| 180 | 0 | 68 |
| 下载次数 | 被引频次 | 阅读次数 |
在近场电纺工艺中，针对泰勒锥状态进行实时监测与调控有利于生成直径一致性更高的微纳射流，从而提高电纺纤维的质量。基于YOLOv7的近场电纺泰勒锥识别算法及电压反馈调控有助于实现上述目标。首先，建立近场电纺监测平台对泰勒锥形态进行实时监测；随后，构建基于YOLOv7泰勒锥识别模型，采用图像处理实时判别泰勒锥在生产过程中的具体形态；最后，对生产时泰勒锥面积实时变化值与设定的标准泰勒锥面积阈值进行对比，使用实时近场电纺电压反馈调控来保障泰勒锥生成的射流尺寸稳定。经实验验证，电压反馈调控下沉积纤维直径的方差为3.861 74,远小于未使用电压反馈调控下的方差(24.529 1),故上述反馈调控有利于近场电纺工艺生产直径一致性更高的纤维。
Abstract：In the near-field electrospinning process, real-time monitoring and regulation of the Taylor cone state is conducive to the generation of micro-nano jets with higher diameter consistency, and thus the quality of electrospinning fibers can be improved. The near-field electrospinning Taylor cone recognition algorithm based on YOLOv7 and voltage feedback regulation are conducive to achieving the above objectives. Firstly, a near-field electrospinning detection platform was established to monitor the Taylor cone shape in real-time. And then, the Taylor cone recognition model based on YOLOv7 was constructed, and the specific shape of the Taylor cone in the production process was discriminated in real-time by image processing. Finally, the real-time change value of the Taylor cone area during production with the threshold value of the set standard Taylor cone area were compared, and the real-time near field electrospinning voltage feedback regulation was used to ensure the stability of the jet size generated by the Taylor cone. It is verified by experiments that the variance of the deposited fiber diameter with the voltage feedback regulation is 3.861 74, which is much smaller than the variance(24.529 1) without the voltage feedback regulation. Therefore, the above feedback regulation is conducive to producing fibers with higher diameter consistency by the near-field electrospinning process.
[1] ZENG X L,YE L,GUO K,et al.Fibrous epoxy substrate with high thermal conductivity and low dielectric property for flexible electronics [J].Advanced Electronic Materials,2016,2(5):1500485-1-1500485-8.
[2] YIN Z P,HUANG Y A,BU N B,et al.Inkjet printing for flexible electronics:materials,processes and equipments [J].Chinese Science Bulletin,2010,55(30):3383-3407.
[3] 张延辉.生物基静电纺纳米纤维空气过滤材料研究 [J].上海纺织科技，2022,50(5):18-22.
[4] DINIS T M,VIDAL G,JOSE R R,et al.Complementary effects of two growth factors in multifunctionalized silk nanofibers for nerve reconstruction [J].Plos One,2014,9(10):e109770-1-e109770-9.
[5] 杜迅，陈莉，王亚梅，等.纳米纤维基酸敏比色传感器的制备及应用 [J].上海纺织科技，2022,50(3):53-56.
[6] 郑高峰，姜佳昕，康国毅，等.光栅编码器电纺直写精确喷印 [J].光学精密工程，2021,29(10):2393-2399.
[7] CHARLES J D,CELAL B,MIKO C,et al.Pressure control system for electros pinning process [J].Polymer Engineering and Science,2010,50(4):800-810.
[8] MIESZCZANEK P,EGGERT S,CORKE P,et al.Automated melt electrowitting platform with real-time process monitoring [J].HardwareX,2021,10:246-260.
[9] MIESZCZANEK P,ROBINSON T M,DALTON P D,et al.Convergence of machine vision and melt electrowriting [J].Advanced Materials,2021,33(29):120-132.
[10] WUNNER F M,MIESZCZANEK P,BAS O,et al.Printomics:the high-throughput analysis of printing parameters applied to melt electrowriting [J].Biofabrication,2019,11(2):025004-1-025004-14.
[11] 刘大利，郭俊，方淑慧，等.使用目标多特征识别的纳米纤维制造在线监测系统 [J].光学精密工程，2012,20(2):360-368.
[12] WANG H,OU W C,ZHONG H Y,et al.Exploring precise deposition and influence mechanism for micro-scale serpentine structure fiber [J].Advances in Nano Research,2022,12(2):151-165.
[13] WANG C Y,BOCHKOVSKIY A,LIAO H Y.YOLOv7:trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [J].Computer Science,2022,2207:02696-1-02696-15.
[14] 王年涛，王淑青，黄剑锋，等.基于改进YOLOv5神经网络的绝缘子缺陷检测方法 [J].激光杂志，2022,43(8):60-65.
[15] GUO Z X,WANG C,YANG G,et al.MSFT-YOLO:improved YOLOv5 based on transformer for detecting defects of steel surface [J].Sensors,2022,22(9):3467-1-3467-15.
[16] 贺愉婷，车进，吴金蔓.基于YOLOv5和重识别的行人多目标跟踪方法 [J].液晶与显示，2022,37(7):880-890.
[17] LV H H,YAN H B,LIU K,et al.YOLOV5-AC:attention mechanism-based lightweight YOLOv5 for track pedestrian detection [J].Sensors,2022,22(15):5903-1-5903-25.
[18] ZHAN W,SUN C F,WANG M,et al.An improved YOLOv5 real-time detection method for small objects captured by UAV [J].Soft Computing,2022,26(1):361-373.
[19] 龙怡灿，雷蓉，董杨，等.基于YOLOv5算法的飞机类型光学遥感识别 [J].地球信息科学学报，2022,24(3):572-582.
[20] FANG W,WANG L,REN P M.Tinier-YOLO:a real-time object detection method for constrained environments [J].IEEE Access,2019,8:1935-1944.
基本信息:
DOI：10.13250/j.cnki.wndz.2023.06.015
中图分类号:TQ340.64
引用信息:
[1]王晗,林锐楠,欧伟程,等.基于YOLOv7近场电纺泰勒锥识别的电压反馈调控[J].微纳电子技术,2023,60(06):931-938.DOI:10.13250/j.cnki.wndz.2023.06.015.
基金信息:
国家自然科学基金(62171142); 广东省自然科学基金(2021A1515011908); 广东省重大科技计划(X190071UZ190)
2023-06-15
2023-06-15