Predição de retrolavagem de filtros em função da qualidade da água de irrigação

Detalhes bibliográficos
Ano de defesa: 2022
Autor(a) principal: Passos, Mádilo Lages Vieira
Orientador(a): Não Informado pela instituição
Banca de defesa: Não Informado pela instituição
Tipo de documento: Dissertação
Tipo de acesso: Acesso aberto
Idioma: por
Instituição de defesa: Não Informado pela instituição
Programa de Pós-Graduação: Não Informado pela instituição
Departamento: Não Informado pela instituição
País: Não Informado pela instituição
Palavras-chave em Português:
Link de acesso: http://www.repositorio.ufc.br/handle/riufc/66523
Resumo: Divided into two chapters, this research addresses technical aspects of using inferior quality water in irrigation systems. In the first chapter, the objective was the construction of a multiparametric probe with accessible hardware and software, protocols and basic assumptions of IoT (Internet of Things) and performance according to fuzzy logic concepts. The probe was based on the Arduino Nano model platform. The sensors used were: pH sensor (hydrogen potential), turbidity and total dissolved solids sensor. For data transmission, classic Bluetooth (HC-06 module) and 802.11 g/b/n standard, ESP8266 module (ESP-01) were implemented. The Wi-Fi standard (IEEE 802.11 g/b/n), via ESP8266 version 01, presented the best results for consistency and efficiency of information transmission, according to the fuzzy modeling. In the second chapter, it was technically investigated the influence of water quality on the need for cleaning in filtering systems with backwash. For this purpose, backwash pressure modeling was expressed as a function of water quality and pressure load at the entrance of screen filters, via artificial neural networks. Water quality variables were measured using a multiparameter probe. Feedforward multilayer perceptron artificial neural networks with 2-4-1 architecture, expressed good precision in modeling the temporal evolution of pressure load in the screen filtering system (120 mesh). The pressure load model based on the water quality characteristics pH, turbidity, total dissolved solids and temperature, expressed poor performance.