摘要
In manual welding process, skilled welders can adjust the welding parameters to ensure the weld quality through their observation of the weld pool surface. In order to acquire useful information of the weld pool for control of the welding process and realizing the automatic welding, the measurement system of DB-GMA W process was established and the weld pool image was obtained by passive vision. Then, three image processing algorithms, Sobel, Canny, and pulse coupled neural network （PCNN） were detailed and applied to extracting the edge of the DB-GMA weld pool. In addition, a scheme was proposed for calculating the length, maximum width and superficial area of the weld pool under different welding conditions. The compared results show that the PCNN algorithm can be used for extracting the edge of the weld pool and the obtained information is more useful and accurate. The calculated results coincide with the actual measurement well, which demonstrates that the proposed algorithm is effective, its imaging processing time is required only 20 ms, which can completely meet the requirement of real-time control.
In manual welding process, skilled welders can adjust the welding parameters to ensure the weld quality through their observation of the weld pool surface. In order to acquire useful information of the weld pool for control of the welding process and realizing the automatic welding, the measurement system of DB-GMA W process was established and the weld pool image was obtained by passive vision. Then, three image processing algorithms, Sobel, Canny, and pulse coupled neural network （PCNN） were detailed and applied to extracting the edge of the DB-GMA weld pool. In addition, a scheme was proposed for calculating the length, maximum width and superficial area of the weld pool under different welding conditions. The compared results show that the PCNN algorithm can be used for extracting the edge of the weld pool and the obtained information is more useful and accurate. The calculated results coincide with the actual measurement well, which demonstrates that the proposed algorithm is effective, its imaging processing time is required only 20 ms, which can completely meet the requirement of real-time control.
基金
This work is supported by the National Natural Science Foundation of China under Grant No. 61365011.
