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

The weld quality depends on many factors and parameters such as continuity of the weld, the weld penetration and the absence of defects in the weld. All these parameters have to be after the welding process (Off-line) examined. 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 using acoustic parameters as input and Weld quality parameter as output in an artificial neural network. For this purpose, acoustic parameters welding process (The difference between the maximum and average sound intensity, The Average of Fast Fourier Transform – FFT coefficients and Standard deviation of FFT coefficients) as inputs and weld quality parameter (the percentage of weld quality) that is given b y non-destructive testing and welding inspection, is considered as an output. The selection process for this study is The gas-shielded welding process (MIG), One of the most commonly used types of welding. Acoustic signals is recorded in the laboratory during the welding process. Acoustic parameters of the process is extracted by the signal processing. Weld quality parameter, also b y Welding Inspection and Testing the quality of welded joints is determined. Finally, The relationship between acoustic parameters and weld quality parameter can be studied with the help of neural network modeling. After data analysis and prediction models, the results are presented.