AURA-Alert: The use of Binary Associative Memories for Condition Monitoring Applications

Research output: Contribution to conferencePaper

Standard

AURA-Alert: The use of Binary Associative Memories for Condition Monitoring Applications. / Austin, Jim; Jackson, Tom; Hodge, Victoria Jane; Brewer, Grant.

2010. 699-711 Paper presented at CM 2010 The Seventh International Conference on Condition Monitoring and Machinery Failure Prevention Technologies , Stratford-upon-Avon, United Kingdom.

Research output: Contribution to conferencePaper

Harvard

Austin, J, Jackson, T, Hodge, VJ & Brewer, G 2010, 'AURA-Alert: The use of Binary Associative Memories for Condition Monitoring Applications', Paper presented at CM 2010 The Seventh International Conference on Condition Monitoring and Machinery Failure Prevention Technologies , Stratford-upon-Avon, United Kingdom, 22/06/10 - 24/06/10 pp. 699-711.

APA

Austin, J., Jackson, T., Hodge, V. J., & Brewer, G. (2010). AURA-Alert: The use of Binary Associative Memories for Condition Monitoring Applications. 699-711. Paper presented at CM 2010 The Seventh International Conference on Condition Monitoring and Machinery Failure Prevention Technologies , Stratford-upon-Avon, United Kingdom.

Vancouver

Austin J, Jackson T, Hodge VJ, Brewer G. AURA-Alert: The use of Binary Associative Memories for Condition Monitoring Applications. 2010. Paper presented at CM 2010 The Seventh International Conference on Condition Monitoring and Machinery Failure Prevention Technologies , Stratford-upon-Avon, United Kingdom.

Author

Austin, Jim ; Jackson, Tom ; Hodge, Victoria Jane ; Brewer, Grant. / AURA-Alert: The use of Binary Associative Memories for Condition Monitoring Applications. Paper presented at CM 2010 The Seventh International Conference on Condition Monitoring and Machinery Failure Prevention Technologies , Stratford-upon-Avon, United Kingdom.

Bibtex - Download

@conference{f8cfb6f176304073bda6df9b14b5123e,
title = "AURA-Alert: The use of Binary Associative Memories for Condition Monitoring Applications",
abstract = "Many Condition Monitoring (CM) domains are suffering from the dual challenges of substantial increases in the volumes of data being produced and collected by sensing systems, and the challenges of modelling increasing complexity in the remote monitored systems. These two issues give rise to the problem that fast and reliable data mining of CM data is a computationally demanding task for real-time (or near real-time) applications. We present the use of AURA [1], a class of binary associative network built on correlation matrix memories (CMMs), as an underpinning technology for efficient, scalable pattern recognition in complex and large scale CM applications. AURA is a class of binary neural network. However, it has a number of advantages over standard neural network techniques for CM pattern classification tasks. These include; high levels of data compression, one-pass training for on-line training, a scalable architecture that can be readily mapped onto high performance computing platforms, and a sound theoretical basis to determine the bounds of the system operation. We describe applications illustrating how the AURA system can be optimised to create an extremely efficient and scalable k-nearest neighbour classifier for multi-variate models. We will also illustrate how the one-pass training capability of the AURA system can be used as the basis of normality and exception modelling in complex CM systems. This latter application has particularly powerful advantages for fault detection models in domains which are characterised by highly dynamic trends or drifting in the standard operational mode of a system, and which, as a result, are extremely difficult to accurately model. The application of the AURA techniques will be illustrated with industry led exemplars in the transport and energy sectors.",
keywords = "Condition Monitoring, Neural network, AURA",
author = "Jim Austin and Tom Jackson and Hodge, {Victoria Jane} and Grant Brewer",
year = "2010",
month = jun,
day = "22",
language = "English",
pages = "699--711",
note = "CM 2010 The Seventh International Conference on Condition Monitoring and Machinery Failure Prevention Technologies ; Conference date: 22-06-2010 Through 24-06-2010",

}

RIS (suitable for import to EndNote) - Download

TY - CONF

T1 - AURA-Alert: The use of Binary Associative Memories for Condition Monitoring Applications

AU - Austin, Jim

AU - Jackson, Tom

AU - Hodge, Victoria Jane

AU - Brewer, Grant

PY - 2010/6/22

Y1 - 2010/6/22

N2 - Many Condition Monitoring (CM) domains are suffering from the dual challenges of substantial increases in the volumes of data being produced and collected by sensing systems, and the challenges of modelling increasing complexity in the remote monitored systems. These two issues give rise to the problem that fast and reliable data mining of CM data is a computationally demanding task for real-time (or near real-time) applications. We present the use of AURA [1], a class of binary associative network built on correlation matrix memories (CMMs), as an underpinning technology for efficient, scalable pattern recognition in complex and large scale CM applications. AURA is a class of binary neural network. However, it has a number of advantages over standard neural network techniques for CM pattern classification tasks. These include; high levels of data compression, one-pass training for on-line training, a scalable architecture that can be readily mapped onto high performance computing platforms, and a sound theoretical basis to determine the bounds of the system operation. We describe applications illustrating how the AURA system can be optimised to create an extremely efficient and scalable k-nearest neighbour classifier for multi-variate models. We will also illustrate how the one-pass training capability of the AURA system can be used as the basis of normality and exception modelling in complex CM systems. This latter application has particularly powerful advantages for fault detection models in domains which are characterised by highly dynamic trends or drifting in the standard operational mode of a system, and which, as a result, are extremely difficult to accurately model. The application of the AURA techniques will be illustrated with industry led exemplars in the transport and energy sectors.

AB - Many Condition Monitoring (CM) domains are suffering from the dual challenges of substantial increases in the volumes of data being produced and collected by sensing systems, and the challenges of modelling increasing complexity in the remote monitored systems. These two issues give rise to the problem that fast and reliable data mining of CM data is a computationally demanding task for real-time (or near real-time) applications. We present the use of AURA [1], a class of binary associative network built on correlation matrix memories (CMMs), as an underpinning technology for efficient, scalable pattern recognition in complex and large scale CM applications. AURA is a class of binary neural network. However, it has a number of advantages over standard neural network techniques for CM pattern classification tasks. These include; high levels of data compression, one-pass training for on-line training, a scalable architecture that can be readily mapped onto high performance computing platforms, and a sound theoretical basis to determine the bounds of the system operation. We describe applications illustrating how the AURA system can be optimised to create an extremely efficient and scalable k-nearest neighbour classifier for multi-variate models. We will also illustrate how the one-pass training capability of the AURA system can be used as the basis of normality and exception modelling in complex CM systems. This latter application has particularly powerful advantages for fault detection models in domains which are characterised by highly dynamic trends or drifting in the standard operational mode of a system, and which, as a result, are extremely difficult to accurately model. The application of the AURA techniques will be illustrated with industry led exemplars in the transport and energy sectors.

KW - Condition Monitoring

KW - Neural network

KW - AURA

M3 - Paper

SP - 699

EP - 711

T2 - CM 2010 The Seventh International Conference on Condition Monitoring and Machinery Failure Prevention Technologies

Y2 - 22 June 2010 through 24 June 2010

ER -