Product category:
Bearings
News Release from: SKF UK | Subject: BearingDetective
Edited by the Engineeringtalk Editorial
Team on 22 July 2004
Expert system predicts bearing failures
BearingDetective is an advanced "expert" system for identifying bearing failure modes.
BearingDetective is an advanced "expert" system for identifying bearing failure modes The system will help customers prevent recurring bearing damage and failures, thus saving on the time and costs associated with unplanned machine stoppages
This article was originally published on Engineeringtalk on 21 Feb 2001 at 8.00am (UK)
Related stories
Laser system ensures more precise belt alignment
The SKF BeltAlign precision laser tool achieves belt alignment accuracy by placing a laser transmitter/receptor magnetically within the groove of each pulley being aligned
SKF launches big range of parts for machine tools
A complete package of products, aimed specifically at machine tool builders and users, has been unveiled by SKF Engineering Products Limited.
As SKF BearingDetective is a web-enabled system, it allows SKF engineers all over the world to remotely assist in bearing failure analysis.
SKF's BearingDetective is a decision support system that allows consistent, fast and accurate assessments of rolling bearing damage or failure.
It is a knowledge-based system that searches its information base and offers a number of possible causes of the bearing damage found in individual situations.
The causes are ranked, with the highest probability ranked first.
The system overcomes the shortcomings of previous expert systems, which are structured as decision trees with symptoms shown branching off to possible causes.
Instead, SKF's BearingDetective is structured from possible causes to symptoms.
This structure, combined with the degree of uncertainty about possible failure states, achieves a more accurate analysis of the physical phenomena that occur during bearing service life.
At the core of the system is a wealth of knowledge gathered from basic rolling bearing principles to practical engineering and application results.
The probabilistic network is a visual network in which nodes are connected by causal relationships, and probability calculations applied.
The network for bearing failure analysis has four node categories; conditions, internal mechanisms, failure modes and observed symptoms.
The combination of these nodes ensures all possible factors are evaluated including bearing speeds and loads, corrosion, sliding contact and lubricant film disruption. Request a free brochure from SKF UK ...
• SKF UK: contact details and other news
• Email this article to a colleague
• Register for the free Engineeringtalk email newsletter
• Engineeringtalk Home Page
