A method for detecting defects in a formed metal part includes locating one or more regions of interest in a synthetic image of a part manufactured by a forming process. The synthetic image is informed based on a physics-based simulation of the forming process. The regions of interest indicate a high risk of having a defect from the forming process. A set of training images including real images of actual manufactured parts are registered with the synthetic image. The regions of interest are overlaid on each training image, to extract patches from the training images that correspond to high-risk regions. An anomaly detection model is trained on the patches extracted from the training images to detect a defect in a formed metal part from an acquired image of the formed metal part, by detecting an anomaly in a patch extracted from the acquired image that corresponds to a high-risk region.

A digital twin modeling method to assemble a robotic teleoperation environment, including: capturing images of the teleoperation environment; identifying a part being assembled; querying the assembly assembling order to obtain a list of assembled parts according to the part being assembled; generating a three-dimensional model of the current assembly from the list and calculating position pose information of the current assembly in an image acquisition device coordinate system; loading a three-dimensional model of the robot, determining a coordinate transformation relationship between a robot coordinate system and an image acquisition device coordinate system; determining position pose information of the robot in an image acquisition device coordinate system from the coordinate transformation relationship; determining a relative positional relationship between the current assembly and the robot from position pose information of the current assembly and the robot in an image acquisition device coordinate system; establishing a digital twin model of the teleoperation environment.

The invention relates to the field of operating, monitoring and controlling mills of the mining industry. It specifically relates to a system and a method for in-line determination of the characteristics of worn balls and pieces thereof, which have been ejected from a semi-autogenous mineral grinding (SAG) mill to the external classifiers.

This invention provides an easy-to-manufacture, easy-to-analyze calibration object which combines measurable and repeatable, but not necessarily accurate, 3D features—such as a two-sided calibration object/target in (e.g.) the form of a frustum, with a pair of accurate and measurable features, more particularly parallel faces separated by a precise specified thickness, so as to provide for simple field calibration of opposite-facing DS sensors. Illustratively, a composite calibration object can be constructed, which includes the two-sided frustum that has been sandblasted and anodized (to provide measurable, repeatable features), with a flange whose above/below parallel surfaces have been ground to a precise specified thickness. The 3D corner positions of the two-sided frustum are used to calibrate the two sensors in X and Y, but cannot establish absolute Z without accurate information about the thickness of the two-sided frustum; the flange provides the absolute Z information.

A method for checking samples for defects is provided, in which image data of the samples are recorded and classified into predeterminable defect categories by a defect detection algorithm, and the samples classified into a defect category are represented in a multi-dimensional confusion matrix as a classification result of the defect detection algorithm, characterized in that—miniature images which reproduce the image data are assigned according to the classified defect categories of the image data to segments of the confusion matrix which represent the defect categories, and these miniature images are displayed visually, —the miniature image is assigned by an interaction with a user or a software robot to a different segment from the assigned segment of the confusion matrix, and is either provided as training image data for the defect detection algorithm or is output as training image data for the defect detection algorithm.

An anomaly detector uses two neural networks, the first, a general purpose classifying convolutional neural network operates as a teacher neural network, while a second neural network in an auto-encoder type configuration. Each of the two neural networks receives the same input stream, and generates respective feature outputs at different levels, corresponding to different resolutions for image data. The respective outputs of the two neural networks are compared at each level, and the resulting difference values consolidated across the difference levels to obtain a final difference value. In a training phase this difference value is used to drive the determination of the weights and biases of the auto-encoder, so as to obtain a auto-encoder trained for a particular input type, under the influence of the teacher neural network. In an operational mode, the difference value is compared to a threshold to determine whether a particular sample is anomalous or not. In certain embodiments, difference values a different levels may be scaled so as to be superimposed at a common resolution, thereby providing an error map indicating the location of anomalous values across the sample.

The disclosure provides a structure diagnosis system and a structure diagnosis method. The structure diagnosis system includes: a lidar scanner scanning a structure to generate a point cloud data; an input interface receiving the point cloud data; and a processor receiving the point cloud data and generating a point cloud data set. The processor executes a surface degradation and geometry abnormal coupling diagnosis module to: marking a first point cloud range of a surface degradation area according to color space value of the point cloud data set; marking a second point cloud range of a geometry abnormal area according to coordinate value of the point cloud data set; when an abnormal area includes the first point cloud range and the second point cloud range at least partially overlapping each other, determining surface degradation or geometry abnormal occurring at the abnormal area and mark the abnormal area with a predetermined mode.

This invention relates to a method for training a neural network, comprising detecting a hole in each training image of a plurality of training images; transforming each training image into a transformed image, to suppress non-crack information in the training image; and training a neural network using the transformed images, to detect cracks in images (i.e. in objects in images).

The present disclosure provides an information processing method for performing the following steps, and the resulting information includes captured image data including at least the robot arm every predetermined period: a step of causing a captured image data acquisition unit to acquire captured image data of an imaging target at least including a robot arm and a control object; a step of causing a control unit to change a state of the control object every predetermined period based on user setting; an image comparison step of causing an image comparison unit to compare the captured image data with reference image data; and a step of causing a result information acquisition unit to detect a predetermined state change based on a result of the comparison in the image comparison step, acquire result information regarding a work of the robot arm, and store the result information in a result information storage unit.

Provided is image processing unit that causes computer to perform: a spatter candidate region detection step of performing, for each of input images obtained by capturing workpiece during arc welding, detection of a spatter candidate region based on a pixel value indicating brightness of a pixel included in the input images; a reflected light region identification step of identifying, in the spatter candidate region detected in the spatter candidate region detection step, a reflected light region in which reflected light of arc light is shown, based on color information of a reference pixel included in the spatter candidate region; and a spatter number identification step of identifying, as the number of spatters, the number of spatter candidate regions obtained by removing the reflected light region identified in the reflected light region identification step in the spatter candidate region detected in the spatter candidate region detection step.