Subscribe to DSC Newsletter

Hello,

I am in the field of Electrical and Electronic devices  like UPS and would like to predict which devices  (UPS ) are prone to failures.

We have real time data from devices coming to us in terms of voltage, current, statuses of various sections of the UPS. There are actually 3 type of variables which can lead to failures - Input Mains (device is generally made self sufficient to cut off in case there is a huge surge in input side), Output side (where load is, however device is quite robust to take care of load shorting, etc,), Internal component failure (which is generally a primary cause).

But internal components are electronic devices like transistors, chips, in which it is very difficult to attribute a reason for failure. Mostly, the failure of reason is known only after the failure has occurred. Can this sort of failure be predicted before hand that this device is more prone to failure? What sort of few analytical techniques can be looked at?

Presently, Manufacturers look for making each of the components more robust by doing their Stress testing, however there is much less practice to attribute the reason of device failure to external factors. Let us say, out of 10000 devices in the market 100 fail in a year. These 100 are in different conditions as compared to others which have not failed. Can these external reasons be attributed to device failures?

I think this study to be much similar to understanding why a mobile phone failed or Television failed..

Any direction in this area is much appreciated

Thanks in advance!

Tags: Device failures, Electronics, IoT, failure prediction

Views: 526

Reply to This

Videos

  • Add Videos
  • View All

© 2019   Data Science Central ®   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service