Augmenting fielded test systems with diagnostic reasoner technology

Harris, M. Dormer; Helton, A.; Sharone, D.

doi:10.1109/autest.2007.4374210

Cited by 5 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Performing in-depth analysis using machine learning techniques or other decision support software in the field during operations is the goal of many smart AME advocates. In both government and industry, it is a commonly accepted idea that advanced statistical analysis with feedback will reduce the time it takes to perform maintenance [2] [7]. The potential benefits are well known, and many avenues are being explored, but the architectural framework does not exist for it to be adequately employed across multiple platforms.…”

Section: Expanding To a Live Environmentmentioning

confidence: 99%

Analyzing Automated Maintenance architectures to provide flexible smart maintenance capabilities

Kirkos

Meseroll

Edwards

et al. 2008

2008 Ieee Autotestcon

View full text Add to dashboard Cite

The computing architecture of an Automated Maintenance Environment (AME) can foster or stunt the ability to employ smart maintenance practices. With software decision support technologies becoming more readily available, there is ample opportunity for diagnostic enhancement within AME's. Data analysis practices and informed decision support are enabled by an enhanced technical infrastructure, which includes data accessibility, common data formats, and sufficient computational capacity. This paper will explain the results of the IDATS team's efforts in creating a lab architecture to facilitate diagnostic analysis and how it further applies in a functioning smart AME. Additionally, the paper will address the computing and decision support software requirements needed to perform efficient maintenance practices within the US Navy, as well as provide an analysis of the strengths and shortcomings of existing Navy AME architectures. Potential change-points or limitations resulting from the existing AME architecture will be identified. This analysis will recognize common data points within the AME that can be improved or augmented to benefit multiple aircraft platforms with the capability of enhanced common diagnostic techniques. The steps toward realizing a common, flexible maintenance capability were investigated by analyzing the structure of all current and indevelopment Navy aircraft AMEs, including the data storage format, the movement of data, and the network infrastructure. A common Navy AME architecture will facilitate timely insertion of new and enhanced diagnostic techniques as they are developed, providing the fleet with intelligent support equipment at the flight line.

show abstract

Section: Expanding To a Live Environmentmentioning

confidence: 99%