Method and apparatus for automatically generating welding procedure specification using machine learning algorithms

A non-transitory computer-readable recording medium having stored therein a computer program for executing, by using a computer, a method comprising:

• collecting a WPS transmission request signal together with welding-related information comprising a welding material for a welding target and a thickness of the welding material;
• generating a WPS corresponding to the welding-related information by using a machine learning model pre-trained to generate the WPS by using the welding-related information;
• and
• transmitting a WPS response signal together with the generated WPS, in response to the WPS transmission request signal,
• wherein the machine learning model is a model trained through supervised learning using training data in which the welding-related information is an input and the WPS corresponding to the welding-related information is a label,
• wherein the WPS comprises a preliminary WPS before completion, and
• the method further comprises, before the transmitting of the WPS response signal, transmitting the preliminary WPS to one or more of a supervisor terminal possessed by a first supervisor, a supervisor terminal possessed by a second supervisor, and a welding device, and
• where the method further comprises:
• receiving welding result monitoring information for the welding device, generated based on the preliminary WPS, from the supervisor terminal possessed by the first supervisor;
• receiving inspection result information for the preliminary WPS, generated based on the welding result monitoring information, from the supervisor terminal possessed by the second supervisor;
• and
• determining approval or disapproval of the preliminary WPS as a completed WPS, based on the inspection result information for the preliminary WPS.

An apparatus for automatically generating a welding procedure specification (WPS) by using a machine learning algorithm, the apparatus comprising:

• a processor;
• and
• a memory operatively connected to the processor and storing at least one code performed by the processor,
• wherein the memory stores codes that cause, when executed through the processor, the processor to:
• collect a WPS transmission request signal together with welding-related information comprising a welding material for a welding target and a thickness of the welding material;
• generate a WPS corresponding to the welding-related information by using a machine learning model pre-trained to generate the WPS by using the welding-related information;
• and
• transmit a WPS response signal together with the generated WPS, in response to the WPS transmission request signal,
• wherein the machine learning model is a model trained through supervised learning using training data in which the welding-related information is an input and the WPS corresponding to the welding-related information is a label,
• wherein the memory further stores codes that cause the processor to, when the WPS comprises a preliminary WPS before completion, transmit the preliminary WPS to one or more of a supervisor terminal possessed by a first supervisor, a supervisor terminal possessed by a second supervisor, and a welding device, before transmitting the WPS response signal, and
• wherein the memory further stores codes that cause the processor to:
• receive welding result monitoring information for the welding device, generated based on the preliminary WPS, from the supervisor terminal possessed by the first supervisor;
• receive inspection result information for the preliminary WPS, generated based on the welding result monitoring information, from the supervisor terminal possessed by the second supervisor;
• and
• determine approval or disapproval of the preliminary WPS as a completed WPS, based on the inspection result information for the preliminary WPS.