Hydraulic performance and parameter optimisation of a microporous ceramic emitter using computational fluid dynamics, artificial neural network and multi-objective genetic algorithm

摘要

As the core of an irrigation system, microporous ceramic emitters (MPCEs) are closely related to the design, operation, and management of underground irrigation systems. In this study, computational fluid dynamics (CFD), an artificial neural network (ANN), and a multi-objective genetic algorithm (MOGA) were used to investigate the hydraulic performance of an MPCE and conduct parameter optimisation. A CFD software package was used to analyse the influence of the working parameters, structural parameters, and material properties on the flow characteristics of MPCE. Subsequently, an ANN and MOGA were used to optimise fabrication cost, flow rate, and flow index of the emitter. The results showed that a decrease in the bottom thickness or wall thickness of the MPCE increased the flow index of the emitter and the sensitivity of the flowrate to changes in pressure. Low working pressure was conducive to maintaining the active irrigation characteristic of the MPCE but the flowrate decreased. For crops with low water requirement, these conditions are ideal. The flow in the MPCE microchannel was mainly affected by the viscous resistance, whereas the inertial resistance only had an effect when the flow velocity was large. For field applications, the parameters can be optimised in the range obtained by the MOGA optimisation depending on the requirements of crop water demand, irrigation quality, and fabrication cost to achieve optimal irrigation performance. The results of this study provide references for the standardised fabrication of MPCEs. (C) 2019 IAgrE. Published by Elsevier Ltd. All rights reserved.