An intelligent model for residual life prediction of thyristor
Bhargava, Cherry ; Singh, Jagdeep LU
and Sharma, Pardeep Kumar
(2019)
In International Journal of Engineering and Advanced Technology
8(5).
p.1862-1866
- Abstract
Modern age is the age of integration, where millions of electronic components are integrated and installed on a single chip, to minimize the size of device and automatically increases the speed. But, as a greater number of components are placed on a single device, reliability becomes a concern issue, as failure of one component can degrade the complete device. From dimmer to high voltage power transmission, thyristors are widely used. The failure of thyristor can be proven dangerous for mankind, so the reliability prediction of thyristor is highly desirable. This paper is based on the accelerated life testing based experimental technique for reliability assessment. An intelligent model is designed using artificial intelligence... (More)
Modern age is the age of integration, where millions of electronic components are integrated and installed on a single chip, to minimize the size of device and automatically increases the speed. But, as a greater number of components are placed on a single device, reliability becomes a concern issue, as failure of one component can degrade the complete device. From dimmer to high voltage power transmission, thyristors are widely used. The failure of thyristor can be proven dangerous for mankind, so the reliability prediction of thyristor is highly desirable. This paper is based on the accelerated life testing based experimental technique for reliability assessment. An intelligent model is designed using artificial intelligence techniques i.e. ANN, Fuzzy and ANFIS and comparative analysis is conducted to estimate the most accurate technique. Fuzzy based Graphical User Interface (GUI) is framed which informs the user about the live status of thyristor under various environmental conditions. The intelligent techniques are validated using experimental technique. An error analysis is conducted to predict the most accurate and reliable system for residual life prediction of thyristor. Out of all prediction techniques, ANFIS has the highest accuracy i.e. 95.3%, whereas ANN and Fuzzy inference system has accuracy range 86.1% and 89.2% respectively.
(Less)
- author
- Bhargava, Cherry
; Singh, Jagdeep
LU
and Sharma, Pardeep Kumar
- organization
- publishing date
- 2019-06-01
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Accelerated life testing, Artificial intelligence, Graphical user interface, Reliability prediction, Thyristor
- in
- International Journal of Engineering and Advanced Technology
- volume
- 8
- issue
- 5
- pages
- 5 pages
- publisher
- Blue Eyes Intelligence Engineering and Sciences Publication
- external identifiers
-
- scopus:85069928264
- ISSN
- 2249-8958
- language
- English
- LU publication?
- yes
- id
- 378cd982-9344-4f15-94c3-8c50af73add4
- date added to LUP
- 2019-08-28 13:55:40
- date last changed
- 2022-04-26 05:11:40
@article{378cd982-9344-4f15-94c3-8c50af73add4,
abstract = {{<p>Modern age is the age of integration, where millions of electronic components are integrated and installed on a single chip, to minimize the size of device and automatically increases the speed. But, as a greater number of components are placed on a single device, reliability becomes a concern issue, as failure of one component can degrade the complete device. From dimmer to high voltage power transmission, thyristors are widely used. The failure of thyristor can be proven dangerous for mankind, so the reliability prediction of thyristor is highly desirable. This paper is based on the accelerated life testing based experimental technique for reliability assessment. An intelligent model is designed using artificial intelligence techniques i.e. ANN, Fuzzy and ANFIS and comparative analysis is conducted to estimate the most accurate technique. Fuzzy based Graphical User Interface (GUI) is framed which informs the user about the live status of thyristor under various environmental conditions. The intelligent techniques are validated using experimental technique. An error analysis is conducted to predict the most accurate and reliable system for residual life prediction of thyristor. Out of all prediction techniques, ANFIS has the highest accuracy i.e. 95.3%, whereas ANN and Fuzzy inference system has accuracy range 86.1% and 89.2% respectively.</p>}},
author = {{Bhargava, Cherry and Singh, Jagdeep and Sharma, Pardeep Kumar}},
issn = {{2249-8958}},
keywords = {{Accelerated life testing; Artificial intelligence; Graphical user interface; Reliability prediction; Thyristor}},
language = {{eng}},
month = {{06}},
number = {{5}},
pages = {{1862--1866}},
publisher = {{Blue Eyes Intelligence Engineering and Sciences Publication}},
series = {{International Journal of Engineering and Advanced Technology}},
title = {{An intelligent model for residual life prediction of thyristor}},
volume = {{8}},
year = {{2019}},
}