RESUMEN
The railway rivet is one of the most important and easily damaged parts of the connection. If rivets develop cracks during the production process, their load-bearing capacity will be reduced, thereby increasing the risk of failure. Fluorescent magnetic particle flaw detection (FMPFD) is a widely used inspection method for train fasteners. Manual inspection is not only time-consuming but also prone to miss detection, therefore intelligent detection system has important application value. However, the fluorescent crack images obtained by FMPFD present challenges for intelligent detection, such as the dense, multi-scaled and uninstantiated cracks. In addition, there is limited research on fluorescent rivet crack detection. This paper adopts instance segmentation to achieve automatic cracks detection of rivets. A decentralized target center and low overlap rate labeling method is proposed, and a Gaussian-weighted correction post-processing method is introduced to improve the recall rate in the areas of dense cracks. An efficient channel spatial attention mechanism for feature extraction is proposed in order to enhance the detection of multi-scale cracks. For uninstantiated cracks, an improvement of crack detection in uninstantiated regions based on multi task feature learning is proposed, thoroughly utilizing the semantic and spatial features of the fluorescent cracks. The experimental results show that the improved methods are better than the baseline and some cutting-edge algorithms, achieving a recall rate and mAP0.5 of 86.4% and 90.3%. In addition, a single coil non-contact train rivet composite magnetization device is built for rivets that can magnetize different shapes of rivets and has universality.
RESUMEN
Herein, we prepared and compared two water-soluble amphiphilic zein-based nanocarrier systems with avermectin (AVM) payload to enhance pesticide's water-dispersity, foliage wettability, adhesion, anti-UV, and pH-responsive controlled release property. Ethylene glycol diglycidyl ether (EGDE) and diethanolamine (DEA) were utilized to conjugate with hydrophobic zein via a ring-opening reaction and then encapsulated with AVM via a hydrophobic interaction to fabricate a nanopesticide marked as AVM@Zein-EGDE/DEA. For the sake of further improving the nanocarrier's performance, sodium carboxymethyl cellulose (CMC) was grafted with methyl methacrylate (MMA) and 2-hydroxyethyl methacrylate (HEMA) to form a kind of copolymer CMC-g-P(HEMA-MMA), which was applied to conjugate with Zein-EGDE via a ring-opening reaction. Likewise, another nanopesticide system named AVM@Zein-EGDE/CMC-g-P(HEMA-MMA) was obtained through hydrophobic interactions as well as the electrostatic effect. Various techniques were utilized to confirm chemical interaction, thermal behavior, structural characteristics, and stability. The results showed that AVM encapsulated in Zein-EGDE/CMC-g-P(HEMA-MMA) possessed a larger particle size with an average value of 180-254 nm than AVM loaded in Zein-EGDE/DEA with 144-175 nm but had better stability in aqueous solution. Also, AVM loaded in Zein-EGDE/CMC-g-P(HEMA-MMA) enhanced the encapsulation efficiency, and both of them exhibited excellent pH-responsive sustained release behavior. Besides, the former improved wettability on a cucumber leaf surface and enhanced adhesion ability compared to AVM@Zein-EGDE/DEA because of CMC-g-P(HEMA-MMA) with hydrophobic segments. Similarly, anti-UV performance was also enhanced owing to CMC-g-P(HEMA-MMA) as an additional protective layer. More importantly, the encapsulation of Zein-EGDE/DEA and Zein-EGDE/CMC-g-P(HEMA-MMA) as protective barriers for AVM still retained a similar toxicity level. Overall, we demonstrated the proof of concept for the application of amphiphilic zein-based nanomaterials as aqueous nanocarriers for hydrophobic pesticides.