鉴定(生物学)
电子鼻
涡流
杀虫剂
航空航天工程
环境科学
计算机科学
物理
工程类
机械
人工智能
生态学
生物
作者
Xietao Wang,Cheng Kong,Lei Zhang,Xiaohui Weng,Zhiyong Chang
标识
DOI:10.20944/preprints202411.2201.v1
摘要
The grain yield in China’s Northeast black soil region represents 1/4 of the national total, resulting in an annual pesticide usage of about 190,000 tons. Pesticide identification is crucial for maintaining the health of black soil. Due to low gas volume and low concentration of pesticide volatile gas in black soil, the traditional vertical electronic noses (E-nose) cannot effectively capture them. To address this issue, we proposed an externally driven vortex E-nose that achieves improved performance. Through multi-objective optimization strategy using computational fluid dynamics (CFD), response surface methodology (RSM), and non-dominated sorting genetic algorithm II (NSGA-II), vortex E-nose was obtained, with an average velocity of 0.117 m/s and an average vorticity of 133.175 s-1 around sensors. The 3D-printed sampling chamber, with a volume of only 81.447 cm³, supports portable applications. Furthermore, pesticide odor information captured by vortex E-nose is analyzed using a convolutional neural network (CNN) algorithm. Experimental results show that vortex E-nose achieves 100% accuracy in identifying pesticide types and 97.62% in detecting pesticide components in black soil. The vortex E-nose we designed has potential advantages in trace gas detection environments.
科研通智能强力驱动
Strongly Powered by AbleSci AI