Monitoramento da qualidade do conforto de ambientes baseado em Lógica Fuzzy e redes de sensores

• Ano de defesa: 2019
• Autor(a) principal: MENDONÇA, Geiza Gomes
• Orientador(a): FONSECA NETO, João Viana da
• Banca de defesa: FONSECA NETO, João Viana da , SANTANA, Ewaldo Eder Carvalho , FREIRE, Raimundo Carlos Silvério
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Maranhão
• Programa de Pós-Graduação: PROGRAMA DE PÓS-GRADUAÇÃO EM ENGENHARIA DE ELETRICIDADE/CCET
• Departamento: DEPARTAMENTO DE ENGENHARIA DA ELETRICIDADE/CCET
• País: Brasil
• Palavras-chave em Português: Qualidade do Ambiente; Lógica Fuzzy; Modelo de funções; Rede de sensores; Internet das coisas
• Palavras-chave em Inglês: Environment quality; Fuzzy logic; Function models; Sensor network; Internet of things
• Área do conhecimento CNPq: Teoria da Computação; Lógicas e Semântica de Programas
• Link de acesso: https://tedebc.ufma.br/jspui/handle/tede/tede/2802

The compliance with the limits established in the technical norms of the environment is fundamental to guarantee the comfort and health of the occupants. Environments that do not meet normative specifications can cause discomfort, malaise, lack of concentration, among other diseases. In this context, this dissertation presents the formulation of intelligent models for monitoring the quality of the environment in accordance with Brazilian standards. The quantities evaluated are temperature, humidity, light, carbon dioxide, noise and dust. The proposed methodology consists of three models. In the first model, the membership functions based on fuzzy logic determine the environmental quality index, it ranges from zero to one and indicates if the measured quantities meet the normative specifications. In the second model, the Mandani type fuzzy system monitors the quality of the environment according to the level of each magnitude. The fuzzy inference system through the set of rules determine whether the environment is little or very healthy according to the number of quantities that do not meet the normative specification. The third is the model of the sensor network that represents each component of the network and the structure used. Each sensor node is composed of a microcontroller that sends the signals acquisition of the sensors to the Internet by means of a transceiver. Cloud storage is performed through an IoT platform. The results are presented applying the functions based on fuzzy logic and the fuzzy system to the sensor network. The monitoring interfaces proposed for the laboratory environment are presented in the form of virtual meters from the developed indices.