BEGIN:VCALENDAR
VERSION:2.0 
PRODID:-/-/EN
BEGIN:VEVENT
SUMMARY:London Section: The What, Why, and How of Machine Learning
UID:213
DESCRIPTION: \n\n





















 \n\n








\n\n














LONDON SECTION - ONLINE\n\n
Please forward this email to any friends or colleages who may have an interest in the subject.\n\n
 \n\n












WEBINAR TECHNICAL PRESENTATION.
 
Our Next Presentation will be onTUESDAY  9th March 2021at 5.00PM
 \n\n






















TITLE: The What, Why, and How of Machine Learningfor Equipment Health Diagnostics  \n\n
PRESENTER:         Peter DamerCOMPANY:                   ABB\n\n
 \n\n
 \n\n








 \n\n












REGISTRATION\n\n
If you wish to attend please email to LIS@instmc.org, and a link email will be provided 48hrs before the presentation. The presentation will be means of MS Teams, this does not require a download of software, and can be viewed on any web browser. \n\n
 \n\n








 \n\n












SYNOPSIS  \n\n
This lecture presents an approach where both machine learning and good old fashioned engineering are used in perfect harmony to provide an effective approach to predictive maintenance. Online condition monitoring combined with data science relies on one of two techniques:\n\n

Detection of anomalies where online measurements deviate from normal operating behaviour
Identification of known failure characteristics where online measurements closely match a fault signature
These techniques both use a data model, the former represents “good health” and the latter captures the “data signature” present under fault conditions. Given that these two techniques are essentially the corollary of each other, the conclusion that they may be equally useful is a natural one to draw. However, in practice the former is often the best approach. This is simply because there is almost always sufficient historical data representing good health, enabling the training of the health data model. Conversely there is often no or insufficient data representing all possible failure conditions.  In this presentation, Peter will demystify Machine Learning by using analogies we all understand, from Covid symptoms to worn wheel bearings. He then shows how these principles are applied to industrial equipment, explaining how the maths works whilst leaving out the bamboozling formulae. The presentation will include a live demonstration using a realtime boiler model to simulate fault conditions.\n\n
 \n\n












BiopicWorking at ABB since 2013, Peter Damer has over thirty years working primarily as a design and commissioning engineer across manufacturing, process and utility sectors.  Holds a bachelor’s degree in Engineering Science, a Master’s degree in Process Automation and a Post Graduate Certificate in Education. A Chartered Electrical Engineer, also a certified Safety Engineer and Microsoft Professional\n\n
 \n\n








 \n\n












FUTURE EVENTS\n\n
Heads Up: Next month:  AGM +New Challenges in the post HC Era.\n\n
We aim to have a technical presentation on the second Tuesday of each month until June 2021. At the present time we are planning only for webinar events.  If you have a suitable presentation, or feel that there is a subject we should be covering, please contact our Programme Secretary , Henry Downes on Henry.Downes@InstMC.org. As and when conditions allow we will recommence face to face lectures, and reinstigate our social programme. Malcolm GeorgeActing Chairman \n\n
 \n\n




































\n\n













\n\n













\n\n













\n\n
 \n\n
 \n\n
 \n\n
DTSTART:20210309T170000Z
DTEND:20210309T170000Z
LOCATION:ONLINE
END:VEVENT
END:VCALENDAR