Machine learning model to predict welding quality using air-coupled acoustic emission and weld inputs

Weld evaluation processes are usually conducted in the post-weld stage. In this way, defects are found after the weld is completed, often resulting in disposal of expensive material or lengthy repair processes. Simultaneously, weld quality inspections tend to be performed manually by a human, even for an automated weld. Therefore, a proper real-time weld quality monitoring method associated with a decision-making strategy is needed to increase the productivity and automaticity in weld. In this study, acoustic emission (AE) as a real-time monitoring method is introduced for gas metal arc weld. The AE system is designed to cover a wide range of frequencies from 5 to 400 kHz. Additionally, the welding parameters (weld current, voltage, gas flow rate, and heat input) are recorded concurrently with AE. Different types of weld defects are artificially created to generate different signals. For the automated decision-making system, machine learning algorithms are used. Several features extracted from the AE and welding parameters feed into a machine learning algorithm. A new AE feature as the rate of AE energy accumulation extracted from time driven AE feature is defined. For decision-making, supervised learning models are trained and evaluated using testing data. General classification methods—such as Logistic Regression—predict each data-point separately. In this study, Adversarial Sequence Tagging method is applied to predict the presence of four weld states as good, excessive penetration, burn-through, porosity and porosity-excessive penetration. We explore the prediction task as a sequence tagging problem where the label of a data-point depends on its corresponding features as well as neighboring labels. When all the AE features as well as heat input are used in the feature set, the sequence tagging and logistic regression algorithms achieve a prediction accuracy of 91.18% and 82.35%, respectively, as compared to metallographic analysis.

[1]  Minghong Lin,et al.  Stochastic analysis of file-swarming systems , 2007, Perform. Evaluation.

[2]  Lu Zhang,et al.  Real-time monitoring of welding process using air-coupled ultrasonics and acoustic emission , 2018, The International Journal of Advanced Manufacturing Technology.

[3]  Laurence J. Jacobs,et al.  Evaluation of the heat-affected zone (HAZ) of a weld joint using nonlinear Rayleigh waves , 2017 .

[4]  Yue Cao,et al.  Control of weld penetration depth using relative fluctuation coefficient as feedback , 2020, J. Intell. Manuf..

[5]  Daniela M. Witten,et al.  An Introduction to Statistical Learning: with Applications in R , 2013 .

[6]  Norman McPherson,et al.  Visualisation and optimisation of shielding gas coverage during gas metal arc welding , 2018 .

[7]  P. Rose,et al.  Automatic recognition of weld defects in x-ray inspection , 1992 .

[8]  K. Rameshkumar,et al.  Use of Machine Learning Algorithms for Weld Quality Monitoring using Acoustic Signature , 2015 .

[9]  Yutaka S. Sato,et al.  Effect of micro-texture on fracture location in friction stir weld of Mg alloy AZ61 during tensile test , 2003 .

[10]  Binoy B. Nair,et al.  Acoustic Signature Based Weld Quality Monitoring for SMAW Process Using Data Mining Algorithms , 2015 .

[11]  Lorella Ceschini,et al.  Effect of friction stir welding on microstructure, tensile and fatigue properties of the AA7005/10 vol.%Al2O3p composite , 2007 .

[12]  M. F. Ghazali,et al.  Porosity detection by analyzing arc sound signal acquired during the welding process of gas pipeline steel , 2017 .

[13]  Baldev Raj,et al.  Image Processing Algorithm for Quantitative Characterization of Thermal Imaging acquired during On-line Weld Monitoring , 2007 .

[14]  Yanling Xu,et al.  Automated control of welding penetration based on audio sensing technology , 2017 .

[15]  Boris I Kapranov,et al.  Remote Acoustic Emission Monitoring of Metal Ware and Welded Joints , 2017 .

[16]  Hongping Gu,et al.  Resonant acoustic emission during laser welding of metals , 1996 .

[17]  Lin Li,et al.  A Comparative Study of Ultrasound Emission Characteristics in Laser Processing , 2002 .

[18]  Vikas Kumar,et al.  Evaluation of welding skill using probability density distributions and neural network analysis , 2018 .

[19]  Lu Yang,et al.  Weld defect classification in radiographic images using unified deep neural network with multi-level features , 2020, Journal of Intelligent Manufacturing.

[20]  T. Jayakumar,et al.  Intelligent modeling for estimating weld bead width and depth of penetration from infra-red thermal images of the weld pool , 2015, J. Intell. Manuf..

[21]  Hong Wang,et al.  Adversarial Sequence Tagging , 2016, IJCAI.

[22]  Krishnan Balasubramaniam,et al.  Automatic defect identification using thermal image analysis for online weld quality monitoring , 2012 .

[23]  Dong Chen,et al.  Effect of shielding gas on the plasma plume in pulsed laser welding , 2019, Measurement.

[24]  Y. S. Tarng,et al.  Intelligent modelling and optimization of the gas tungsten arc welding process , 1999, J. Intell. Manuf..

[25]  Yanling Xu,et al.  Online defect detection of Al alloy in arc welding based on feature extraction of arc spectroscopy signal , 2015 .

[26]  Lu Zhang,et al.  Real-time nondestructive monitoring of the gas tungsten arc welding (GTAW) process by combined airborne acoustic emission and non-contact ultrasonics , 2018, Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[27]  Dave F. Farson,et al.  Generation of optical and acoustic emissions in laser weld plumes , 1999 .

[28]  Steven Delrue,et al.  Applying a nonlinear, pitch-catch, ultrasonic technique for the detection of kissing bonds in friction stir welds. , 2016, Ultrasonics.

[29]  S. Chokkalingham,et al.  Predicting the depth of penetration and weld bead width from the infra red thermal image of the weld pool using artificial neural network modeling , 2012, J. Intell. Manuf..

[30]  Kyoung-Yun Kim,et al.  Data-driven Weld Nugget Width Prediction with Decision Tree Algorithm , 2017 .