EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mathematically Grounded Neuro-Fuzzy Control of IoT-Enabled Irrigation Systems

Nikolay Hinov, Reni Kabakchieva, Daniela Gotseva, Plamen Stanchev

Mathematics · 16.01.2026 · 14 (2) · 314

DOI: 10.3390/math14020314 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 16.01.2026. Verfasst von Nikolay Hinov und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper develops a mathematically grounded neuro-fuzzy control framework for IoT-enabled irrigation systems in precision agriculture. A discrete-time, physically motivated model of soil moisture is formulated to capture the nonlinear water dynamics driven by evapotranspiration, irrigation, and drainage in the crop root zone. A Mamdani-type fuzzy controller is designed to approximate the optimal irrigation strategy, and an equivalent Takagi–Sugeno (TS) representation is derived, enabling a rigorous stability analysis based on Input-to-State Stability (ISS) theory and Linear Matrix Inequalities (LMIs). Online parameter estimation is performed using a Recursive Least Squares (RLS) algorithm applied to real IoT field data collected from a drip-irrigated orchard. To enhance prediction accuracy and long-term adaptability, the fuzzy controller is augmented with lightweight artificial neural network (ANN) modules for evapotranspiration estimation and slow adaptation of membership-function parameters. This work provides one of the first mathematically certified neuro-fuzzy irrigation controllers integrating ANN-based estimation with Input-to-State Stability (ISS) and LMI-based stability guarantees. Under mild Lipschitz continuity and boundedness assumptions, the resulting neuro-fuzzy closed-loop system is proven to be uniformly ultimately bounded. Experimental validation in an operational IoT setup demonstrates accurate soil-moisture regulation, with a tracking error below 2%, and approximately 28% reduction in water consumption compared to fixed-schedule irrigation. The proposed framework is validated on a real IoT deployment and positioned relative to existing intelligent irrigation approaches.

Zitieren

APA

Hinov, N., Kabakchieva, R., Gotseva, D., & Stanchev, P. (2026). Mathematically Grounded Neuro-Fuzzy Control of IoT-Enabled Irrigation Systems. Mathematics, 14(2), 314. https://doi.org/10.3390/math14020314

Vancouver

Hinov N, Kabakchieva R, Gotseva D, Stanchev P. Mathematically Grounded Neuro-Fuzzy Control of IoT-Enabled Irrigation Systems. Mathematics. 2026;14(2):314. doi:10.3390/math14020314

BibTeX
@article{Hinov2026,
  author = {Hinov, Nikolay and Kabakchieva, Reni and Gotseva, Daniela and Stanchev, Plamen},
  title = {Mathematically Grounded Neuro-Fuzzy Control of IoT-Enabled Irrigation Systems},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {2},
  pages = {314},
  doi = {10.3390/math14020314}
}
Kostenlos starten →