End-to-End Automated Analytics for CBM+

End-to-End Condition Based Maintenance Plus (CBM+) requires careful balances between data generation, filtering, preprocessing, compression, secure communications, cleansing/validation, persistence, categorization, classification, analysis, summarization, reporting and distribution. Often, the conditions themselves demand flexibility within the CBM+ framework to adapt for data volumes, traffic priority, and critical impact on safety and operations. Intelligent services distributed across disparate operational environments and varying data schemas enable collaborative applications to strike the balance needed for effective operation of CBM+ systems. Open standards in a service oriented architecture enable cooperating processes to provide synergy and expand opportunities for discovery and insight to diagnostic procedures and predictive maintenance.

Too often, CBM+ has focused on the data structures and detailed component structure models resulting in overly rigid designs that are labor intensive and have difficulty accommodating change brought on by varying platform configurations and new insights from analysis. This paper discusses how automating data analysis for CBM+ is possible in a distributed, open standards based SOA environment from the embedded applications on monitored platforms through intermediate processing / communications gateways to the enterprise repository and among collaborative service providers and consumers. In particular, we draw from experience gained in US Army and commercial automotive applications to highlight challenges and possible solutions. We discuss data synchronization strategies, distributing cooperative analytics, data compression and summarization strategies, how automated analysis of CBM data can improve OLTP and OLAP management and performance strategies for CBM+, and how to simplify SOA implementations for quick adoption while retaining open standards and flexibility. We also discuss driving factors for CBM+ framework requirements and their affect on selecting among alternative implementation strategies.

By: Nathaniel Mills

Published in: RC24799 in 2009

LIMITED DISTRIBUTION NOTICE:

This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.

rc24799.pdf

Questions about this service can be mailed to reports@us.ibm.com .