Rapid Identification of Morphology Defects of Arc Welding Assisted Aluminum Alloy Droplet Deposition Based on ORB-SVM

GUO Xinxin; DU Jun; MA Chen; WEI Zhengying

doi:10.7652/xjtuxb202210020

您当前的位置：

首页 >

文章列表页 >

Rapid Identification of Morphology Defects of Arc Welding Assisted Aluminum Alloy Droplet Deposition Based on ORB-SVM

更新时间：2025-07-09

- Rapid Identification of Morphology Defects of Arc Welding Assisted Aluminum Alloy Droplet Deposition Based on ORB-SVM
- Vol. 56, Issue 10, Pages: 201-208(2022)
- 作者机构：
  
  西安交通大学机械制造系统工程国家重点实验室,西安,710049
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202210020
  CLC： V260.5
- Online First：10 October 2022，
  
  Published：2022
- 稿件说明：
移动端阅览
GUO Xinxin, DU Jun, MA Chen, et al. Rapid Identification of Morphology Defects of Arc Welding Assisted Aluminum Alloy Droplet Deposition Based on ORB-SVM[J]. 2022, 56(10): 201-208.
DOI：

GUO Xinxin, DU Jun, MA Chen, et al. Rapid Identification of Morphology Defects of Arc Welding Assisted Aluminum Alloy Droplet Deposition Based on ORB-SVM[J]. 2022, 56(10): 201-208. DOI： 10.7652/xjtuxb202210020.

摘要

针对铝合金熔滴复合电弧增材制造堆积层潜在的形貌缺陷

以及图像处理时长导致的整个监控系统滞后的问题

建立了一个快速原位被动视觉系统来识别缺陷类型。首先

基于ORB算法自动提取堆积层形貌关键点的二值字符串描述子; 然后

采用BOW模型得到维度相同的图像特征描述向量; 最后

利用提取的特征向量对SVM分类器进行训练

并在分类准确性和处理时间方面验证了性能。结果表明

ORB-SVM模型对堆积层形貌识别的准确率为0.96

特征提取、编码与识别总时间约为9 ms/帧

为确保熔滴复合电弧增材制造在复杂制造条件下的堆积层精度提供了一种可行的解决方案

并且在实时监控应用中具有较大的潜力。

Abstract

A fast in-situ passive vision system is established to identify the defect types in the context of the potential morphology defects of the arc welding assisted aluminum alloy droplet deposition additive manufacturing and the lag of the entire monitoring system caused by the image processing time. Firstly

the binary string descriptors of the key points of the deposition layer morphology are automatically extracted based on ORB algorithm; then the BOW model is used to obtain the image feature description vectors with the same dimension; finally

the SVM classifier is trained with the extracted feature vectors

and the performance is verified in terms of classification accuracy and processing time. The results show that the ORB-SVM model has an accuracy of 0.96 for recognizing the deposition layer morphology

and the total time for feature extraction

encoding and recognition of a single image is about 9 milliseconds. In addition

it provides a feasible solution to ensure the deposition layer accuracy of arc welding assisted droplet deposition additive manufacturing under complex manufacturing conditions and has a great potential in real-time monitoring.

关键词

Keywords

references

黄智, 贾卫博, 王颢铭, 等. 选区激光熔化激光能量在TC4粉末中分布特性研究 [J]. 西安交通大学学报, 2022, 56(4): 109-118.

HUANG Zhi, JIA Weibo, WANG Haoming, et al. Study on distribution characteristics of laser energy in TC4 powder in selective laser melting process [J]. Journal of Xi'an Jiaotong University, 2022, 56(4): 109-118.

KENEVISI M S, LIN Feng. Selective electron beam melting of high strength Al2024 alloy: microstructural characterization and mechanical properties [J]. Journal of Alloys and Compounds, 2020, 843: 155866.

CHEN Zhehan, GUO Xinxin, SHI Jing. Hardness prediction and verification based on key temperature features during the directed energy deposition process [J]. International Journal of Precision Engineering and Manufacturing: Green Technology, 2021, 8(2): 453-469.

赵昀, 卢振洋, 陈树君, 等. 薄壁结构冷金属过渡增材制造工艺优化 [J]. 西安交通大学学报, 2019, 53(8): 82-89.

ZHAO Yun, LU Zhenyang, CHEN Shujun, et al. Optimization of manufacturing process for thin-walled structures based on cold metal transfer [J]. Journal of Xi'an Jiaotong University, 2019, 53(8): 82-89.

WANG Zeya, ZIMMER-CHEVRET S, LÉONARD F, et al. Improvement strategy for the geometric accuracy of bead's beginning and end parts in wire-arc additive manufacturing(WAAM)[J]. The International Journal of Advanced Manufacturing Technology, 2022, 118(7): 2139-2151.

OMIYALE B O, OLUGBADE T O, ABIOYE T E, et al. Wire arc additive manufacturing of aluminium alloys for aerospace and automotive applications: a review [J]. Materials Science and Technology, 2022, 38(7): 391-408.

杜军, 蒋敏博, 张永恒, 等. TIG电弧复合熔滴沉积增材制造45钢/铅合金双金属结构工艺研究 [J]. 材料导报, 2022, 36(2): 144-148.

DU Jun, JIANG Minbo, ZHANG Yongheng, et al. Study on the TIG-droplet hybrid additive manufacturing of 45 steel/lead alloy bimetallic structure [J]. Materials Reports, 2022, 36(2): 144-148.

贺鹏飞, 魏正英, 杜军, 等. 铝合金熔滴复合电弧沉积同步WC颗粒强化增材制造工艺研究 [J]. 机械工程学报, 2022, 58(5): 258-267.

HE Pengfei, WEI Zhengying, DU Jun, et al. Investigation of droplet + arc deposition additive manufacturing with WCP simultaneous reinforcement for aluminum alloy [J]. Journal of Mechanical Engineering, 2022, 58(5): 258-267.

DU Jun, WANG Daqing, XU Siyuan. Gas Tungsten arc welding assisted droplet deposition manufacturing of steel/lead bimetallic structures [J]. Journal of Materials Processing Technology, 2021, 292: 117069.

WANG Xin, XIAO Hong, LI Haiqing, et al. Detection and control of the morphology of TIG-metal fused coating additive manufacturing [J]. Journal of Mechanical Science and Technology, 2021, 35(5): 2161-2166.

WANG C, TAN X P, TOR S B, et al. Machine learning in additive manufacturing: state-of-the-art and perspectives [J]. Additive Manufacturing, 2020, 36: 101538.

SHI Zhangyue, MANDAL S, HARIMKAR S, et al. Surface morphology analysis using convolutional autoencoder in additive manufacturing with laser engineered net shaping [J]. Procedia Manufacturing, 2021, 53: 16-23.

ZHANG Binbin, JAISWAL P, RAI R, et al. Convolutional neural network-based inspection of metal additive manufacturing parts [J]. Rapid Prototyping Journal, 2019, 25(3): 530-540.

ZHU Haixing, GE Weimin, LIU Zhenzhong. Deep learning-based classification of weld surface defects [J]. Applied Sciences, 2019, 9(16): 3312.

DENG Junhao, XU Yanling, ZUO Zhangchi, et al. Bead geometry prediction for multi-layer and multi-bead wire and arc additive manufacturing based on XGBoost [C]//Transactions on Intelligent Welding Manufacturing. Cham, Germany: Springer, 2019: 125-135.

XIA Chunyang, PAN Zengxi, POLDEN J, et al. Modelling and prediction of surface roughness in wire arc additive manufacturing using machine learning [J]. Journal of Intelligent Manufacturing, 2022, 33(5): 1467-1482.

REN Zhonghe, FANG Fengzhou, YAN Ning, et al. State of the art in defect detection based on machine vision [J]. International Journal of Precision Engineering and Manufacturing: Green Technology, 2022, 9(2): 661-691.

陈雪松, 徐学军. 一种二值图像特征提取的新理论 [J]. 计算机工程与科学, 2011, 33(6): 31-36.

CHEN Xuesong, XU Xuejun. A new theory of feature extraction for binary images [J]. Computer Engineering Science, 2011, 33(6): 31-36.

MA Chen, DANG Haifei, DU Jun, et al. Research on automated defect classification based on visual sensing and convolutional neural network-support vector machine for GTA-assisted droplet deposition manufacturing process [J]. Metals, 2021, 11(4): 639.

RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB: an efficient alternative to SIFT or SURF [C]//2011 International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2011: 2564-2571.

ROSTEN E, DRUMMOND T. Machine learning for high-speed corner detection [C]//Computer Vision-ECCV 2006. Berlin, Germany: Springer, 2006: 430-443.[22] CALONDER M, LEPETIT V, STRECHA C, et al. BRIEF: binary robust independent elementary features [C]//Computer Vision-ECCV 2010. Berlin, Germany: Springer, 2010: 778-792.

BANSAL M, KUMAR M, KUMAR M. 2D object recognition: a comparative analysis of SIFT, SURF and ORB feature descriptors [J]. Multimedia Tools and Applications, 2021, 80(12): 18839-18857.

费旋珈, 孔莹莹. 基于SIFT-SVM的北冰洋海冰识别研究 [J]. 电子技术与软件工程, 2016(24): 92-95.

FEI Xuanjia, KONG Yingying. Research on arctic ocean sea ice identification based on SIFT-SVM [J]. Electronic Technology Software Engineering, 2016(24): 92-95.

BRERETON R G, LLOYD G R. Support vector machines for classification and regression [J]. Analyst, 2010, 135(2): 230-267.

YOU Deyong, GAO Xiangdong, KATAYAMA S. Multisensor fusion system for monitoring high-power disk laser welding using support vector machine [J]. IEEE Transactions on Industrial Informatics, 2014, 10(2): 1285-1295.

ZHANG Yingjie, HONG G S, YE Dongsen, et al. Extraction and evaluation of melt pool, plume and spatter information for powder-bed fusion AM process monitoring [J]. Materials Design, 2018, 156: 458-469.

师彬彬, 陈哲涵. 基于图像特征融合的粉末床缺陷检测方法 [J]. 航空学报, 2021, 42(10): 420-431.

SHI Binbin, CHEN Zhehan. Defect detection method of powder bed based on image feature fusion [J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(10): 420-431.

MA W, KAUTZ E J, BASKARAN A, et al. Image-driven discriminative and generative machine learning algorithms for establishing microstructure-processing relationships [J]. Journal of Applied Physics, 2020, 128(13): 134901.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Fast Calculation Method for Thermal Flow Fields in Transformer Windings Based on PI-DeepONet

Sensitivity Analysis of Foil Geometrical Parameters for the Third-Generation CO2 Gas Foil Bearings Based on Design of Experiments Method

Effects of Steam Addition on the Swirl Combustion and Emission Characteristics of Cracked Ammonia

Integrated and Joint Design Optimization of Centrifugal Compressor Impeller and Casing Treatment at Multiple Working Points

Review of the Application of EBSILON Software in Combined Heat and Power System Optimization

Related Author

No data

Related Institution

No data

⁰