國立虎尾科技大學 |

Classification of High Frequency NILM Switching Transients Based on Denoising Convolutional Neural Networks.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Classification of High Frequency NILM Switching Transients Based on Denoising Convolutional Neural Networks./
Author:	Guzman, Ian.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
Description:	50 p.
Notes:	Source: Masters Abstracts International, Volume: 84-04.
Contained By:	Masters Abstracts International84-04.
Subject:	Electrical engineering. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29261637
ISBN:	9798351457871

Classification of High Frequency NILM Switching Transients Based on Denoising Convolutional Neural Networks.
Guzman, Ian.

Classification of High Frequency NILM Switching Transients Based on Denoising Convolutional Neural Networks. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 50 p.

Source: Masters Abstracts International, Volume: 84-04.

Thesis (M.E.E.)--University of Delaware, 2022.

This item must not be sold to any third party vendors.

Smart electric meters require efficient signal processing algorithms for load identification and energy disaggregation. Non-intrusive load monitoring (NILM) systems are able to extract features from the 60 Hz power signal in order to collect information about the end use of electric loads. Switching transients induced by turning on or off a certain appliance can be used to identify which appliance is connected or disconnected at a given time in the electrical network. The dataset used in this work is the most recent version of the Plug-Load Appliance Identification Dataset (PLAID) available online as a public resource/database for NILM research which contains records of voltages and currents of different electrical appliances captured at a high sampling frequency (30 kHz). This thesis presents a new approach for appliance classification with deep learning techniques by using a FIR high pass filter to remove the fundamental signal, then the short time Fourier transform (STFT) is computed for the feature extraction of high frequency start-up transients induced in the fundamental signal. The proposed convolutional neural network architecture yields a classification accuracy of 95.22% and 88.20% for twelve and sixteen different appliances, respectively.

ISBN: 9798351457871Subjects--Topical Terms:

596380
Electrical engineering.
Subjects--Index Terms:

Smart electric meters

Classification of High Frequency NILM Switching Transients Based on Denoising Convolutional Neural Networks.
LDR:02494nam a2200373 4500 001 1104645
005 20230619080110.5
006 m o d
007 cr#unu||||||||
008 230907s2022 ||||||||||||||||| ||eng d
020 $a 9798351457871
035 $a (MiAaPQ)AAI29261637
035 $a AAI29261637
040 $a MiAaPQ $c MiAaPQ
100 1 $a Guzman, Ian. $3 1413549
245 1 0 $a Classification of High Frequency NILM Switching Transients Based on Denoising Convolutional Neural Networks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 50 p.
500 $a Source: Masters Abstracts International, Volume: 84-04.
500 $a Advisor: Goossen, Keith;Barner, Kenneth.
502 $a Thesis (M.E.E.)--University of Delaware, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Smart electric meters require efficient signal processing algorithms for load identification and energy disaggregation. Non-intrusive load monitoring (NILM) systems are able to extract features from the 60 Hz power signal in order to collect information about the end use of electric loads. Switching transients induced by turning on or off a certain appliance can be used to identify which appliance is connected or disconnected at a given time in the electrical network. The dataset used in this work is the most recent version of the Plug-Load Appliance Identification Dataset (PLAID) available online as a public resource/database for NILM research which contains records of voltages and currents of different electrical appliances captured at a high sampling frequency (30 kHz). This thesis presents a new approach for appliance classification with deep learning techniques by using a FIR high pass filter to remove the fundamental signal, then the short time Fourier transform (STFT) is computed for the feature extraction of high frequency start-up transients induced in the fundamental signal. The proposed convolutional neural network architecture yields a classification accuracy of 95.22% and 88.20% for twelve and sixteen different appliances, respectively.
590 $a School code: 0060.
650 4 $a Electrical engineering. $3 596380
653 $a Smart electric meters
653 $a Efficient signal processing algorithms
653 $a Load identification
653 $a Energy disaggregation
690 $a 0544
690 $a 0800
710 2 $a University of Delaware. $b Electrical and Computer Engineering. $3 1195516
773 0 $t Masters Abstracts International $g 84-04.
790 $a 0060
791 $a M.E.E.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29261637