Nonlinear Auto-Regressive with Exogenous Inputs (NARX) Modelling of Hydroponics Water pH Level in response to Acid and Alkaline Solutions

Abstract

Nutrients are essential to optimising plant growth. However, the introduction of fertiliser in a hydroponics setup influences the pH level of the nutrient solution. This, in turn, could affect plants' growth as many types of plants require a specific pH range to grow optimally. Conventional hydroponics cultivation performs pH adjustment manually – a meticulous and error-prone process. Manual adjustment of pH solutions is prone to estimation errors, particularly when the pH levels change drastically due to the slow response of the solution to the addition of alkaline or acidic mixtures and sensitivity to minute errors in mixture delivery. For these reasons, a model to estimate the solution's pH would help improve the delivery accuracy of the alkaline and acidic mixtures. Past research offers minimal study to optimally construct the model from a System Identification (SI) perspective. This study represents a pH water neutralisation behaviour using the Nonlinear Autoregressive model with Exogeneous Inputs (NARX). The project begins with input and output data acquisition, leading to the development of the NARX model. Model performance was then evaluated by analysing the model fit and residual distribution.