Finite element analysis coupled artificial neural network approach to design the longitudinal-torsional mode ultrasonic welding horn

The longitudinal-torsional mode horn has gained popularity recently for ultrasonic welding (USW) because it is more efficient than a conventional longitudinal horn. Addition of slanting grooves to the front mass to achieve torsionality is not a novel approach, and few works have already addressed this issue, but comparative studies about the effect of different groove parameters such as length, depth, angle, width, and distance upon the torsionality and resonance frequency are very rare. In the present work, only one parameter was varied at a time while others were kept constant to see their effect on horn attributes, i.e., torsionality and resonance frequency. The torsionality was maximized while keeping the value of resonance frequency as close to working frequency (i.e., 20 kHz) as possible. Depth is considered to be the most important parameter since its effect on torsionality was higher than the other four parameters. Multi-layer perceptron neural network was trained using the input features (i.e., groove parameters) which has the potential of transfer learning and would ease the process of finding the optimum parameters for torsionality maximization in later projects.

[1]  Dawei Zhao,et al.  A comparison of two types of neural network for weld quality prediction in small scale resistance spot welding , 2017 .

[2]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[3]  Jiromaru Tsujino,et al.  Recent developments of ultrasonic welding , 1995, 1995 IEEE Ultrasonics Symposium. Proceedings. An International Symposium.

[4]  Lin Shuyu.  Study on the longitudinal-torsional composite transducer with slanting slots , 1999 .

[5]  Hong Hocheng,et al.  On-line tool wear monitoring during ultrasonic machining using tool resonance frequency , 2002 .

[6]  R Rudramoorthy,et al.  Computational modeling and experimental studies of the dynamic performance of ultrasonic horn profiles used in plastic welding. , 2013, Ultrasonics.

[7]  Tianqi Chen,et al.  Empirical Evaluation of Rectified Activations in Convolutional Network , 2015, ArXiv.

[8]  Seyed Sajad Mirjavadi,et al.  Fracture Analysis of a Special Cracked Lap Shear (CLS) Specimen with Utilization of Virtual Crack Closure Technique (VCCT) by Finite Element Methods , 2017, Journal of Failure Analysis and Prevention.

[9]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[10]  Hassan Al-Budairi,et al.  Design and analysis of ultrasonic horns operating in longitudinal and torsional vibration , 2012 .

[11]  Tao Xie,et al.  Design and Fabrication of a Skew-Typed Longitudinal-Torsional Composite Ultrasonic Vibrator for Titanium Wire Drawing , 2016, IEEE Access.

[12]  Reimund Neugebauer,et al.  Ultrasonic application in drilling , 2004 .

[13]  K. Cheng,et al.  Innovative design and analysis of a longitudinal-torsional transducer with the shared node plane applied for ultrasonic assisted milling , 2018, Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science.

[14]  Dawei Zhao,et al.  Weld quality monitoring research in small scale resistance spot welding by dynamic resistance and neural network , 2017 .

[15]  Patrick Harkness,et al.  A design approach for longitudinal–torsional ultrasonic transducers , 2013 .

[16]  Shuyu Lin.  Study on the longitudinal-torsional composite mode exponential ultrasonic horns , 1996 .

[17]  Jiromaru Tsujino,et al.  New methods of ultrasonic welding of metal and plastic materials , 1996 .

[18]  Farid Vakili-Tahami,et al.  Controlling the in-service welding parameters for T-shape steel pipes using neural network , 2019, International Journal of Pressure Vessels and Piping.

[19]  Margaret Lucas,et al.  Optimisation of the longitudinal-torsional output of a half-wavelength Langevin transducer , 2012 .

[20]  T. Jun,et al.  Effect of process parameters on the joint strength in ultrasonic welding of Cu and Ni foils , 2019, Materials and Manufacturing Processes.

[21]  Guangrui Wen,et al.  Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding , 2019, Journal of Manufacturing Processes.

[22]  Xiaobiao Shan,et al.  A new piezoelectric ceramic longitudinal–torsional composite ultrasonic vibrator for wire drawing , 2015 .

[23]  Ping Guo,et al.  Feasibility Study of Longitudinal–Torsional-Coupled Rotary Ultrasonic Machining of Brittle Material , 2018 .

[24]  Stewart Sherrit,et al.  Ultrasonic/sonic sampler and sensor platform for in-situ planetary exploration , 2003, Proceedings International Conference on MEMS, NANO and Smart Systems.

[25]  Margaret Lucas,et al.  Coupling and degenerating modes in longitudinal-torsional step horns. , 2012, Ultrasonics.

[26]  Margaret Lucas,et al.  A Strategy for Delivering High Torsionality in Longitudinal-Torsional Ultrasonic Devices , 2011 .

[27]  Seyed Sajad Mirjavadi,et al.  Investigation of Mesh Sensitivity Influence to Determine Crack Characteristic by Finite Element Methods , 2016, Journal of Failure Analysis and Prevention.

[28]  Ljn Shuyu,et al.  Sandwiched Piezloelectric Ultrasonic Transducers of Longit udinal-Torsional Compound Vibrational Modes , 1997 .

[29]  Saeid Amini,et al.  Effect of longitudinal−torsional vibration in ultrasonic-assisted drilling , 2017 .

[30]  Aurélien Géron,et al.  Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems , 2017 .

[31]  J. G. Lewis,et al.  A Shifted Block Lanczos Algorithm for Solving Sparse Symmetric Generalized Eigenproblems , 1994, SIAM J. Matrix Anal. Appl..

[32]  Dewang Zhao,et al.  Effect of welding parameters on tensile strength of ultrasonic spot welded joints of aluminum to steel – By experimentation and artificial neural network , 2017 .