Answers are grounded in this paper and cite their sources.
To address the challenges of multi-variable coupling, sensor noise interference, and inefficient energy regulation in controlled environment agriculture (CEA), this study develops an intelligent greenhouse environmental control system integrating multi-sensor fusion, Kalman filtering, and genetic algorithm (GA)-optimized fuzzy control. The proposed system combines real-time sensing of key environmental parameters, including air temperature, relative humidity, CO₂ concentration, and photosynthetic photon flux density (PPFD), with a hierarchical control architecture implemented on the LabVIEW platform. A Kalman filtering algorithm is introduced to improve sensing reliability, while a GA optimization strategy is developed to automatically adjust fuzzy membership functions and control rules, enhancing the adaptability of conventional fuzzy controllers under dynamic greenhouse conditions. The system integrates automatic–manual switching, actuator status feedback, alarm management, and MySQL-based data storage to achieve reliable greenhouse environmental regulation. Comprehensive performance evaluation was conducted through greenhouse experiments, including controlled greenhouse experiments and long-term field operation. Compared with conventional PID control, the proposed GA-optimized fuzzy control strategy reduced energy consumption by 17.6% (p < 0.01), reduced control response time to 1.8 s, and maintained environmental stability within ±0.5°C for air temperature and ±2.1% RH. An 180-day continuous field validation demonstrated 99.7% system availability, confirming the reliability and practical applicability of the proposed framework. The developed system provides an adaptive, scalable, and energy-efficient solution for intelligent greenhouse environmental control. The integration of computational intelligence methods with multi-sensor fusion offers potential applications for sustainable controlled environment agriculture and agricultural energy management.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: