Evaluate and Control the weld quality, Using Acoustic data and Artificial Neural Network Modeling

Evaluate and Control the weld quality, Using Acoustic data and Artificial Neural Network Modeling

… Download …


Part of #Evaluate and Control the weld quality, Using Acoustic data and Artificial Neural Network Modeling# :

Publishing year : 2013

Conference : National Conference on Mechanical Engineering of Iran

Number of pages : 6

Abstract: The weld quality depends on many factors and parameters such as continuity of the weld, weld penetration and the absence of defects in the weld. All these parameters have been examined after the welding process (Off-line). Since Welding sound signal is an important feedback, In this research it is used as a (On-line) Criterion to determine the weld quality. The purpose of this investigation is to evaluate and control the weld quality by using acoustic parameters as a input and Weld quality parameter as output in an artificial neural network. For this purpose, the acoustic parameters welding process (the difference between the maximum and average sound intensity, the FFT coefficients and the standard deviation of the FFT coefficients) as inputs and the weld quality parameter (the weld quality ratio), which is Given by non-destructive testing and welding inspection, is considered as an output. The gas-shielded welding process (MIG), one of the most commonly used types of welding. The welding process is recorded in the laboratory by the laboratory. The acoustic parameters of the process are extracted by the signal processing. Weld quality parameter, also by Welding Inspection and Testing, the quality of welded joints is determined. Finally, the relationship between the acoustic parameters and the weld quality parameter can be studied with the help of neural network modeling. After data analysis and prediction models, the results are presented