The real-time detection of porosity in welding process is an important problem to be solved in intelligent welding manufacturing. A new on-line detection method for porosity of aluminum alloy in robotic arc welding based on arc spectrum is proposed in this paper. First, k-shape and the improved k-means were used for the initial feature selection of the preprocessed arc spectrum to reduce the data dimension. Second, the secondary feature selection was carried out based on the importance of features to further reduce feature redundancy. Then, the optimal sample label library was established by combining the final characteristic parameters and the X-ray pictures of welds. Finally, an on-line detection method of porosity in gas tungsten arc welding of aluminum alloy based on light gradient boosting machine (LightGBM) was proposed. Compared with extreme gradient boosting(XGBoost) and categorical boosting (CatBoost), this method can achieve better detection performance. The new method proposed in this paper can be used to detect other welding defects, which is helpful to the development of intelligent welding technology.
JIANG Haoqiang (蒋浩强), CHEN Shanben* (陈善本), XU Jingyuan (许靖远)
. On-Line Detection of Porosity in Gas Tungsten Arc Welding of Aluminum Alloy Based on Spectrum Features[J]. Journal of Shanghai Jiaotong University(Science), 2024
, 29(2)
: 339
-348
.
DOI: 10.1007/s12204-022-2495-5
[1] CHEN S B, LV N. Research evolution on intelligentized technologies for arc welding process [J]. Journal of Manufacturing Processes, 2014, 16(1): 109-122.
[2] RYAZANTSEV V I, FEDOSEEV V A. Metallurgical and technological porosity of aluminium alloys in arc welding [J]. Welding International, 2002, 16(4): 320-324.
[3] KUTSUNA M, YAN Q. Study on porosity formation in laser welds in aluminium alloys (Report 1): Effects of hydrogen and alloying elements [J]. Welding International, 1998, 12(12): 937-949.
[4] CHEN Q H, GE H L, YANG C L, et al. Study on pores in ultrasonic-assisted TIG weld of aluminum alloy [J]. Metals, 2017, 7(2): 53.
[5] XIAO R S, ZHANG X Y. Problems and issues in laser beam welding of aluminum-lithium alloys [J]. Journal of Manufacturing Processes, 2014, 16(2): 166-175.
[6] ALAKNANDA, ANAND R S, KUMAR P. Flaw detection in radiographic weld images using morphological approach [J]. NDT & E International, 2006, 39(1): 29-33.
[7] ZHANG Z F, CHEN H B, XU Y L, et al. Multisensorbased real-time quality monitoring by means of feature extraction, selection and modeling for Al alloy in arc welding [J]. Mechanical Systems and Signal Processing, 2015, 60/61: 151-165.
[8] MIRAPEIX J, RUIZ-LOMBERA R, VALDIANDE J J, et al. Defect detection with CCD-spectrometer and photodiode-based arc-welding monitoring systems [J]. Journal of Materials Processing Technology, 2011, 211(12): 2132-2139.
[9] LI Z Y, WANG B, DING J B. Detection of GTA welding quality and disturbance factors with spectral signal of arc light [J]. Journal of Materials Processing Technology, 2009, 209(10): 4867-4873.
[10] ZHAO Z, GUO Y T, BAI L F, et al. Quality monitoring in wire-arc additive manufacturing based on cooperative awareness of spectrum and vision [J]. Optik, 2019, 181: 351-360.
[11] YU H W, XU Y L, LV N, et al. Arc spectral processing technique with its application to wire feed monitoring in Al-Mg alloy pulsed gas tungsten arc welding [J]. Journal of Materials Processing Technology, 2013, 213(5): 707-716.
[12] YU H W, XU Y L, SONG J Q, et al. On-line monitor of hydrogen porosity based on arc spectral information in Al-Mg alloy pulsed gas tungsten arc welding [J]. Optics & Laser Technology, 2015, 70: 30-38.
[13] HUANG Y M, WU D, LV N, et al. Investigation of porosity in pulsed GTAW of aluminum alloys based on spectral and X-ray image analyses [J]. Journal of Materials Processing Technology, 2017, 243: 365-373.
[14] ZHANG Z F, YU H W, LV N, et al. Real-time defect detection in pulsed GTAW of Al alloys through online spectroscopy [J]. Journal of Materials Processing Technology, 2013, 213(7): 1146-1156.
[15] ZHANG Z F, YANG Z, REN W J, et al. Random forest-based real-time defect detection of Al alloy in robotic arc welding using optical spectrum [J]. Journal of Manufacturing Processes, 2019, 42: 51-59.
[16] SUN L X, YU H B. Automatic estimation of varying continuum background emission in laser-induced breakdown spectroscopy [J]. Spectrochimica Acta Part B: Atomic Spectroscopy, 2009, 64(3): 278-287.
[17] SUN X L, LIU M X, SIMA Z Q. A novel cryptocurrency price trend forecasting model based on LightGBM [J]. Finance Research Letters, 2020, 32: 101084.
[18] TANG M Z, ZHAO Q, DING S X, et al. An improved LightGBM algorithm for online fault detection of wind turbine gearboxes [J]. Energies, 2020, 13(4): 807.
[19] ZHANG Y Y, ZHU C F, WANG Q R. LightGBMbased model for metro passenger volume forecasting [J]. IET Intelligent Transport Systems, 2020, 14(13): 1815-1823.
[20] MA M H, ZHAO G, HE B S, et al. XGBoost-based method for flash flood risk assessment [J]. Journal of Hydrology, 2021, 598: 126382.
[21] CHEN K, CHEN H B, LIU L, et al. Prediction of weld bead geometry of MAG welding based on XGBoost algorithm [J]. International Journal of Advanced Manufacturing Technology, 2019, 101(9/10/11/12): 2283-2295.
[22] HUANG G M, WU L F, MA X, et al. Evaluation of CatBoost method for prediction of reference evapotranspiration in humid regions [J]. Journal of Hydrology, 2019, 574: 1029-1041.
[23] LEE S, VO T P, THAI H T, et al. Strength prediction of concrete-filled steel tubular columns using Categorical Gradient Boosting algorithm [J]. Engineering Structures, 2021, 238: 112109.
