Reconhecimento não-intrusivo de equipamentos elétricos empregando projeção vetorial
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Manancial - Repositório Digital da UFSM |
Texto Completo: | http://repositorio.ufsm.br/handle/1/8580 |
Resumo: | Electricity consumption in homes and workplaces has been growing steadily over the decades and attitudes to reduce these costs should be taken. An interesting solution is to provide to electricity users, and also to the energy company, detailed data of individual consumption of each electrical appliance. To accomplish this, researchers in the field have focused their efforts on non-intrusive methods of load identification, where a single energy meter is able to desagreggate the appliances by monitoring the total consumption of electricity of that location. Non-intrusive methods are easy to install and demand little maintenance, but require a robust method for identifying these loads. Therefore, the aim of this work is to investigate nonintrusive methods of recognition of electrical appliances to find the desaggregated consumption of these loads. Among these methods, there are the already widely used image recognition pattern methods, that now are been used also to detect electrical devices. In this paper, two of these techniques are discussed, the Principal Component Analisys, a classical method in the literature, and the Vector Projection Length, a completely new method and never used in the loads recognition field before. Current and voltage data were collected from 16 residential appliances, involving all types of loads (resistive, inductive, electronic and hybrid/other types). These data were used as training samples and test samples (unknown samples). A study is carried out using the current and also the power, independently, as load signatures. Also, a comparative analysis of the results of signatures in the time domain and time-frequency (Stowkwell transform) is conducted. As the main contributions to this work, we verified that the Vector Projection Length for load identification is quite feasible, with results up to 96% of tested appliances being identified. However, the results with Principal Component Analisys did not presented the same performance, reaching only 81% of accuracy rate. Comparing the signatures, it became clear that one should use the current in the time-frequency domain for better performance. Neither the use of power, or the time domain obtained satisfactory results of load identification when applying image pattern recognition techniques to load recognition. |
id |
UFSM-20_eab6aa1abbc2537ea3511fa2ca0152ee |
---|---|
oai_identifier_str |
oai:repositorio.ufsm.br:1/8580 |
network_acronym_str |
UFSM-20 |
network_name_str |
Manancial - Repositório Digital da UFSM |
repository_id_str |
3913 |
spelling |
2017-06-062017-06-062016-02-19BORIN, Vinicius Pozzobon. Non-intrusive electrical appliances recognition using vector projection. 2016. 158 f. Dissertação (Mestrado em Engenharia Elétrica) - Universidade Federal de Santa Maria, Santa Maria, 2016.http://repositorio.ufsm.br/handle/1/8580Electricity consumption in homes and workplaces has been growing steadily over the decades and attitudes to reduce these costs should be taken. An interesting solution is to provide to electricity users, and also to the energy company, detailed data of individual consumption of each electrical appliance. To accomplish this, researchers in the field have focused their efforts on non-intrusive methods of load identification, where a single energy meter is able to desagreggate the appliances by monitoring the total consumption of electricity of that location. Non-intrusive methods are easy to install and demand little maintenance, but require a robust method for identifying these loads. Therefore, the aim of this work is to investigate nonintrusive methods of recognition of electrical appliances to find the desaggregated consumption of these loads. Among these methods, there are the already widely used image recognition pattern methods, that now are been used also to detect electrical devices. In this paper, two of these techniques are discussed, the Principal Component Analisys, a classical method in the literature, and the Vector Projection Length, a completely new method and never used in the loads recognition field before. Current and voltage data were collected from 16 residential appliances, involving all types of loads (resistive, inductive, electronic and hybrid/other types). These data were used as training samples and test samples (unknown samples). A study is carried out using the current and also the power, independently, as load signatures. Also, a comparative analysis of the results of signatures in the time domain and time-frequency (Stowkwell transform) is conducted. As the main contributions to this work, we verified that the Vector Projection Length for load identification is quite feasible, with results up to 96% of tested appliances being identified. However, the results with Principal Component Analisys did not presented the same performance, reaching only 81% of accuracy rate. Comparing the signatures, it became clear that one should use the current in the time-frequency domain for better performance. Neither the use of power, or the time domain obtained satisfactory results of load identification when applying image pattern recognition techniques to load recognition.O consumo de eletricidade em residências e ambientes de trabalho vem crescendo continuamente ao longo das décadas e atitudes para reduzir estes gastos devem ser tomadas. Uma solução interessante é fornecer aos usuários de energia elétrica, e também à própria concessionária, dados detalhados de consumo individual de cada equipamento elétrico. Para alcançar este objetivo, pesquisadores na área tem focado seus esforços em métodos não-intrusivos de identificação das cargas (equipamentos elétricos), onde um único medidor de energia é capaz de desagregar os equipamentos através do monitoramento do consumo total de energia elétrica daquele local. Métodos não-intrusivos são de fácil instalação e de pouca manutenção, porém requerem um robusto método de identificação destas cargas. Portanto, o objetivo deste trabalho é investigar métodos não-intrusivos de reconhecimento de equipamentos elétricos para encontrar o consumo desagregado destas cargas. Dentre estes métodos, existem os já muito utilizados no reconhecimento de padrões em imagens, mas que agora tem sido também usados para detectar cargas elétricas. Neste trabalho duas destas técnicas são abordadas, a Principal Component Analisys, método clássico na literatura, e o Vector Projection Length, um método completamente novo e nunca usado no reconhecimento de cargas. Coletou-se dados de corrente e tensão de 16 equipamentos elétricos residenciais dos mais variados tipos, envolvendo todos os tipos de cargas existentes (resistivas, indutivas, eletrônicas e híbridas/outros tipos). Estes dados coletados foram utilizados como amostras de treinamento e amostras de teste (amostras desconhecidas). Como assinatura das cargas é realizado um estudo empregando corrente e também potência, de forma independente. Ainda, uma análise comparativa de resultados das assinaturas no domínio do tempo e do tempo-frequência (Transformada de Stowkwell) é conduzido. Como principais contribuições para este trabalho obteve-se que o uso do Vector Projection Length na identificação de equipamentos é bastante viável, com resultados de até 96% dos equipamentos testados sendo identificados. Já os resultados com o Principal Component Analisys ficaram abaixo de seu concorrente, atingindo 81% de taxa de acertos. Comparando as assinaturas, ficou claro que deve-se utilizar a corrente no domínio do tempo-frequência para uma melhor performance. Nem o uso da potência, nem o domínio do tempo obtiveram resultados satisfatórios de identificação quando empregados.Fundação de Amparo a Pesquisa no Estado do Rio Grande do Sulapplication/pdfporUniversidade Federal de Santa MariaPrograma de Pós-Graduação em Engenharia ElétricaUFSMBREngenharia ElétricaIdentificação de cargasReconhecimento de equipamentos elétricosReconhecimento não-intrusivoReconhecimento de padrõesTransformada de StockwellAppliances recognitionLoad identificationNon-intrusive recognitionPattern recognitionStockwell transformCNPQ::ENGENHARIAS::ENGENHARIA ELETRICAReconhecimento não-intrusivo de equipamentos elétricos empregando projeção vetorialNon-intrusive electrical appliances recognition using vector projectioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisCampos, Alexandrehttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4780200P7Barriquello, Carlos Henriquehttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4260662Z8Machado, Renatohttp://lattes.cnpq.br/2684900317624442Denardin, Gustavo Weberhttp://lattes.cnpq.br/4251219281955392Martins, Mário Lúcio da Silvahttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4707553D1http://lattes.cnpq.br/4507865873127430Borin, Vinicius Pozzobon300400000007400500300300300300300272a7edd-3c46-4479-b573-4cd18bb0b3769bbc2094-748c-4a2d-8216-9836b63d949504c94bff-bf51-45c8-99f9-66544f525c191664f8e7-ae72-4e98-9b63-07892c66826da289b01f-d097-4f5d-90a8-af90d6cfbee807184d01-606c-4427-984b-c3907dc6ba4dinfo:eu-repo/semantics/openAccessreponame:Manancial - Repositório Digital da UFSMinstname:Universidade Federal de Santa Maria (UFSM)instacron:UFSMORIGINALBORIN, VINICIUS POZZOBON.pdfapplication/pdf54955285http://repositorio.ufsm.br/bitstream/1/8580/1/BORIN%2c%20VINICIUS%20POZZOBON.pdf1ccd1eb5cc6ffbd368ac3925cb0477f6MD51TEXTBORIN, VINICIUS POZZOBON.pdf.txtBORIN, VINICIUS POZZOBON.pdf.txtExtracted texttext/plain198732http://repositorio.ufsm.br/bitstream/1/8580/2/BORIN%2c%20VINICIUS%20POZZOBON.pdf.txt738918550438805bf8430446f5415b85MD52THUMBNAILBORIN, VINICIUS POZZOBON.pdf.jpgBORIN, VINICIUS POZZOBON.pdf.jpgIM Thumbnailimage/jpeg4766http://repositorio.ufsm.br/bitstream/1/8580/3/BORIN%2c%20VINICIUS%20POZZOBON.pdf.jpgdb3c86066cf0a95d26aa1dd48aedf498MD531/85802017-07-25 11:46:46.897oai:repositorio.ufsm.br:1/8580Repositório Institucionalhttp://repositorio.ufsm.br/PUBhttp://repositorio.ufsm.br/oai/requestopendoar:39132017-07-25T14:46:46Manancial - Repositório Digital da UFSM - Universidade Federal de Santa Maria (UFSM)false |
dc.title.por.fl_str_mv |
Reconhecimento não-intrusivo de equipamentos elétricos empregando projeção vetorial |
dc.title.alternative.eng.fl_str_mv |
Non-intrusive electrical appliances recognition using vector projection |
title |
Reconhecimento não-intrusivo de equipamentos elétricos empregando projeção vetorial |
spellingShingle |
Reconhecimento não-intrusivo de equipamentos elétricos empregando projeção vetorial Borin, Vinicius Pozzobon Identificação de cargas Reconhecimento de equipamentos elétricos Reconhecimento não-intrusivo Reconhecimento de padrões Transformada de Stockwell Appliances recognition Load identification Non-intrusive recognition Pattern recognition Stockwell transform CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA |
title_short |
Reconhecimento não-intrusivo de equipamentos elétricos empregando projeção vetorial |
title_full |
Reconhecimento não-intrusivo de equipamentos elétricos empregando projeção vetorial |
title_fullStr |
Reconhecimento não-intrusivo de equipamentos elétricos empregando projeção vetorial |
title_full_unstemmed |
Reconhecimento não-intrusivo de equipamentos elétricos empregando projeção vetorial |
title_sort |
Reconhecimento não-intrusivo de equipamentos elétricos empregando projeção vetorial |
author |
Borin, Vinicius Pozzobon |
author_facet |
Borin, Vinicius Pozzobon |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Campos, Alexandre |
dc.contributor.advisor1Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4780200P7 |
dc.contributor.advisor-co1.fl_str_mv |
Barriquello, Carlos Henrique |
dc.contributor.advisor-co1Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4260662Z8 |
dc.contributor.referee1.fl_str_mv |
Machado, Renato |
dc.contributor.referee1Lattes.fl_str_mv |
http://lattes.cnpq.br/2684900317624442 |
dc.contributor.referee2.fl_str_mv |
Denardin, Gustavo Weber |
dc.contributor.referee2Lattes.fl_str_mv |
http://lattes.cnpq.br/4251219281955392 |
dc.contributor.referee3.fl_str_mv |
Martins, Mário Lúcio da Silva |
dc.contributor.referee3Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4707553D1 |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/4507865873127430 |
dc.contributor.author.fl_str_mv |
Borin, Vinicius Pozzobon |
contributor_str_mv |
Campos, Alexandre Barriquello, Carlos Henrique Machado, Renato Denardin, Gustavo Weber Martins, Mário Lúcio da Silva |
dc.subject.por.fl_str_mv |
Identificação de cargas Reconhecimento de equipamentos elétricos Reconhecimento não-intrusivo Reconhecimento de padrões Transformada de Stockwell |
topic |
Identificação de cargas Reconhecimento de equipamentos elétricos Reconhecimento não-intrusivo Reconhecimento de padrões Transformada de Stockwell Appliances recognition Load identification Non-intrusive recognition Pattern recognition Stockwell transform CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA |
dc.subject.eng.fl_str_mv |
Appliances recognition Load identification Non-intrusive recognition Pattern recognition Stockwell transform |
dc.subject.cnpq.fl_str_mv |
CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA |
description |
Electricity consumption in homes and workplaces has been growing steadily over the decades and attitudes to reduce these costs should be taken. An interesting solution is to provide to electricity users, and also to the energy company, detailed data of individual consumption of each electrical appliance. To accomplish this, researchers in the field have focused their efforts on non-intrusive methods of load identification, where a single energy meter is able to desagreggate the appliances by monitoring the total consumption of electricity of that location. Non-intrusive methods are easy to install and demand little maintenance, but require a robust method for identifying these loads. Therefore, the aim of this work is to investigate nonintrusive methods of recognition of electrical appliances to find the desaggregated consumption of these loads. Among these methods, there are the already widely used image recognition pattern methods, that now are been used also to detect electrical devices. In this paper, two of these techniques are discussed, the Principal Component Analisys, a classical method in the literature, and the Vector Projection Length, a completely new method and never used in the loads recognition field before. Current and voltage data were collected from 16 residential appliances, involving all types of loads (resistive, inductive, electronic and hybrid/other types). These data were used as training samples and test samples (unknown samples). A study is carried out using the current and also the power, independently, as load signatures. Also, a comparative analysis of the results of signatures in the time domain and time-frequency (Stowkwell transform) is conducted. As the main contributions to this work, we verified that the Vector Projection Length for load identification is quite feasible, with results up to 96% of tested appliances being identified. However, the results with Principal Component Analisys did not presented the same performance, reaching only 81% of accuracy rate. Comparing the signatures, it became clear that one should use the current in the time-frequency domain for better performance. Neither the use of power, or the time domain obtained satisfactory results of load identification when applying image pattern recognition techniques to load recognition. |
publishDate |
2016 |
dc.date.issued.fl_str_mv |
2016-02-19 |
dc.date.accessioned.fl_str_mv |
2017-06-06 |
dc.date.available.fl_str_mv |
2017-06-06 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
BORIN, Vinicius Pozzobon. Non-intrusive electrical appliances recognition using vector projection. 2016. 158 f. Dissertação (Mestrado em Engenharia Elétrica) - Universidade Federal de Santa Maria, Santa Maria, 2016. |
dc.identifier.uri.fl_str_mv |
http://repositorio.ufsm.br/handle/1/8580 |
identifier_str_mv |
BORIN, Vinicius Pozzobon. Non-intrusive electrical appliances recognition using vector projection. 2016. 158 f. Dissertação (Mestrado em Engenharia Elétrica) - Universidade Federal de Santa Maria, Santa Maria, 2016. |
url |
http://repositorio.ufsm.br/handle/1/8580 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.cnpq.fl_str_mv |
300400000007 |
dc.relation.confidence.fl_str_mv |
400 500 300 300 300 300 300 |
dc.relation.authority.fl_str_mv |
272a7edd-3c46-4479-b573-4cd18bb0b376 9bbc2094-748c-4a2d-8216-9836b63d9495 04c94bff-bf51-45c8-99f9-66544f525c19 1664f8e7-ae72-4e98-9b63-07892c66826d a289b01f-d097-4f5d-90a8-af90d6cfbee8 07184d01-606c-4427-984b-c3907dc6ba4d |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal de Santa Maria |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Engenharia Elétrica |
dc.publisher.initials.fl_str_mv |
UFSM |
dc.publisher.country.fl_str_mv |
BR |
dc.publisher.department.fl_str_mv |
Engenharia Elétrica |
publisher.none.fl_str_mv |
Universidade Federal de Santa Maria |
dc.source.none.fl_str_mv |
reponame:Manancial - Repositório Digital da UFSM instname:Universidade Federal de Santa Maria (UFSM) instacron:UFSM |
instname_str |
Universidade Federal de Santa Maria (UFSM) |
instacron_str |
UFSM |
institution |
UFSM |
reponame_str |
Manancial - Repositório Digital da UFSM |
collection |
Manancial - Repositório Digital da UFSM |
bitstream.url.fl_str_mv |
http://repositorio.ufsm.br/bitstream/1/8580/1/BORIN%2c%20VINICIUS%20POZZOBON.pdf http://repositorio.ufsm.br/bitstream/1/8580/2/BORIN%2c%20VINICIUS%20POZZOBON.pdf.txt http://repositorio.ufsm.br/bitstream/1/8580/3/BORIN%2c%20VINICIUS%20POZZOBON.pdf.jpg |
bitstream.checksum.fl_str_mv |
1ccd1eb5cc6ffbd368ac3925cb0477f6 738918550438805bf8430446f5415b85 db3c86066cf0a95d26aa1dd48aedf498 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Manancial - Repositório Digital da UFSM - Universidade Federal de Santa Maria (UFSM) |
repository.mail.fl_str_mv |
|
_version_ |
1801223807495569408 |