Answers are grounded in this paper and cite their sources.
Existing wine grape harvesting methods face challenges in balancing harvesting efficiency and fruit damage. This study proposed a negative-pressure airflow-based whole-cluster harvesting method and investigated grape cluster motion and damage during pneumatic conveying and collection. A multi-sensor integrated visualization platform incorporating high-speed imaging, photoelectric sensors, force sensors, and an inertial measurement unit was developed. The effects of cluster mass, airflow velocity, and conveying–collection configurations were evaluated using conveying time (Tc), maximum force recorded during the collision between the grape cluster and the buffer plate (Fb), and berry loss rate (Rs). Four machine learning models were compared to predict conveying performance. Results showed that cluster motion comprised five stages: suspended conveying, horizontal conveying, projectile motion, collision buffering, and collection. Increasing airflow velocity shortened conveying time but increased collision impact and berry loss. BP-MLP achieved the best overall predictive performance, with R2 values of 0.81 (±0.07), 0.84 (±0.04), and 0.85 (±0.02) for Tc, Fb, and Rs, respectively. A model-derived feasible airflow velocity range of 24.00–24.45 m/s was identified under the constraints of Tc ≤ 0.4 s, Fb ≤ 10 N, and Rs ≤ 10%. Five additional groups of bench-scale experiments were conducted to evaluate the feasibility of selected operating conditions within this range. These findings provide a reference for the development of negative-pressure airflow-based whole-cluster wine grape harvesting equipment.
No takes yet. Share an insight, caveat, or question.
Ma et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: