Search

【Objective】Cage biometrics and statistics are one of the key reference factors for marine pasture farming management. Aiming at the interference of reverberation noise and complex background, this paper constructs fish detection data sets under different lighting conditions, and uses forward-looking sonar imaging technology to propose a fish recognition lightweight model based on YOLOV5-MobilenetV3 and sonar images (LAPR-Net) to realize fish recognition in water cages in turbid or dark scenes.【Method】Taking tilapia as the research object, based on the frame structure of the YOLOV5 model, the backbone network module ado pts the lightweight Mob ileNetV3 bneck block, using the linear bottleneck inverse residual structure and depth separable convolution extract the features of fish in sonar images, applying the attention mechanism SE-Net to obtain multi-scale semantic features of sonar images and enhance the correlation between features; the neck network adopts the path aggregation network structure to perform multi-scale fusion of target features, to enhance the feature fusion ability; the prediction part adopts the maximum local search based on the non-maximum suppression method, removes the redundant detection frame, screens the detection frame with the highest confidence, and finally outputs and displays the detection result of the fish, including the position, category and detection probability of detecting an object.【Result】Four other mainstream detection models were selected for comparative experiments, including YOLOV3-ting (Darknet53), YOLOV5 (CSPdarknet53), YOLOV5 (Repvgg), and YOLOV5s (Transformer). It proposes the model parameter quantityof 3 545 453, FLOPs of 6.3 G, and the mAP of 0.957, and the average inference speed of each picture of the model is 0.08868 s. Compared with the YOLOV5 model, the mAP of the improved model has increased by 9.7%.【Conclusion】The proposed network improves the speed of training and recognition, reduces the requirements for hardware equipment, and provides a reference for the detection model of cage cultured fish in marine pastures.

【Objective】Light is the most important factor affecting plant growth, development, metabolism and external phenotype. In the process of plant growth, artificial light sources are often used instead of natural light to fill the seeds and seedlings to improve the quality, yield and efficiency of fruits and vegetables. Artificial light plant is one of the important ways for standardized and efficient seedling cultivation, but its high energy consumption, accounting for 60% to 80% of the total energy consumption of plant factories, seriously hinder the promotion and application of factory seedling technology. Therefore, reducing the energy consumption of light source and improving the utilization rate of light is one of the core goals for plant seedling.【Method】Aiming at the problems of fixed height, high energy consumption and difficult to match the light demand of seed and seedling growth, this study developed a precise light cultivation platform for seedlings based on Programmable Logic Controller (PLC) technology by combining theoretical analysis, model construction and experiment. Taking cucumber seedlings as the object, the performance of the light intensity control system of the precision light cultivation platform for seedlings was verified, and its effect on the growth of cucumber seedlings was explored.【Result】The experimental results showed that the light intensity and light distribution uniformity were improved after the optimization of the lamp bead structure. The developed platform can fill the light of cucumber seedlings by manual, automatic, Human Machine Interface (HMI) and host computer. Through the platform optical radiation energy consumption model and the layer level adjustment control strategy, the LED operating power is effectively reduced, saving about 40.65% of electric energy. The maximum and minimum relative error of the optical platform radiation model are 34.37% and 3.57%, respectively, and the average relative error is 11.45%. Cultivation experiments showed that under the same light intensity treatment, there was no significant difference in seedling phenotype parameters and strong seedling index by comparing the precision light cultivation platform with the traditional high floor fixed platform.【Conclusion】The precision light cultivation platform of seedlings based on PLC technology realizes automatic lifting and intelligent dimming, and saves up to 40.65% power without affecting the growth of seedlings.

【Objective】In order to improve the preservation quality and prolong the shelf life of flowering cabbage, a kind of display cabinet with cyclic air curtain semiconductor refrigeration was designed.【Method】The display cabinet was taken as the display object, a heat load model based on internal and external heat transfer of the cabinet was established, and the fresh-keeping effect of the display cabinet with cyclic air curtain semiconductor refrigeration was verified by experiments.【Result】After 27 h of display, mass loss rates of three display modes (display cabinet with cyclic air curtain semiconductor refrigeration, open display cabinet and room temperature display) were 9.3%, 20.6% and 34.8%, respectively. The good vegetable rates were 35.8%, 0 and 0, respectively. And the sensory evaluation scores were 2.17, 1.08, 0, respectively. The SPAD values of the three display modes varied between 46 and 54. The mass loss rate of flowering cabbage with cyclic air curtain display cabinet was significantly lower than that of the other two modes after 3 h of display. After 6 h of display, the good vegetable rate and sensory evaluation score were significantly higher than those of the other two modes.【Conclusion】With the flowering cabbage as display object in display cabinet, a heat load model based on internal and external heat transfer of the cabinet is established, and the display cabinet with cyclic air curtain semiconductor refrigeration has a good fresh-keeping effect on flowering cabbage.