Weld Defect Detection of a CMT Arc-Welded Aluminum Alloy Sheet Based on Arc Sound Signal Processing
Source abstract
Abstract
The cold metal transfer (CMT) process is widely used in thin plate welding because of its characteristics of low heat input and stable arc. In actual production, a larger weld gap, misalignment, or other problems due to assembly error lead to serious welding defects, such as burn-through and a lack of fusion. The arc sound contains a wealth of information related to the quality of the weld. This work analyzes the mechanism of CMT arc sound generation, as well as the correlation between the time–frequency spectrum of the arc sound signal and welding quality. This paper studies the extraction of the multi-channel time–frequency spectrum of an arc sound and inputs it to a custom convolutional neural network for the CMT welding defect identification of thin aluminum alloy plates. The experimental result shows that the average accuracy of the proposed model is 91.49% in the defect identification of a CMT arc-welded aluminum alloy sheet, which is higher than that of the single-channel time–frequency convolutional neural network and other traditional classification models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Welding Techniques and Residual Stresses · Advanced machining processes and optimization · Laser Material Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Materials Science and Engineering, Dalian Jiaotong University, Dalian 116028, China
Liaoning Key Laboratory of Welding and Reliability of Rail Transportation Equipment, Dalian Jiaotong University, Dalian 116028, China
Funding
National Natural Science Foundation of China · Foundation for Overseas Talents Training Project in Liaoning Colleges and Universities · Foundation Scientific Research Project in Liaoning Provincial Education Department
References (28)
Show source-provided references
1. Research progress of aluminum alloy welding technology10.1007/s00170-020-05606-1 ↗
2. Zhou, B., Liu, B., and Zhang, S. (2021). The advancement of 7xxx series aluminum alloys for aircraft structures: A review. Metals, 11.10.3390/met11050718 ↗
3. Cold metal transfer (CMT) technology—An overview10.1016/j.dt.2017.08.002 ↗
4. The CMT short-circuiting metal transfer process and its use in thin aluminium sheets welding10.1016/j.matdes.2008.07.015 ↗
5. Microstructures and properties of titanium—Copper lap welded joints by cold metal transfer technology10.1016/j.matdes.2013.06.030 ↗
6. Effect of cooling and CMT mode process on additive manufacturing10.1080/10426914.2021.2006221 ↗
7. Properties and optimization of dissimilar aluminum steel CMT welds10.1007/s40194-016-0386-9 ↗
8. CMT Welding of Low Carbon Steel Thin Sheets10.1088/1757-899X/209/1/012051 ↗
9. Kołodziejczak, P., Bober, M., and Chmielewski, T. (2022). Wear Resistance Comparison Research of High-Alloy Protective Coatings for Power Industry Prepared by Means of CMT Cladding. Appl. Sci., 12.10.3390/app12094568 ↗
10. Welding penetration monitoring for pulsed GTAW using visual sensor based on AAM and random forests10.1016/j.jmapro.2020.04.005 ↗
11. Control of 3D weld pool surface10.1016/j.conengprac.2013.06.019 ↗
12. Recognition of penetration state in GTAW based on vision transformer using weld pool image10.1007/s00170-021-08538-6 ↗
13. Audio sensing and modeling of arc dynamic characteristic during pulsed Al alloy GTAW process
14. Automated control of welding penetration based on audio sensing technology10.1016/j.jmatprotec.2017.07.005 ↗
15. Weld bead penetration identification based on human-welder subjective assessment on welding arc sound10.1016/j.measurement.2020.107475 ↗
16. A Novel Convolutional Neural Network Based on Time-Frequency Spectrogram of Arc Sound and Its Application on GTAW Penetration Classification10.1109/TII.2020.2978114 ↗
17. Analysis of the frequency features of arc voltage and its application to the recognition of welding penetration in K-TIG welding10.1016/j.jmapro.2019.09.002 ↗
18. Weld penetration sensing in pulsed gas tungsten arc welding based on arc voltage10.1016/j.jmatprotec.2015.09.034 ↗
19. Weld bead penetration state recognition in GMAW process based on a central auditory perception model10.1016/j.measurement.2019.106901 ↗
20. Penetration state identification of lap joints in gas tungsten arc welding process based on two channel arc sounds10.1016/j.jmatprotec.2020.116762 ↗
21. Quality analysis of CMT lap welding based on welding electronic parameters and welding sound10.1016/j.jmapro.2021.11.055 ↗
22. Tran, N.-H., Bui, V.-H., and Hoang, V.-T. (2023). Development of an Artificial Intelligence-Based System for Predicting Weld Bead Geometry. Appl. Sci., 13.10.3390/app13074232 ↗
23. Machine Learning Approach for the Prediction of Defect Characteristics in Wire Arc Additive Manufacturing10.1007/s12666-022-02715-1 ↗
24. Recognition of penetration states based on arc sound of interest using VGG-SE network during pulsed GTAW process10.1016/j.jmapro.2022.12.034 ↗
25. Area-Efficient Short-Time Fourier Transform Processor for Time–Frequency Analysis of Non-Stationary Signals10.3390/app10207208 ↗
26. A review of convolutional neural network architectures and their optimizations10.1007/s10462-022-10213-5 ↗
27. A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects10.1109/TNNLS.2021.3084827 ↗
28. Arc characteristics and metal transfer behavior of CMT + P welding process10.1016/j.jmatprotec.2016.07.033 ↗