( due to fault or non fault), an ES is proposed in ...
doi:10.1109/access.2021.3087016
fatcat:ax3fld2mnvgxpksur6icrqhm2u
We present our system design for both Sequentially Consistent and Total Store Ordering processors. ...
Our results show that (i) our parallel accelerators improve performance by 2-9X and 1.13-3.4X for our two lifeguards, respectively, (ii) we are 5-126X faster than the time-slicing approach required by ...
5-126X faster than the time-slicing approach required by existing techniques; and (iii) our average overheads for applications with eight threads are 51% and 28% for the two lifeguards, respectively. ...
doi:10.1145/1736020.1736051
dblp:conf/asplos/VlachosGKCFGM10
fatcat:vgmjase5afambcealu3rxlq55e
ParaLog
2010
SIGARCH Computer Architecture News
We present our system design for both Sequentially Consistent and Total Store Ordering processors. ...
Our results show that (i) our parallel accelerators improve performance by 2-9X and 1.13-3.4X for our two lifeguards, respectively, (ii) we are 5-126X faster than the time-slicing approach required by ...
5-126X faster than the time-slicing approach required by existing techniques; and (iii) our average overheads for applications with eight threads are 51% and 28% for the two lifeguards, respectively. ...
doi:10.1145/1735970.1736051
fatcat:qd7mtznrevbflb2wmbxzne7ifm
ParaLog
2010
SIGPLAN notices
We present our system design for both Sequentially Consistent and Total Store Ordering processors. ...
Our results show that (i) our parallel accelerators improve performance by 2-9X and 1.13-3.4X for our two lifeguards, respectively, (ii) we are 5-126X faster than the time-slicing approach required by ...
5-126X faster than the time-slicing approach required by existing techniques; and (iii) our average overheads for applications with eight threads are 51% and 28% for the two lifeguards, respectively. ...
doi:10.1145/1735971.1736051
fatcat:2u7bpiymlffrhlrwgvaun2xite
« Previous
Showing results 1 — 15 out of 150 results