MUMBAI, India, Aug. 24 -- Intellectual Property India has published a patent application (202641097772 A) filed by Diva Senthilnathan on August 13, 2026, for Ai-Driven Adaptive Livestock Feeding System.
Inventors include Dr. T. Kalaikumaran; Mrs. P. Sreedevi; Mrs. R. Vaishnavi Karthika; Barathvishva M; Kathirvel K; Naveen S; Selvakumar S; Sivakesavan C; Sree Gayathree R; Srinitha G; and Subasanjeev S.
The application for the patent was published on August 21, 2026, under issue no. 34/2026.
Abstract: Conventional livestock feeding systems rely largely on fixed feeding schedules and generalized rationing, which often fail to account for variations in individual animal growth, health status, feed intake, and production requirements. This paper proposes an AI-driven adaptive livestock feeding system that integrates RFID-based animal identification, load-cell weight sensing, feeding-behaviour monitoring, and environmental sensing to enable individualized and continuously optimized nutrition. Unlike conventional automated feeders that primarily automate feed dispensing, the proposed system establishes a closed-loop intelligent feeding mechanism in which real- time animal data are analysed to predict nutritional requirements, detect abnormal feeding behaviour, and dynamically adjust subsequent feed portions. The proposed framework employs machine-learning techniques to establish an individual behavioural and nutritional profile for each animal. Parameters including body-weight variation, feeding frequency, feeding duration, feed consumption, growth stage, and environmental conditions are continuously analysed to estimate the animal's current nutritional demand. An anomaly-detection module identifies deviations from the animal's normal feeding pattern and generates early health-risk alerts, while the adaptive rationing module modifies feed quantity and composition according to predicted requirements. This enables the system to transition from predetermined feeding schedules toward self-adjusting, animal-specific feeding decisions. The key contribution of the proposed approach is the integration of individualized nutrition optimization, behavioural anomaly detection, and automatic feed dispensing within a single feedback-driven architecture. Continuous feedback from each feeding cycle is used to refine subsequent feeding decisions, thereby creating an adaptive learning loop. The system is expected to improve feed utilization, reduce feed wastage, support early identification of health abnormalities, and improve animal productivity while reducing dependence on manual intervention. The proposed framework provides a scalable foundation for intelligent precision livestock farming by transforming automated feeders from simple dispensing machines into adaptive decision- making systems for real-time animal nutrition and health management.
Disclaimer: Curated by HT Syndication.
