Abstract: This welding system comprises: a welding device, various different types of a plurality of sensors which detect an event according to welding performed by a welding device; and an estimation unit which uses a trained model that is pre-generated by machine-learning by taking, as input data, a plurality of pieces of data for learning obtained by detecting events according to welding by means of the same types of sensors as the plurality of sensors, and, as training data, labels representing whether the welding is normal or abnormal, thereby estimating an abnormality of the welding performed by the welding device from a plurality of pieces of detection data generated by the plurality of sensors.

Abstract: This learning model generation method is for generating a learning model for learning by taking, as teaching data, image data from a visual sensor and welding information extracted from the image data, wherein: a plurality of welding conditions to be used for generating the learning model correspond to the difference in setting pertaining to at least one item; the image data corresponding to each of the plurality of welding conditions includes at least one of a molten pool, a welding wire, and an arc; the welding information includes at least one of information pertaining to the behavior of the molten pool, information pertaining to the position of the welding wire, and information pertaining to the arc; and the learning model which receives the image data as an input and outputs the welding information is generated.

Abstract: An automated welding system includes a camera for capturing a camera image of a molten pool and an arc generated in a groove by arc welding; an estimation unit for outputting a probability distribution image based on a camera image by using a learned model; an extraction unit for extracting a region having at least a predetermined probability from the probability distribution image; a selection unit for selecting a representative point corresponding to a feature point of an arc and a representative point corresponding to a feature point of a molten pool, in the region having at least the predetermined probability; and a correction unit for correcting a control parameter of a welding robot based on a positional relationship of the representative point corresponding to the feature point of the arc and the representative point corresponding to the feature point of the molten pool.

Abstract: An automatic welding system, an automatic welding method, a welding assistance device, and a program wherein the amount of correction of the welding speed is determined on the basis of the distance between an arc and the tip of a molten pool when the distance between the arc and the tip of the molten pool is within a predetermined range in arc welding performed while alternately weaving a welding torch in the front downward direction and the rear upward direction when the welding progress direction is the frontward direction with respect to a horizontally extending groove formed between two members to be welded aligned in the vertical direction.

Abstract: An object detection device (1) includes: a correction unit (41) that corrects, by using projective transformation, distortion of an image (Im) captured by a camera (2) capturing an image of a detection target object and mounted on a construction machine (100); and a processing unit (42) that sets, in the image (Im) after correction, a plurality of regions (R-1, R-2, and R-3) provided in accordance with a distance between the camera (2) and the object and each having a different area, and performs image processing of detecting the object with respect to a part of the image (Im) corresponding to each of the plurality of regions (R-1, R-2, and R-3).