Method for selecting best imaging waveband of molten pool vision based on spectral analysis

Abstract

The invention discloses a method for selecting a best imaging waveband of molten pool vision based on spectral analysis. The method includes the following steps: (1) according to the spectral responseof a camera, simulating the response intensity of the camera at different wavelengths under different blackbody temperatures to obtain a camera spectrogram and normalize the camera spectrogram; collecting a molten pool self-radiation spectrogram in the welding process by a spectrometer, and normalizing the corresponding intensity of the collected molten pool self-radiation spectrogram; (2) makinga difference between the relative intensity of the normalized molten pool self-radiation spectrogram at different wavelengths and the relative intensity of the normalized camera spectrogram to obtaina difference value; (3) selecting a waveband with a difference value greater than or equal to 0.4 as the best imaging waveband for molten pool vision. According to the method for selecting the best imaging waveband of the molten pool vision based on spectral analysis, arc light in the bast imaging waveband of the molten pool vision is weaker, the camera spectral response is stronger, and the imaging waveband is wider, so that the radiation amount of the molten pool can be effectively improved.

Description

technical field [0001] The invention belongs to the field of molten pool vision, and relates to a method for selecting the best imaging band for molten pool vision based on spectral analysis. Background technique [0002] Welding is an important processing technology in the manufacturing industry. With the continuous development of modern technology, the traditional method of observing the quality of the weld after welding can no longer meet the needs of the manufacturing industry. Real-time intelligent monitoring of welding is becoming more and more important, and has become the focus of people's research. The welding state of the molten pool can be understood through visual information, acoustic information, electrical information, etc., and the molten pool vision has become the main research direction of welding quality monitoring because it contains a lot of information. The collection of molten pool images is the basis of molten pool visual processing. [0003] The mo...

AI Technical Summary

Problems solved by technology

The study shows that the selection of the filter band will seriously affect the imaging quality of the molten pool

However, the selection of the filter band is more based on the summary of the experimental results, and no systematic and scientific theoretical analysis is given.

The visual band selection methods proposed by different researchers are quite different, and there is no theoretical unity; there is no optimal melting pool imaging band selection method for different processes and materials

Images