Search

Background: To produce jasmine tea of excellent quality, it is crucial to select jasmine flowers at their optimal growth stage during harvesting. However, achieving this goal remains a challenge due to environmental and manual factors. This study addresses this issue by classifying different jasmine flowers based on visual attributes using the YOLOv7 algorithm, one of the most advanced algorithms in convolutional neural networks. Results: The mean average precision (mAP value) for detecting jasmine flowers using this model is 0.948, and the accuracy for five different degrees of openness of jasmine flowers, namely small buds, buds, half‐open, full‐open and wiltered, is 87.7%, 90.3%, 89%, 93.9% and 86.4%, respectively. Meanwhile, other ways of processing the images in the dataset, such as blurring and changing the brightness, also increased the credibility of the algorithm. Conclusion: This study shows that it is feasible to use deep learning algorithms for distinguishing jasmine flowers at different growth stages. This study can provide a reference for jasmine production estimation and for the development of intelligent and precise flower‐picking applications to reduce flower waste and production costs. © 2024 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

[Objectives]The deep-sea Crawling-Swimming Vehicle(CSV)is a new type of underwater robot,of which the multi-legged pose will change the distribution of the surrounding flow field and its center of gravity.[Methods]Based on the structural characteristics of the CSV,i.e. left-right symmetry, front-back approximate symmetry and up-down asymmetry, the maneuvering vertical plane motion equation of CSV was established and the corresponding stability criteria and critical speed were obtained. The hybrid mesh was used to compute the hydrodynamic coefficients of CSVs' pure heaving motion and pure pitching motion,and the results of computation were compared with the experimental results. According to the stability criterion,the static stability and dynamic stability of CSVs in three poses including the longitudinal expansion pose,lateral expansion pose and landing pose were judged,and main influence factors of motion stability were analyzed.[Results]The results show that CSVs in all three poses are in the state of static instability and relative dynamic stability. The design speed is lower than the critical speed,which can satisfy the requirement of linear stability. The static stability mainly depends on the position derivative related to vertical force. The static stability in lateral expansion pose is the best, while that in landing pose is the worst. The dynamic stability mainly depends on the position derivative related to vertical force,the initial height of stability center and the structure layout. The dynamic stability in lateral expansion pose is the worst,while that in landing pose is the best.[Conclusions]The hydrodynamic and stability laws of CSVs' multi-legged pose can better guide the design of control system and make it run safely.