RESUMEN
The identification of safflower filament targets and the precise localization of picking points are fundamental prerequisites for achieving automated filament retrieval. In light of challenges such as severe occlusion of targets, low recognition accuracy, and the considerable size of models in unstructured environments, this paper introduces a novel lightweight YOLO-SaFi model. The architectural design of this model features a Backbone layer incorporating the StarNet network; a Neck layer introducing a novel ELC convolution module to refine the C2f module; and a Head layer implementing a new lightweight shared convolution detection head, Detect_EL. Furthermore, the loss function is enhanced by upgrading CIoU to PIoUv2. These enhancements significantly augment the model's capability to perceive spatial information and facilitate multi-feature fusion, consequently enhancing detection performance and rendering the model more lightweight. Performance evaluations conducted via comparative experiments with the baseline model reveal that YOLO-SaFi achieved a reduction of parameters, computational load, and weight files by 50.0%, 40.7%, and 48.2%, respectively, compared to the YOLOv8 baseline model. Moreover, YOLO-SaFi demonstrated improvements in recall, mean average precision, and detection speed by 1.9%, 0.3%, and 88.4 frames per second, respectively. Finally, the deployment of the YOLO-SaFi model on the Jetson Orin Nano device corroborates the superior performance of the enhanced model, thereby establishing a robust visual detection framework for the advancement of intelligent safflower filament retrieval robots in unstructured environments.
RESUMEN
D-amino acid oxidase (DAAO) is widely used in the industrial preparation of L-amino acids, and cultivating Escherichia coli (E. coli) expressing DAAO for the biosynthesis of L-phosphinothricin (L-PPT) is very attractive. At present, the biomass production of DAAO by fermentation is still limited in large-scale industrial applications because the expression of DAAO during the fermentation process inhibits the growth of host cells, which limits higher cell density. In this study, the factors that inhibit the growth of bacterial cells during a 5-L fed-batch fermentation process were explored, and the fermentation process was optimized by co-expressing catalase (CAT), by balancing the biomass and the enzyme activity, and by adding exogenous D-alanine (D-Ala) to relieve the limitation of DAAO on the cells and optimize fermentation. Under optimal conditions, the DO-STAT feeding mode with DO controlled at 30% ± 5% and the addition of 27.5 g/L lactose mixed with 2 g/L D-Ala during induction at 28 °C resulted in the production of 26.03 g dry cell weight (DCW)/L biomass and 390.0 U/g DCW specific activity of DAAO; an increase of 78% and 84%, respectively, compared with the initial fermentation conditions. The fermentation strategy was successfully scale-up to a 5000-L fermenter.