Bead appearance inspection device, bead appearance inspection method, program, and bead appearance inspection system

A bead appearance inspection method executed by a bead appearance inspection device, the bead appearance inspection method comprising:

• an input step of inputting input data related to a welding bead of a workpiece produced by welding;
• a first determination step of using the input data and master data of a non-defective workpiece, and performing a first inspection determination related to a shape of the welding bead based on a comparison between the input data and the master data;
• k second determination steps, where k is an integer of 1 or more, of equipping k types of artificial intelligence, and performing a second inspection determination related to a welding defect of the welding bead based on processings of the k types of artificial intelligence targeting the input data;
• and
• an output step of outputting a result of an appearance inspection of the welding bead to an output device based on determination results of the first determination step and the k second determination steps,
• wherein the result of the appearance inspection of the welding bead is that the welding bead is defective when the determination result of the first determination step or the determination result of the k second determination steps is defective, and the result of the appearance inspection of the welding bead is that the welding bead is non-defective when the determination results of both the first determination step and the k second determination steps are non-defective,
• wherein an appearance inspection item related to the shape of the welding bead that is a target of the first inspection determination and an appearance inspection item related to the welding defect of the welding bead that is a target of the second inspection determination are different inspection items related to the welding of the workpiece,
• wherein the first determination step performs comparison judgement based on the input data as the first inspection determination and the k second determination steps perform artificial intelligence judgement based on the input data as the second inspection determination,
• wherein the appearance inspection item that is the target of the first inspection determination is an inspection item from a first group of inspection items,
• wherein the appearance inspection item that is the target of the second inspection determination is an inspection item from a second group of inspection items,
• wherein none of the inspection items in the first group of inspection items is in the second group of inspection items, and none of the inspection items in the second group of inspection items is in the first group of inspection items, and
• wherein the first inspection determination and the second inspection determination are performed on the same input data related to the same welding bead.

A bead appearance inspection system comprising:

• a memory configured to store master data of a non-defective workpiece;
• an input unit configured to enter input data related to a welding bead of a workpiece produced by welding;
• a first determination unit configured to use the input data and the master data of the non-defective workpiece, and to perform a first inspection determination related to a shape of the welding bead based on a comparison between the input data and the master data;
• k second determination units, where k is an integer of 1 or more, that are equipped with k types of artificial intelligence, and that are configured to perform a second inspection determination related to a welding defect of the welding bead based on processings of the k types of artificial intelligence targeting the input data;
• and
• a comprehensive determination unit configured to output a result of an appearance inspection of the welding bead to an output device based on determination results of the first determination unit and the k second determination units,
• wherein the result of the appearance inspection of the welding bead is that the welding bead is defective when the determination result of the first determination unit or the determination result of the k second determination units is defective, and the result of the appearance inspection of the welding bead is that the welding bead is non-defective when the determination results of both the first determination unit and the k second determination units are non-defective,
• wherein an appearance inspection item related to the shape of the welding bead that is a target of the first inspection determination and an appearance inspection item related to the welding defect of the welding bead that is a target of the second inspection determination are different inspection items related to the welding of the workpiece,
• wherein the first determination unit performs comparison judgement based on the input data as the first inspection determination and the k second determination units perform artificial intelligence judgement based on the input data as the second inspection determination,
• wherein the appearance inspection item that is the target of the first inspection determination is an inspection item from a first group of inspection items,
• wherein the appearance inspection item that is the target of the second inspection determination is an inspection item from a second group of inspection items,
• wherein none of the inspection items in the first group of inspection items is in the second group of inspection items, and none of the inspection items in the second group of inspection items is in the first group of inspection items, and
• wherein the first inspection determination and the second inspection determination are performed on the same input data related to the same welding bead.