ABSTRACT
Deep learning techniques have made great progress in the field of target detection in recent years, making it possible to accurately identify plants in complex environments in agricultural fields. This project combines deep learning algorithms with spraying technology to design a machine vision precision real-time targeting spraying system for field scenarios. Firstly, the overall structure scheme of the system consisting of image acquisition and recognition module, electronically controlled spray module and pressure-stabilized pesticide supply module was proposed. After that, based on the target detection model YOLOv5s, the model is lightened and improved by replacing the backbone network and adding an attention mechanism. Based on this, a grille decision control algorithm for solenoid valve group on-off was designed, while common malignant weeds were selected as objects to produce data sets and complete model training. Finally, the deployment of the hardware system and detection model on the electric spray bar sprayer was completed, and field trials were conducted at different speeds. The experimental results show that the improved algorithm reduces the model size to 53.57% of the original model with less impact on mAP accuracy, improves FPS by 18.16%. The accuracy of on-target spraying at 2km/h, 3km/h and 4km/h speeds were 90.80%, 86.20% and 79.61%, respectively, and the spraying hit rate decreased as the operating speed increased. Among the hit rate components, the effective recognition rate was significantly affected by speed, while the relative recognition hit rate was less affected.
ABSTRACT
In this work, a novel method of carbodiimide-assisted zwitterionic modification was proposed and implemented to incorporate zwitterionic moieties onto poly(piperazine amide) membrane for improved water permeability and anti-depositing property, which are crucial for highly efficient nanofiltration of dye-contained effluents. Carboxyl groups of polyamide layer were firstly transferred into N-acylurea using excess l-ethyl-3-(3-(dimethylamino)propyl)-carbodiimide. Zwitterions were then incorporated through ring-opening reaction between tertiary amine groups of N-acylurea and 1, 4-butanesultone. Carbodiimide-assisted zwitterionic modification was verified by ATR-IR and XPS analyses and was found to not affect membrane pore size but significantly enhance membrane's permeation and anti-dye-deposition performances. Compared with those of virgin membrane, water permeabilities of the desired zwitterionic membrane to pure water, Congo red aqueous solution and Victoria blue B aqueous solution were higher by 42.9, 62.3 and 95.2 %, respectively, hydraulic resistances from irreversible deposition of Congo red and Victoria blue B molecules were dramatically lowered by 68.4 and 91.8 %, respectively. Furthermore, the perm-selectivity performance of the desired zwitterionic membrane in terms of molecular weight cut-off and pure water permeability was better than most of the reported zwitterionic membranes, and the separation and anti-depositing performances to both anionic and cationic dye aqueous solutions were better than commercial membrane NF270.
ABSTRACT
Illumination in the natural environment is uncontrollable, and the field background is complex and changeable which all leads to the poor quality of broccoli seedling images. The colors of weeds and broccoli seedlings are close, especially under weedy conditions. The factors above have a large influence on the stability, velocity and accuracy of broccoli seedling recognition based on traditional 2D image processing technologies. The broccoli seedlings are higher than the soil background and weeds in height due to the growth advantage of transplanted crops. A method of broccoli seedling recognition in natural environments based on Binocular Stereo Vision and a Gaussian Mixture Model is proposed in this paper. Firstly, binocular images of broccoli seedlings were obtained by an integrated, portable and low-cost binocular camera. Then left and right images were rectified, and a disparity map of the rectified images was obtained by the Semi-Global Matching (SGM) algorithm. The original 3D dense point cloud was reconstructed using the disparity map and left camera internal parameters. To reduce the operation time, a non-uniform grid sample method was used for the sparse point cloud. After that, the Gaussian Mixture Model (GMM) cluster was exploited and the broccoli seedling points were recognized from the sparse point cloud. An outlier filtering algorithm based on k-nearest neighbors (KNN) was applied to remove the discrete points along with the recognized broccoli seedling points. Finally, an ideal point cloud of broccoli seedlings can be obtained, and the broccoli seedlings recognized. The experimental results show that the Semi-Global Matching (SGM) algorithm can meet the matching requirements of broccoli images in the natural environment, and the average operation time of SGM is 138 ms. The SGM algorithm is superior to the Sum of Absolute Differences (SAD) algorithm and Sum of Squared Differences (SSD) algorithms. The recognition results of Gaussian Mixture Model (GMM) outperforms K-means and Fuzzy c-means with the average running time of 51 ms. To process a pair of images with the resolution of 640×480, the total running time of the proposed method is 578 ms, and the correct recognition rate is 97.98% of 247 pairs of images. The average value of sensitivity is 85.91%. The average percentage of the theoretical envelope box volume to the measured envelope box volume is 95.66%. The method can provide a low-cost, real-time and high-accuracy solution for crop recognition in natural environment.
Subject(s)
Brassica , Image Processing, Computer-Assisted/methods , Seedlings , Algorithms , Vision, BinocularABSTRACT
Additional structures are usually adopted to support the overhanging structures in order to resist the deformation of parts. Improper geometric design of the support structures may result in a sharp deterioration in the surface quality and a failure of manufacture, which affects the expansion in the use of selective laser melting (SLM) technology. In this research, cuboids were added into the conventional block support for a better heat dissipation. The Taguchi method was used to analyze the effect of the geometric design of this support on the part's deformation and surface roughness. It was found that solid pieces or cuboids as support structures can reduce the deformation. However, their effects are weaker than those of teeth structures which decrease the deformation by more reliable connections. It is interesting that narrowing the gap between the cuboids and overhang can weaken the strength of teeth structures and then increases the deformation of part. In general, the distance between every two adjacent walls of support and the gap between the cuboids and the overhang have the greatest influence on the part's deformation and surface quality respectively.
ABSTRACT
A deep understanding of the laser-material interaction mechanism, characterized by laser absorption, is very important in simulating the laser metal powder bed fusion (PBF) process. This is because the laser absorption of material affects the temperature distribution, which influences the thermal stress development and the final quality of parts. In this paper, a three-dimensional finite element analysis model of heat transfer taking into account the effect of material state and phase changes on laser absorption is presented to gain insight into the absorption mechanism, and the evolution of instantaneous absorptance in the laser metal PBF process. The results showed that the instantaneous absorptance was significantly affected by the time of laser radiation, as well as process parameters, such as hatch space, scanning velocity, and laser power, which were consistent with the experiment-based findings. The applicability of this model to temperature simulation was demonstrated by a comparative study, wherein the peak temperature in fusion process was simulated in two scenarios, with and without considering the effect of material state and phase changes on laser absorption, and the simulated results in the two scenarios were then compared with experimental data respectively.
ABSTRACT
Copper alloys, combined with selective laser melting (SLM) technology, have attracted increasing attention in aerospace engineering, automobile, and medical fields. However, there are some difficulties in SLM forming owing to low laser absorption and excellent thermal conductivity. It is, therefore, necessary to explore a copper alloy in SLM. In this research, manufacturing feasibility and forming properties of Cu-4Sn in SLM were investigated through a systematic experimental approach. Single-track experiments were used to narrow down processing parameter windows. A Greco-Latin square design with orthogonal parameter arrays was employed to control forming qualities of specimens. Analysis of variance was applied to establish statistical relationships, which described the effects of different processing parameters (i.e., laser power, scanning speed, and hatch space) on relative density (RD) and Vickers hardness of specimens. It was found that Cu-4Sn specimens were successfully manufactured by SLM for the first time and both its RD and Vickers hardness were mainly determined by the laser power. The maximum value of RD exceeded 93% theoretical density and the maximum value of Vickers hardness reached 118 HV 0.3/5. The best tensile strength of 316-320 MPa is inferior to that of pressure-processed Cu-4Sn and can be improved further by reducing defects.
