Development of a recommendation system in PCBA repair
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10773/34920 |
Resumo: | Industry 4.0 has promoted the digitalisation of industrial activities, representing a significant impact on process improvement and increased productivity. However, the systems that operate using these innovations present themselves generating quantities of information at an exacerbated velocity and in an unimaginable volume, big data. As a result, it becomes impractical and detrimental in many procedures for the analysis of the data set and decisions not to be taken by using the digital means available. The background process related to this dissertation takes place at Bosch Security Systems, where every day around twelve hundred printed circuit board assemblies (PCBA) are submitted for quality control tests from the production line. Each evaluation encompasses approximately four hundred measuring points at which the measured physical quantity is varying. Given the size of the referred around thirty-seven thousand test files with a total of approximately fourteen million eight hundred and eighty thousand measurements are generated each month. Therefore, assuming that for each type of fault identified in a file referring to a failed test there exists a repair method regarded as the most effective to fix the defect and guarantee the functionality levels of each board, the work proposal arises in the context of studying the possibility and practicability of developing a model of a recommendation system applied to the mentioned process. This has the objective of providing suggestions for repair methods, increasing both the rapidity of human decision making and the efficiency of the actions applied by the repairers. The proposed solution relies on being a recommendation system of hybrid category. At its base the essential tools used are the Python programming language, the Pandas library for data analysis and the algorithms based on gradient descent method for applying the technique of utility matrix completion, along with K-means clustering to consolidate the system in cases where data sparsity and cold start issues occur. Briefly, to reinforce the fact that the theme of this work should be seen with an innovative character, once currently this type of systems are present every day in people’s lives in ecommerce platforms, streaming, music, among many other areas, but not in industrial activities. Based on the dissertation and as a proposal for future work, if the operation of the developed model is seen as viable by the company’s responsibles in the short and long term, it can be implemented to the referred process as well as to others. In this way practical benefits will be brought that corroborate some of the previously mentioned goals of Industry 4.0. |
id |
RCAP_943e21bf2a4a0cbdae1955e438ea39b3 |
---|---|
oai_identifier_str |
oai:ria.ua.pt:10773/34920 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Development of a recommendation system in PCBA repairBig dataBoschData analysisFault identificationPCBA repairRecommendation systemQuality controlIndustry 4.0 has promoted the digitalisation of industrial activities, representing a significant impact on process improvement and increased productivity. However, the systems that operate using these innovations present themselves generating quantities of information at an exacerbated velocity and in an unimaginable volume, big data. As a result, it becomes impractical and detrimental in many procedures for the analysis of the data set and decisions not to be taken by using the digital means available. The background process related to this dissertation takes place at Bosch Security Systems, where every day around twelve hundred printed circuit board assemblies (PCBA) are submitted for quality control tests from the production line. Each evaluation encompasses approximately four hundred measuring points at which the measured physical quantity is varying. Given the size of the referred around thirty-seven thousand test files with a total of approximately fourteen million eight hundred and eighty thousand measurements are generated each month. Therefore, assuming that for each type of fault identified in a file referring to a failed test there exists a repair method regarded as the most effective to fix the defect and guarantee the functionality levels of each board, the work proposal arises in the context of studying the possibility and practicability of developing a model of a recommendation system applied to the mentioned process. This has the objective of providing suggestions for repair methods, increasing both the rapidity of human decision making and the efficiency of the actions applied by the repairers. The proposed solution relies on being a recommendation system of hybrid category. At its base the essential tools used are the Python programming language, the Pandas library for data analysis and the algorithms based on gradient descent method for applying the technique of utility matrix completion, along with K-means clustering to consolidate the system in cases where data sparsity and cold start issues occur. Briefly, to reinforce the fact that the theme of this work should be seen with an innovative character, once currently this type of systems are present every day in people’s lives in ecommerce platforms, streaming, music, among many other areas, but not in industrial activities. Based on the dissertation and as a proposal for future work, if the operation of the developed model is seen as viable by the company’s responsibles in the short and long term, it can be implemented to the referred process as well as to others. In this way practical benefits will be brought that corroborate some of the previously mentioned goals of Industry 4.0.A indústria 4.0 tem promovido a digitalização das atividades industriais, representando um impacto significativo na melhoria de processos e aumento de produtividade. Contudo, os sistemas que operam utilizando estas inovações apresentam-se a gerar quantidades de informação a uma velocidade exacerbada e numa magnitude inimaginável, big data. Torna-se deste modo impraticável e prejudicial em muitos procedimentos a análise de dados e decisões não serem tomadas com recurso aos meios digitais disponíveis. O processo que contextualiza esta dissertação tem lugar na Bosch Sistemas de Segurança, onde todos os dias cerca de mil e duzentas printed circuit board assemblies (PCBA) são submetidas para testes de controlo de qualidade a partir da linha de produção. Cada avaliação engloba à volta de quatrocentos pontos de medição nos quais a grandeza física medida se encontra a variar. Atendendo à dimensão do referido, cerca de trinta e sete mil ficheiros de teste com um total de aproximadamente catorze milhões oitocentas e oitenta mil medições são gerados a cada mês. Assim, assumindo que para cada tipo de falha identificada num ficheiro referente a um teste falhado existe um método de reparação considerado como o mais eficaz para reparar o defeito e garantir os níveis de funcionalidade de cada placa, a proposta de trabalho surge no âmbito de estudar a possibilidade e praticabilidade de desenvolver um modelo de um sistema de recomendação aplicado ao processo referido. Este tem como objetivo fornecer sugestões de métodos de reparação, aumentando tanto a rapidez da tomada de decisão humana, como a eficácia das ações aplicadas pelos reparadores. A solução proposta fundamenta-se por ser um sistema de recomendação de categoria híbrida. Na sua base as ferramentas essenciais utilizadas são a linguagem de programação Python, o pacote Pandas para análise de dados e os algoritmos baseados no método de gradient descent para aplicação da técnica de preenchimento da matriz de utilidade, assim como K-means clustering para reforçar o sistema em casos onde ocorrem problemas de data sparsity e cold start. Brevemente, reforçar o facto da temática deste trabalho dever ser vista com um caráter inovador, uma vez que atualmente este tipo de sistemas estão presentes todos os dias na vida das pessoas em plataformas de comércio eletrónico, streaming, musica, entre muitas outras áreas, mas não em atividades industriais. Com base na dissertação e como proposta de trabalho de futuro, se a operação do modelo desenvolvido for vista como viável pelos responsáveis da empresa a curto e longo prazo, este poderá ser aplicado a este processo, assim como a outros. Desta forma serão trazidos benefícios práticos que corroboram algumas das metas mencionadas anteriormente da indústria 4.0.2022-10-18T09:53:06Z2022-07-26T00:00:00Z2022-07-26info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10773/34920engCozinheiro, José Pedro Nevesinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-02-22T12:07:14Zoai:ria.ua.pt:10773/34920Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:06:03.443841Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Development of a recommendation system in PCBA repair |
title |
Development of a recommendation system in PCBA repair |
spellingShingle |
Development of a recommendation system in PCBA repair Cozinheiro, José Pedro Neves Big data Bosch Data analysis Fault identification PCBA repair Recommendation system Quality control |
title_short |
Development of a recommendation system in PCBA repair |
title_full |
Development of a recommendation system in PCBA repair |
title_fullStr |
Development of a recommendation system in PCBA repair |
title_full_unstemmed |
Development of a recommendation system in PCBA repair |
title_sort |
Development of a recommendation system in PCBA repair |
author |
Cozinheiro, José Pedro Neves |
author_facet |
Cozinheiro, José Pedro Neves |
author_role |
author |
dc.contributor.author.fl_str_mv |
Cozinheiro, José Pedro Neves |
dc.subject.por.fl_str_mv |
Big data Bosch Data analysis Fault identification PCBA repair Recommendation system Quality control |
topic |
Big data Bosch Data analysis Fault identification PCBA repair Recommendation system Quality control |
description |
Industry 4.0 has promoted the digitalisation of industrial activities, representing a significant impact on process improvement and increased productivity. However, the systems that operate using these innovations present themselves generating quantities of information at an exacerbated velocity and in an unimaginable volume, big data. As a result, it becomes impractical and detrimental in many procedures for the analysis of the data set and decisions not to be taken by using the digital means available. The background process related to this dissertation takes place at Bosch Security Systems, where every day around twelve hundred printed circuit board assemblies (PCBA) are submitted for quality control tests from the production line. Each evaluation encompasses approximately four hundred measuring points at which the measured physical quantity is varying. Given the size of the referred around thirty-seven thousand test files with a total of approximately fourteen million eight hundred and eighty thousand measurements are generated each month. Therefore, assuming that for each type of fault identified in a file referring to a failed test there exists a repair method regarded as the most effective to fix the defect and guarantee the functionality levels of each board, the work proposal arises in the context of studying the possibility and practicability of developing a model of a recommendation system applied to the mentioned process. This has the objective of providing suggestions for repair methods, increasing both the rapidity of human decision making and the efficiency of the actions applied by the repairers. The proposed solution relies on being a recommendation system of hybrid category. At its base the essential tools used are the Python programming language, the Pandas library for data analysis and the algorithms based on gradient descent method for applying the technique of utility matrix completion, along with K-means clustering to consolidate the system in cases where data sparsity and cold start issues occur. Briefly, to reinforce the fact that the theme of this work should be seen with an innovative character, once currently this type of systems are present every day in people’s lives in ecommerce platforms, streaming, music, among many other areas, but not in industrial activities. Based on the dissertation and as a proposal for future work, if the operation of the developed model is seen as viable by the company’s responsibles in the short and long term, it can be implemented to the referred process as well as to others. In this way practical benefits will be brought that corroborate some of the previously mentioned goals of Industry 4.0. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-10-18T09:53:06Z 2022-07-26T00:00:00Z 2022-07-26 |
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.uri.fl_str_mv |
http://hdl.handle.net/10773/34920 |
url |
http://hdl.handle.net/10773/34920 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
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.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799137715780845568 |