Applications of ultrasonic testing and machine learning methods to predict the static & fatigue behavior of spot-welded joints

Abstract Ultrasonic Testing (UT) is one of the well-known Non-Destructive Techniques (NDT) of spot-weld inspection in the advanced industries, especially in automotive industry. However, the relationship between the UT results and strength of the spot-welded joints subjected to various loading conditions is unknown. The main purpose of this research is to present an integrated search system as a new approach for assessment of tensile strength and fatigue behavior of the spot-welded joints. To this end, Resistance Spot Weld (RSW) specimens of three-sheets were made of different types of low carbon steel. Afterward, the ultrasonic tests were carried out and the pulse-echo data of each sample were extracted utilizing Image Processing Technique (IPT). Several experiments (tensile and axial fatigue tests) were performed to study the mechanical properties of RSW joints of multiple sheets. The novel approach of the present research is to provide a new methodology for static strength and fatigue life assessment of three-sheets RSW joints based on the UT results by utilizing Artificial Neural Network (ANN) simulation. Next, Genetic Algorithm (GA) was used to optimize the structure of ANN. This approach helps to decrease the number of tests and the cost of performing destructive tests with appropriate reliability.

[1]  Md. Saiful Alam,et al.  Nondestructive Evaluation of Spot Weld in Stainless Steel Using Ultrasonic Immersion Method , 2014 .

[2]  Hu Zhang,et al.  Artificial neural network application to study quantitative relationship between silicide and fracture toughness of Nb-Si alloys , 2017 .

[3]  Siamak Serajzadeh,et al.  Simulation of welding residual stresses in resistance spot welding, FE modeling and X-ray verification , 2008 .

[4]  Feng Chen,et al.  Multi-performance optimization of small-scale resistance spot welding process parameters for joining of Ti-1Al-1Mn thin foils using hybrid approach , 2017 .

[5]  Dilip Kumar Pratihar,et al.  A combined neural network and genetic algorithm based approach for optimally designed femoral implant having improved primary stability , 2016, Appl. Soft Comput..

[6]  Bin Wang,et al.  Classification of spot‐welded joint strength using ultrasonic signal time‐frequency features and PSO‐SVM method , 2019, Ultrasonics.

[7]  Iradj Sattari-Far,et al.  Numerical and experimental study of nugget size growth in resistance spot welding of austenitic stainless steels , 2012 .

[8]  Huiqing Ouyang,et al.  Application of Neural Network Technology in Welding Procedure Qualification for Joint , 2018 .

[9]  W. Marsden.  I and J , 2012 .

[10]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[11]  YuMing Zhang,et al.  Iterative Local ANFIS-Based Human Welder Intelligence Modeling and Control in Pipe GTAW Process: A Data-Driven Approach , 2015, IEEE/ASME Transactions on Mechatronics.

[12]  Óscar Martín,et al.  Artificial neural networks for quality control by ultrasonic testing in resistance spot welding , 2007 .

[13]  Mohsen Eshraghi,et al.  A Parametric Study of Resistance Spot Welding of a Dual‐Phase Steel Using Finite Element Analysis , 2013 .

[14]  Dilip Kumar Pratihar,et al.  Modeling of TIG welding process using conventional regression analysis and neural network-based approaches , 2007 .

[15]  Mohsen Hamedi,et al.  New parametric study of nugget size in resistance spot welding process using finite element method , 2010 .

[16]  Jing Liu,et al.  Ultrasonic test of resistance spot welds based on wavelet package analysis. , 2015, Ultrasonics.

[17]  Li Han,et al.  Progress in NDT of resistance spot welding of aluminium using ultrasonic C-scan , 2012 .

[18]  Yaowu Shi,et al.  Ultrasonic nondestructive evaluation of spot welds for zinc-coated high strength steel sheet based on wavelet packet analysis , 2009 .

[19]  Jiju Antony,et al.  Application of design of experiments to a spot welding process , 2003 .

[20]  Janez Diaci,et al.  Expulsion detection system for resistance spot welding based on a neural network , 2004 .

[21]  J. Senkara,et al.  Suppressing Cracking in Resistance Welding AA5754 by Mechanical Means , 2002 .

[22]  G. H. Farrahi,et al.  Modelling of Conventional and Severe Shot Peening Influence on Properties of High Carbon Steel via Artificial Neural Network , 2017 .

[23]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[24]  Werner Roye Krautkrämer.  Ultrasonic Testing of Spot Welds in the Automotive Industry , 1999 .

[25]  M. Pouranvari,et al.  Critical review of automotive steels spot welding: process, structure and properties , 2013 .

[26]  J. Senkara,et al.  Cracking in spot welding aluminum alloy AA5754 , 2000 .

[27]  Y. Zhou,et al.  Microstructure and Mechanical Properties of Resistance Spot Welded Advanced High Strength Steels , 2008 .

[28]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[29]  Xiang Huang,et al.  Multi-objective optimization of mechanical quality and stability during micro resistance spot welding , 2018, The International Journal of Advanced Manufacturing Technology.

[31]  Yu-Kang Liu,et al.  Supervised Learning of Human Welder Behaviors for Intelligent Robotic Welding , 2017, IEEE Transactions on Automation Science and Engineering.

[32]  José Manuel Galán,et al.  Assessment of resistance spot welding quality based on ultrasonic testing and tree-based techniques , 2014 .

[33]  Hyo Sun Yu,et al.  A study on ultrasonic test for evaluation of spot weldability in automotive materials , 1999 .

[34]  G. Mozurkewich,et al.  Spatially resolved ultrasonic attenuation in resistance spot welds: implications for nondestructive testing. , 2008, Ultrasonics.

[35]  P. Velmurugan,et al.  Optimization of resistance spot welding process parameters and microstructural examination for dissimilar welding of AISI 316L austenitic stainless steel and 2205 duplex stainless steel , 2017 .

[36]  An,et al.  Modeling and prediction of weld strength in ultrasonic metal welding process using artificial neural network and multiple regression method , 2018 .