船舶从生产到投入使用，在作业中难免会因为焊接节点的设计问题、货物装卸的操作不规范以及诸如线性尺度较大、吃水较多而受风、流等外部环境的影响而对船体结构造成腐蚀，最终导致船体外部出现裂纹，给船舶的航行带来安全隐患。因此加强关于船舶裂纹的排查，是保证船舶安全行驶的关键。本文从改进卷积神经网络入手，以工程船为例，通过对其船舶纹理进行图形分割研究，提升智能检测的精准度，从而为运维检修带来一定的帮助，并为海上作业的安全性检测提供理论支持。
From production to putting into use, it is inevitable that ships will suffer from corrosion to the hull structure due to the design issues of welded joints, non-standard cargo handling operations, and external environments such as large linear scales and high drafts, resulting in cracks on the exterior of the hull, which pose potential safety hazards for shipping trips. Therefore, strengthening the inspection of ship cracks is the key to ensuring the safe operation of ships. This article will attempt to improve the convolutional neural network, take engineering ships as an example, and conduct graphic segmentation research on their ship texture, aiming to improve the accuracy of intelligent detection, thereby bringing some help to relevant operation and maintenance personnel in the maintenance work, and providing theoretical support for the safety detection of offshore industry.
2023,45(8): 177-180 收稿日期：2022-11-07
DOI：10.3404/j.issn.1672-7649.2023.08.035
分类号：TN911.73
作者简介：朱素杰(1987-),女,硕士,讲师,主要从事图像识别研究
参考文献：
[1] 鲁玉军, 周世豪, 胡小勇. 基于BP神经网络和小波神经网络的太阳辐射强度预测[J]. 软件工程, 2023, 26(1): 5–8+4
LU Yu-jun, ZHOU Shi-hao, HU Xiao-yong. Prediction of solar radiation intensity based on BP neural network and wavelet neural network[J]. Software Engineering, 2023, 26(1): 5–8+4
[2] 刘月峰, 杨涵晰, 蔡爽, 等. 基于改进卷积神经网络的单幅图像超分辨率重建方法[J]. 计算机应用, 2019, 39(5): 1440–1447
LIU Yue-feng, YANG Han-xi, CAI Shuang, et al. Single image super-resolution reconstruction method based on improved convolutional neural network[J]. Computer Applications, 2019, 39(5): 1440–1447
[3] 王霄, 朱恩照, 艾自胜. 卷积神经网络的原理及其在医学影像诊断中的应用[J]. 中国医学物理学杂志, 2022, 39(12): 1485–1489
WANG Xiao, ZHU En-zhao, AI Zi-sheng. The principle of convolutional neural network and its application in medical imaging diagnosis[J]. Chinese Journal of Medical Physics, 2022, 39(12): 1485–1489
[4] 刘宇, 王伟伟, 邸克, 等. 基于SA优化BP神经网络的室内外无缝定位算法[J]. 计算机仿真, 2022, 39(12): 485–489
LIU Yu, WANG Wei-wei, DI Ke, et al. Indoor and outdoor seamless positioning algorithm based on SA optimized BP neural network[J]. Computer Simulation, 2022, 39(12): 485–489
[5] 石晨晨, 陈宏涛, 杨波, 等. 基于人工神经网络的水下爆破振动预测技术[J]. 价值工程, 2022, 41(34): 133–135
SHI Chen-chen, CHEN Hong-tao, YANG Bo, et al. Underwater blasting vibration prediction technology based on artificial neural network[J]. Value Engineering, 2022, 41(34): 133–135
[6] 陈欣, 王凌, 朱佳佳, 等. 深度卷积神经网络图像超分辨率重建方法研究[J]. 单片机与嵌入式系统应用, 2023, 23(1): 7–10
CHEN Xin, WANG Ling, ZHU Jiajia, et al. Research on image super-resolution reconstruction method of deep convolutional neural network[J]. Application of Microcontroller and Embedded System, 2023, 23(1): 7–10
