Convolutional Neural Network Prediction of Aluminum Alloy GTAW Penetration Process Based on Arc Sound Sensing

Aluminum alloy is a metal material that is widely used in industry. Gas Tungsten Arc Welding (GTAW) is a common welding method for aluminum alloy welding, which has advantages of good welding quality, strong adaptability, and wide welding range. GTAW is widely used in the field of precision welding. The welding process is a complex process of change. To obtain good welding quality, the welding process must be monitored in real time to find out the problems during the welding process. This paper uses industrial Internet of Things (IoT) to design a set of technical solutions, uploading various data collected during the welding process to the cloud for storage, and to remotely monitor the welding process in real time through a browser. At the same time, with the collected sound signals, establish a welding penetration state classification model to further mine the value of sound signal data based on convolutional neural networks.

[1]  Dimitri Palaz,et al.  Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks , 2013, INTERSPEECH.

[2]  Wang Guoqing,et al.  Research Progress of Bobbin Tool Friction Stir Welding of Aluminum Alloys: A Review , 2020 .

[3]  James R. Glass,et al.  Speech feature denoising and dereverberation via deep autoencoders for noisy reverberant speech recognition , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  D. Saini,et al.  An investigation of gas metal arc welding sound signature for on-line quality control , 1998 .

[5]  Joseph Tam.  Methods of Characterizing Gas-Metal Arc Welding Acoustics for Process Automation , 2005 .

[6]  Navdeep Jaitly,et al.  Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[7]  Zachary Chase Lipton.  A Critical Review of Recurrent Neural Networks for Sequence Learning , 2015, ArXiv.

[8]  J. Huissoon,et al.  Developing psycho-acoustic experiments in gas metal arc welding , 2005, IEEE International Conference Mechatronics and Automation, 2005.

[9]  Shanben Chen,et al.  On Intelligentized Welding Manufacturing , 2014 .

[10]  D. Lingaraju,et al.  Effect Of Different Edge Preparations On The Tensile And Hardness Properties Of Gtaw Welded 6082 Aluminum Alloy , 2017 .

[11]  Elijah Kannatey-Asibu,et al.  Sensor systems for real-time monitoring of laser weld quality , 1999 .

[12]  Bo-Young Lee,et al.  Research progress of aluminum alloy welding technology , 2020, The International Journal of Advanced Manufacturing Technology.

[13]  Bo Chen,et al.  A study on application of multi-sensor information fusion in pulsed GTAW , 2010, Ind. Robot.

[14]  A. P. Anaraki,et al.  Investigation of Heat Source Models and Process Factors on Temperature and Residual Stress in GTAW of Aluminum Plates , 2019, Russian Journal of Non-Ferrous Metals.

[15]  J. Grum,et al.  Feasibility study of acoustic signals for on-line monitoring in short circuit gas metal arc welding , 2004 .

[16]  Haichao Li,et al.  An intelligent weld control strategy based on reinforcement learning approach , 2019 .

[17]  Ron J. Weiss,et al.  Speech acoustic modeling from raw multichannel waveforms , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[18]  Yao Liu,et al.  Microstructure and mechanical properties of aluminum 5083 weldments by gas tungsten arc and gas metal arc welding , 2012 .