The present disclosure relates to a metal machining apparatus having a gas nozzle for generating a gas jet. The apparatus also has a nozzle exit opening on one end on the outside; an electronic camera for acquiring a digital image of the end of the gas nozzle with the nozzle exit opening. The apparatus also includes a pattern recognition module for mapping the digital image to at least one nozzle pattern from the group of nozzle state and/or nozzle type.

A laser repair method includes a repair process of performing repair work by setting a laser radiation range for a defect part in a multi-layer film substrate and irradiating the defect part with a laser beam under set laser working conditions. In the repair process, spectrum data of the defect part is acquired, and the laser working conditions of the laser beam, with which the defect part is to be irradiated, are set using a neural network after learning on the basis of the spectrum data, and the neural network has undergone machine learning using, as learning data, measurement data including multi-layer film structure data, spectrum data of each multi-layer film structure, and laser working experimental data of each multi-layer film structure.

A laser machining system according to the present invention includes a laser machining tool, a detection unit that detects a machining state of the laser machining tool, a test machining condition generation unit that generates a machining condition including at least one control parameter settable to the laser machining tool, a machining determination unit that determines quality of machining based on the machining state detected by the detection unit, a candidate condition generation unit that generates a candidate condition, which is a candidate for a machining condition to be set to the laser machining tool, based on a determination result from the machining determination unit and on a machining condition corresponding to the determination result, and a tolerance check unit that causes check machining to be performed for checking a machining tolerance using the candidate condition, where the machining tolerance indicates robustness of the candidate condition.

Systems and methods for part tracking using machine learning techniques are described. In some examples a part tracking system analyzes feature characteristics related to one or more welds to identify, determine characteristics of, and/or label one or more parts repeatedly assembled by the welds. Identifying parts assembled from the welds may make it possible to do part based analytics (e.g., related to part quality, cost, production efficiency, etc.), as opposed to just weld based analytics, on past welding data. Additionally, identifying a part assembled from several welds results in an ordering of those several welds used to create the part, which can make it easier to compare/contrast similar welds across parts. Further, determining the characteristics of the parts can assist in configuring certain part tracking systems, thereby reducing the expertise, time, and personnel required.

A brazing work assistance method includes: displaying (i) a first reference range indicating a range between an upper value and a lower value obtained from a first temperature waveform that is a model temperature waveform of a brazing portion in the brazing work, and (ii) a measured waveform that is a temperature waveform of the brazing portion brazed during the brazing work conducted by the worker; and displaying a second reference range according to the measured waveform when the measured waveform falls outside the first reference range. The second reference range indicates a range between an upper value and a lower value obtained from a second temperature waveform and is different from the first reference range. The second temperature waveform is a model temperature waveform of the brazing portion in the brazing work, is different from the first temperature waveform.

A welding bead modeling method for wire-arc additive manufacturing, a device therefor and a system therefor including using a dynamic parameter method, and using different welding process parameters in the same welding bead in the a wire-arc additive manufacturing process to obtain a welding bead with synchronous and dynamic changes in profile along with the dynamic changes of the welding process parameters. The method further comprising using a line laser sensor for scanning to obtain the segmented profile of the processed welding bead, and corresponding each welding bead profile to the welding process parameters one by one to train the neural network as training data, so as to obtain a welding bead modeling model capable of obtaining the corresponding welding bead profile according to the input welding process parameters.

A machine learning device that performs machine learning of a welding condition for manufacturing an additively-manufactured object by welding a filler metal and depositing weld beads, the machine learning device includes: at least one hardware processor configured to perform a learning process for generating a learned model using two pieces of shape data of a weld bead or a difference between the two pieces of shape data is used as input data and a difference between welding conditions corresponding to the difference between the two pieces of shape data as output data.

Systems and methods are provided herein useful to analyzing weld quality. In some embodiments, the systems and methods identify or predict weld characteristics such as surface discontinuities and/or subsurface discontinuities based on surface topology data and/or welding process parameters. The systems and methods described herein leverage machine learning algorithms to identify relationships between historic weld characteristics and historic pre-weld surface topology, historic post-weld surface topology, and/or historic welding process parameters. Thus, the systems and methods described herein may identify weld characteristics for a weld based on the relationships and the pre-weld surface topology, post-weld surface topology, and/or welding process parameters for the weld. Further, the systems and methods described herein may also identify weld as conforming or not conforming to one or more weld standards based on the relationships and the pre-weld surface topology, post-weld surface topology, and/or welding process parameters for the weld.

A welding control device configured to control a position control object which includes at least one of a welding wire used to weld a welding object or an electrode for melting the welding wire includes a first decision unit for deciding an actual position of the position control object based on a welding feature amount detected from an image which is shot to include at least the position control object, a second decision unit for deciding a target position which is a target of the actual position according to an input condition based on the input condition which includes at least one of attitude information of the electrode when the welding object is welded or shape information of the welding object, and a control unit for performing position control of the position control object so that the actual position becomes the target position.

A method for processing a chip based on deep learning and an apparatus for processing a chip based on deep learning are provided. The method includes scanning the chip with femtosecond laser in a predetermined polarization state to produce a main scanning trajectory and periodic nano-stripes on both sides of the main scanning trajectory, so as to form a nano-ridge structure on a surface of the chip; obtaining a super-resolution microscopic image of the nano-ridge structure by super-resolution microscopy; obtaining a target image; reconstructing the target image based on deep learning for image super-resolution to obtain the reconstructed image, and recognizing and processing the reconstructed image to obtain characteristic parameters of the nano-ridge structure as input parameters for deep learning for femtosecond laser processing; adjusting processing parameters of the chip according to the output values of the deep learning model for femtosecond laser processing; and outputting the optimized nano-ridge structure.