Maize is one of the essential crops for food supply. Accurate sorting of seeds is critical for cultivation and marketing purposes, while the traditional methods of variety identification are time-consuming, inefficient, and easily damaged. This study proposes a rapid classification method for maize seeds using a combination of machine vision and deep learning. 8080 maize seeds of five varieties were collected, and then the sample images were classified into training and validation sets in the proportion of 8:2, and the data were enhanced. The proposed improved network architecture, namely P-ResNet, was fine-tuned for transfer learning to recognize and categorize maize seeds, and then it compares the performance of the models. The results show that the overall classification accuracy was determined as 97.91, 96.44, 99.70, 97.84, 98.58, 97.13, 96.59, and 98.28% for AlexNet, VGGNet, P-ResNet, GoogLeNet, MobileNet, DenseNet, ShuffleNet, and EfficientNet, respectively. The highest classification accuracy result was obtained with P-ResNet, and the model loss remained at around 0.01. This model obtained the accuracy of classifications for BaoQiu, ShanCu, XinNuo, LiaoGe, and KouXian varieties, which reached 99.74, 99.68, 99.68, 99.61, and 99.80%, respectively. The experimental results demonstrated that the convolutional neural network model proposed enables the effective classification of maize seeds. It can provide a reference for identifying seeds of other crops and be applied to consumer use and the food industry.
HighlightsEffectively separating the “white pollution” from agricultural soil.Three different spades for mechanical recycling residual film were tested.All spades had a similar draft requirement and soil disturbance trend.Spade A provided a higher residual film recovery rate.Abstract. Plastic film mulching cultivation provides important support for increasing the crop yield and ensuring food security, but residual plastic film pollution has become a prominent problem affecting the sustainable development of agriculture especially in northwest China. Recovery of thicker film by residual plastic film recycling machines may represent an effective way to solve this problem. In this study, a combined implement comprising three different spades (spades A, B, and C) were tested in a cotton field to compare their performance. All three types of spades were tested at a travel speed of 4.5 kmh-1 and a working depth of 40 mm. The residual plastic film recovery rate, soil draft force, soil disturbance characteristics (furrow profile), and cotton stubble uprooting were measured. Spade B had a higher draft force than the other spades. This trend was also observed for the soil disturbance area. Spades A and C produced stubble uprooting of approximately 5%, and spade B resulted in an approximately 5.7% larger degree of uprooting. Spade A had the largest recovery rate of residual film, while spade C had the smallest one. Overall, considering both recovery rate of residual film and draft force requirement, spade A showed better performance compared to spades B and C. Keywords: Draft force, Residual plastic film, Recovery rate, Soil disturbance, Spade.
When the gearbox body interference is connected to the ring gear, prestressing occurs in the ring gear, which has a significant impact on the strength and life of the gear. Research on the prestressing of the inner ring gear is in the preliminary stage, and the distribution rule of the prestressing and the influence of each parameter on the interference prestressing have not been derived. In this paper, based on the method of calculating the prestressing of the thick cylinder in interference fit, the ring gear is found to be equivalent to a thick cylinder, and the distribution rule of prestressing of the ring gear in the interference fit is inferred. Then, by modeling and analyzing the gearbox body and ring gear in the interference fit using ABAQUS, the distribution rule of prestressing the ring gear in the interference fit is obtained through a numerical simulation. Finally, the prestressing of the ring gear in the interference fit is measured using X-ray diffraction, and the distribution rule of prestressing of the ring gear in the interference fit is obtained through analysis. Compared with the distribution rule of prestressing in theory, numerical simulation, and experiment, the theoretical distribution rule of prestressing is amended through a statistical method, and a more accurate formula of prestressing is obtained. Through the calculation of the stress and bending moment in the dangerous section of the ring gear through prestressing, the formula for checking the tooth root flexural fatigue strength in the interference fit prestressing is inferred. This research proposes a tooth root bending strength conditional formula for the inner ring gear of the interference fit, which serves as a guide for the design and production of the actual interference joint inner ring gear.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.