USING BACK-PROPAGATION NETWORK TO PREDICT CONTACT RESISTANCE OF LOAD BREAK SWITCH
碩士 === 大同大學 === 工程管理碩士在職專班 === 101 === The Load Break Switch (LBS) is an economical type of protection switch, which is applicable to general facilities protection. With arcing chamber and power fuse, LBS, an over current protection for the main transformer, can open up normal load and shut down o...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2013
|
Online Access: | http://ndltd.ncl.edu.tw/handle/86372814948880800100 |
id |
ndltd-TW-101TTU05031038 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-101TTU050310382015-10-13T22:52:06Z http://ndltd.ncl.edu.tw/handle/86372814948880800100 USING BACK-PROPAGATION NETWORK TO PREDICT CONTACT RESISTANCE OF LOAD BREAK SWITCH 應用倒傳遞神經網路於負載啟斷開關接觸電阻預測之研究 Yng-Ying Sun 孫瑛霙 碩士 大同大學 工程管理碩士在職專班 101 The Load Break Switch (LBS) is an economical type of protection switch, which is applicable to general facilities protection. With arcing chamber and power fuse, LBS, an over current protection for the main transformer, can open up normal load and shut down overload current when system is in the normal state. In the other way, the abnormal/ over rated current will cause the contacts of LBS burn-out and lead to next stage equipment damage. To ensure product quality and safety use of electricity, the product has to go through the test of Voltage Dips and Short interruptions. Since there is no qualified agency for the test of Voltage Dips and Short interruptions in Taiwan, the examination therefore has to be undertaken abroad with lengthy time, higher cost, and complicated application process. This study will use the BPN approach to establish the model of numerical values of electrical impedance to predict product life cycle and the qualified products will then reduce the failure rate for oversea examination. The selection of influence factors and quality performance of this BPN network model is based on the long term basis of data collection by the equipment engineers in the case company and using the collected data to establish BPN learning model to predict two thousand times contact resistance experiment result. Normally, contact resistance experiment required two weeks per thousand times, therefore, the establishment of learning model will save the experimental time and provide a more stable quality of the device for certification. According to the International Electro Technical Commission (IEC) specification, mechanical operations qualification test only required one thousand switching with less than 20% changes of resistance value. However, if there is fault current go through the device, the mechanical operation switching will be abnormal, and normally, the feeder switching will trip the protection relay and interrupt the power. Since there is no protective mechanism in load break switches, it is necessary to forecast two thousand times mechanical operation resistance value. BPN applies to predict the non-linear time series processing and it possesses high speed calculating, fast reviewing, great learning precision, fault tolerance capability, and etc. to carry out studies and analysis of data so as to predict the load break switch resistance value changes process. Hence, the BPN approach is selected in this study to predict LBS resistance value changes. This study adopts actual data from industry and establishes BPN network learning model with 75 data. The other 20 data will be used to verify the completion learning model and the result shows the learning model’s accuracy reaches 98.87%, which indicates this learning model can be definitely used as one of the crucial factors in the management decision making process in this case company. Ming-Yung Wang Yung-Jen Lin 王明庸 林永仁 2013 學位論文 ; thesis 79 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 大同大學 === 工程管理碩士在職專班 === 101 === The Load Break Switch (LBS) is an economical type of protection switch, which is applicable to general facilities protection. With arcing chamber and power fuse, LBS, an over current protection for the main transformer, can open up normal load and shut down overload current when system is in the normal state. In the other way, the abnormal/ over rated current will cause the contacts of LBS burn-out and lead to next stage equipment damage. To ensure product quality and safety use of electricity, the product has to go through the test of Voltage Dips and Short interruptions. Since there is no qualified agency for the test of Voltage Dips and Short interruptions in Taiwan, the examination therefore has to be undertaken abroad with lengthy time, higher cost, and complicated application process.
This study will use the BPN approach to establish the model of numerical values of electrical impedance to predict product life cycle and the qualified products will then reduce the failure rate for oversea examination. The selection of influence factors and quality performance of this BPN network model is based on the long term basis of data collection by the equipment engineers in the case company and using the collected data to establish BPN learning model to predict two thousand times contact resistance experiment result. Normally, contact resistance experiment required two weeks per thousand times, therefore, the establishment of learning model will save the experimental time and provide a more stable quality of the device for certification.
According to the International Electro Technical Commission (IEC) specification, mechanical operations qualification test only required one thousand switching with less than 20% changes of resistance value. However, if there is fault current go through the device, the mechanical operation switching will be abnormal, and normally, the feeder switching will trip the protection relay and interrupt the power. Since there is no protective mechanism in load break switches, it is necessary to forecast two thousand times mechanical operation resistance value.
BPN applies to predict the non-linear time series processing and it possesses high speed calculating, fast reviewing, great learning precision, fault tolerance capability, and etc. to carry out studies and analysis of data so as to predict the load break switch resistance value changes process. Hence, the BPN approach is selected in this study to predict LBS resistance value changes. This study adopts actual data from industry and establishes BPN network learning model with 75 data. The other 20 data will be used to verify the completion learning model and the result shows the learning model’s accuracy reaches 98.87%, which indicates this learning model can be definitely used as one of the crucial factors in the management decision making process in this case company.
|
author2 |
Ming-Yung Wang |
author_facet |
Ming-Yung Wang Yng-Ying Sun 孫瑛霙 |
author |
Yng-Ying Sun 孫瑛霙 |
spellingShingle |
Yng-Ying Sun 孫瑛霙 USING BACK-PROPAGATION NETWORK TO PREDICT CONTACT RESISTANCE OF LOAD BREAK SWITCH |
author_sort |
Yng-Ying Sun |
title |
USING BACK-PROPAGATION NETWORK TO PREDICT CONTACT RESISTANCE OF LOAD BREAK SWITCH |
title_short |
USING BACK-PROPAGATION NETWORK TO PREDICT CONTACT RESISTANCE OF LOAD BREAK SWITCH |
title_full |
USING BACK-PROPAGATION NETWORK TO PREDICT CONTACT RESISTANCE OF LOAD BREAK SWITCH |
title_fullStr |
USING BACK-PROPAGATION NETWORK TO PREDICT CONTACT RESISTANCE OF LOAD BREAK SWITCH |
title_full_unstemmed |
USING BACK-PROPAGATION NETWORK TO PREDICT CONTACT RESISTANCE OF LOAD BREAK SWITCH |
title_sort |
using back-propagation network to predict contact resistance of load break switch |
publishDate |
2013 |
url |
http://ndltd.ncl.edu.tw/handle/86372814948880800100 |
work_keys_str_mv |
AT yngyingsun usingbackpropagationnetworktopredictcontactresistanceofloadbreakswitch AT sūnyīngyīng usingbackpropagationnetworktopredictcontactresistanceofloadbreakswitch AT yngyingsun yīngyòngdàochuándìshénjīngwǎnglùyúfùzàiqǐduànkāiguānjiēchùdiànzǔyùcèzhīyánjiū AT sūnyīngyīng yīngyòngdàochuándìshénjīngwǎnglùyúfùzàiqǐduànkāiguānjiēchùdiànzǔyùcèzhīyánjiū |
_version_ |
1718081870013399040 |