智能化电弧熔丝增材制造在线监控研究现状
武汉工程大学, 机电工程学院, 湖北武汉 430205
| 摘 要： | 电弧熔丝增材制造（WAAM）凭借沉积效率高、成本低及成形尺寸受限小等优势，在大型复杂金属构件的快速制造领域展现出显著潜力。然而，受逐层累积热循环影响，成形精度控制难、内部微观缺陷（如气孔、裂纹）及力学性能各向异性等问题，严重制约了该技术的产业化应用与可靠性。针对WAAM工艺参数间强耦合、非线性及随机扰动等特征，智能化在线监控已成为提升制造质量的核心途径。本文首先梳理了WAAM过程信息监测的多元传感方案，涵盖视觉（可见光、激光、红外、X射线）、声发射及电弧光谱传感，对比分析了各技术在捕捉熔池形貌与内部质量特征方面的性能边界；继而探讨了机器学习（ML）在信号特征提取与状态判别中的研究进展，重点剖析了深度神经网络与支持向量机在缺陷识别及工艺预测中的鲁棒性表现。在此基础上，归纳了基于数据驱动模型与强化学习算法的智能控制策略，探讨了其在实现熔滴过渡、送丝速率等关键参数自适应控制中的应用价值。最后，针对当前多源数据融合困难、高质量样本集匮乏及多变量协同控制薄弱等瓶颈问题，对WAAM智能化制造的发展趋势进行了展望 |
| 关 键 词： | 电弧增材制造; 在线监控; 视觉传感; 机器学习; 智能控制 |
| DOI： | 10.57237/j.cst.2026.02.004 |
View:
Downloads:
收稿日期: 2026-04-30
接受日期: 2026-05-15
在线出版日期: 2026-05-19
Research Status of Intelligent Online Monitoring for Wire Arc Additive Manufacturing
School of Mechanical and Electrical Engineering, Wuhan Institute of Technology, Wuhan 430205, China
| Abstract: | Wire arc additive manufacturing (WAAM), owing to its advantages of high deposition efficiency, low cost, and low limitations on part dimensions, exhibits significant potential in the rapid fabrication of large and complex metal components. However, issues such as difficulties in geometrical accuracy control, internal micro-defects (e.g., porosity, cracks), and anisotropy of mechanical properties caused by the cyclic thermal history during layer-by-layer deposition severely restrict the industrial application and reliability of this technology. In response to the strongly coupled, nonlinear, and randomly disturbed characteristics of WAAM process parameters, intelligent online monitoring has become a key approach to improving manufacturing quality. This paper first reviews the diverse sensing schemes for WAAM process information monitoring, covering vision-based (visible light, laser, infrared, X-ray), acoustic emission, and arc spectroscopy methods, and comparatively analyzes the performance boundaries of each technique in capturing melt pool morphology and internal quality features. Subsequently, the research progress of machine learning (ML) in signal feature extraction and state classification is discussed, with emphasis on the robustness of deep neural networks and support vector machines in defect identification and process prediction. On this basis, intelligent control strategies based on data-driven models and reinforcement learning algorithms are summarized, and their application value in achieving adaptive control of key parameters such as droplet transfer and wire feed speed is explored. Finally, in view of current bottlenecks including difficulties in multi-source data fusion, scarcity of high-quality sample datasets, and weaknesses in multivariable cooperative control, the development trends of intelligent WAAM manufacturing are prospected. |
| Keywords: | WAAM; Online Monitoring; Vision Sensing; Machine Learning; Intelligent Control |
参考文献
| [1] | Cunningham C R, Flynn J M, Shokrani A, et al. Invited review article: strategies and processes for high quality wire arc additive manufacturing [J]. Additive Manufacturing, 2018, 22: 672-686. https://doi.org/10.1016/j.addma.2018.06.020 |
| [2] | Jin Z, Zhang Z, Gu G X. Automated real-time detection and prediction of interlayer imperfections in additive manufacturing processes using artificial intelligence [J]. Advanced Intelligent Systems, 2020, 2(1): 1900130. https://doi.org/10.1002/aisy.201900130 |
| [3] | McCann R, et al. In-situ sensing, process monitoring and machine control in laser powder bed fusion: a review [J]. Additive Manufacturing, 2021, 45: 102058. https://doi.org/10.1016/j.addma.2021.102058 |
| [4] | Ma C, Yan Y H, Yan Z Z, et al. Investigation of bypass-coupled double-pulsed directed energy deposition of Al-Mg alloys [J]. Additive Manufacturing, 2022, 58: 103058. https://doi.org/10.1016/j.addma.2022.103058 |
| [5] | 余鹏飞. 基于激光视觉传感的焊缝检测与焊接过程控制研究 [D]. 长春: 长春工业大学, 2024. |
| [6] | 李冰, 白云山, 赵宽, 等. 基于视觉传感的薄板对接焊缝检测方法研究 [J]. 热加工工艺, 2024, 53(17): 13-19. https://doi.org/10.14158/j.cnki.1001-3814.20221431 |
| [7] | Garmendia I, Leunda J, Pujana J, et al. In-process height control during laser metal deposition based on structured light 3D scanning [C] // Procedia CIRP, 2018, 74: 87-91. https://doi.org/10.1016/j.procir.2017.12.098 |
| [8] | Wang H, Qi S N, Zang T J, et al. In-situ surface inspection for wire-arc directed energy deposition integrating 3D topography reconstruction, defect detection and roughness measurement [J]. Optics & Laser Technology, 2025, 187: 112871. https://doi.org/10.1016/j.optlastec.2025.112871 |
| [9] | Xiong J, Li Y J, Yin Z Q, et al. Determination of surface roughness in wire and arc additive manufacturing based on laser vision sensing [J]. Chinese Journal of Mechanical Engineering, 2018, 31: 74. https://doi.org/10.1186/s10033-018-0276-8 |
| [10] | Yu R, He S, Yang D, et al. Identification of cladding layer offset using infrared temperature measurement and deep learning for WAAM [J]. Optics and Lasers, 2024, 170: 110243. https://doi.org/10.1016/j.optlastec.2023.110243 |
| [11] | Chen, X, Fu Y H, Kong F R, et al. An in-process multi-feature data fusion nondestructive testing approach for wire arc additive manufacturing [J]. Rapid Prototyping Journal, 2021, 28(3): 573-584. https://doi.org/10.1108/rpj-02-2021-0034 |
| [12] | Al-Nabulsi Z, Mottram J T, Gillie M, et al. Mechanical and X ray computed tomography characterisation of a WAAM 3D printed steel plate for structural engineering applications [J]. Construction and Building Materials, 2021, 274: 121700. https://doi.org/10.1016/j.conbuildmat.2020.121700 |
| [13] | Brown D W, Losko A, Carpenter J S, et al. In-situ high-energy X-ray diffraction during a linear deposition of 308 stainless steel via wire arc additive manufacture [J]. Metallurgical and Materials Transactions A, 2020, 51: 1379-1394. https://doi.org/10.1007/s11661-019-05605-2 |
| [14] | Bigelow T A, Schneider B, Taheri H. Detection of pores in additive manufactured parts by near field response of laser induced ultrasound [C] AIP Conference Proceedings, 2019, 2102(1): 70002. https://doi.org/10.1063/1.5099802 |
| [15] | Rozin E H, Sultan T, Taheri H, et al. Detecting selective laser melting beam power from ultrasonic temporal and spectral responses of phononic crystal artifacts toward in-situ real-time quality monitoring [J]. 3D Printing and Additive Manufacturing, 2024, 11(6): 1982-1995. https://doi.org/10.1089/3dp.2023.0063 |
| [16] | Zhang H, Qian R W, Tang W L, et al. Acoustic signal-based defect identification for directed energy deposition-arc using wavelet time-frequency diagrams [J]. Sensors, 2024, 24(13): 4397. https://doi.org/10.3390/s24134397 |
| [17] | Alcaraz J. Developing process monitoring and real-time defect detection for wire-arc additive manufacturing [D]. Leuven, Belgium: KU Leuven, 2025. |
| [18] | Hauser T, Reisch R T, Kamps T, et al. Acoustic emissions in directed energy deposition processes [J]. The International Journal of Advanced Manufacturing Technology, 2022, 119: 3517-3532. https://doi.org/10.1007/s00170-021-08598-8 |
| [19] | Zhang C, Chen C, Zeng X Y, et al. Spectral diagnosis of wire arc additive manufacturing of Al alloys [J]. Additive Manufacturing, 2019, 30: 100869. https://doi.org/10.1016/j.addma.2019.100869 |
| [20] | Zhuang Z, Guo Y T, Jing H, et al. Quality monitoring in wire-arc additive manufacturing based on cooperative awareness of spectrum and vision [J]. Optik, 2019, 181: 351-360. https://doi.org/10.1016/j.ijleo.2018.12.071 |
| [21] | Hamoud M, Sobhi A. A new algorithm for optimal process parameters based on minimum building time in additive manufacturing [J]. Beni-Suef University Journal of Basic and Applied Sciences, 2022, 11(1): 80. https://doi.org/10.1186/s43088-022-00260-w |
| [22] | Cheng J, De Waele W. Prediction and optimization of surface waviness of WAAM components using a hybrid Rank-Gaussian PSO algorithm and ANN [J]. Structures, 2024, 69: 107247. https://doi.org/10.1016/j.istruc.2024.107247 |
| [23] | Guizani A, Hammadi M, Yousfi L, et al. Predictive modeling of part quality in the WAAM process using PCA model reduction and machine learning [C] Design and Modeling of Mechanical Systems - VI. 2023: 410-419. https://doi.org/10.1007/978-3-031-65007-9_43 |
| [24] | Paturi U M R, Palakurthy S, Reddy A, et al. Role of Machine Learning in Additive Manufacturing of Titanium Alloys—A Review [J]. Archives of Computational Methods in Engineering, 2023, 30(6): 3867-3895. https://doi.org/10.1007/s11831-023-09969-y |
| [25] | Lee C, Seo G, Kim D B, et al. Development of defect detection AI model for wire + arc additive manufacturing using high dynamic range images [J]. Applied Sciences, 2021, 11: 7541. https://doi.org/10.3390/app11167541 |
| [26] | Pan H, Pang Z, Wang Y, et al. A new image recognition and classification method combining transfer learning algorithm and mobilenet model for welding defects [J]. IEEE Access, 2020, 8: 119951-119960. https://doi.org/10.1109/access.2020.3005450 |
| [27] | Nomura K, Fukushima K, Matsumura T, et al. Burnthrough prediction and weld depth estimation by deep learning model monitoring the molten pool in gas metal arc welding with gap fluctuation [J]. Journal of Manufacturing Processes, 2021, 61: 590-600. https://doi.org/10.1016/j.jmapro.2020.10.019 |
| [28] | Qin J, Wang Y P, Ding J L, et al. Optimal droplet transfer mode maintenance for wire + arc additive manufacturing (WAAM) based on deep learning [J]. Journal of Intelligent Manufacturing, 2023, 34: 3173-3189. https://doi.org/10.1007/s10845-022-01986-1 |
| [29] | Huang Y, Yue C, Tan X, et al. Quality prediction for wire arc additive manufacturing based on multi-source signals, whale optimization algorithm–variational modal decomposition, and one-dimensional convolutional neural network [J]. Journal of Materials Engineering and Performance, 2024, 33(5): 2331-2346. https://doi.org/10.1007/s11665-023-08768-7 |
| [30] | Hu D, Lyu B, Wang J J, et al. Study on HOG-SVM detection method of weld surface defects using laser visual sensing [J]. Transactions of the China Welding Institution, 2023, 44(1): 57-62, 70. https://doi.org/10.12073/j.hjxb.20211231001 |
| [31] | Zhang H, Bai X, Dong H, et al. Modelling and prediction of process parameters with low energy consumption in wire arc additive manufacturing based on machine learning [J]. Metals, 2024, 14(5): 567. https://doi.org/10.3390/met14050567 |
