An inspection system includes machine learning circuitry configured to determine whether each of objects belongs to a predetermined attribute based on feature data of each of the objects, feature data acquisition circuitry configured to acquire feature data of reevaluated objects which are determined to belong to the predetermined attribute without using the machine learning circuitry among excluded objects which are determined not to belong to the predetermined attribute by the machine learning circuitry, and parameter update circuitry configured to update a learning parameter of the machine learning circuitry based on teaching data including the acquired feature data acquired by the feature data acquisition circuitry.

A workpiece data processing method and apparatus are for accurately determining a relationship between production equipment processing parameters/ambient condition data and workpiece quality inspection results. A workpiece data method includes acquiring processing condition data, a quality attribute value and quality inspection result data of each of multiple workpieces processed by a piece of production equipment, the processing condition data of one workpiece including a processing parameter used by the production equipment when processing the workpiece and ambient condition data of the production equipment when processing the workpiece; determining a first relationship between the quality attribute value of the workpiece processed by the production equipment and the ambient condition data of the production equipment when processing the workpiece and the processing parameter of the production equipment; and determining a second relationship between the quality inspection result data and quality attribute value of the workpiece processed by the production equipment.

A method for configuring a semiconductor manufacturing process, the method including: providing an initial prediction model including a plurality of model parameters to one or more remote locations; receiving at least one updated model parameter from the one or more remote locations, the at least one model parameter is updated by training the initial prediction model with local data at the one or more remote locations; determining aggregated model parameters based on the at least one updated model parameter received from the one or more remote locations; and adjusting the initial prediction model based on the aggregated model parameters, the adjusted prediction model being operable to configure the semiconductor manufacturing process.

A cyber-physical system type machining system includes: a machine tool disposed in a real world and including a machine body and a control device; and a computer device connected to communicate with the control device and including a processor and a memory storing a program for generating, in a virtual world, a virtual machining phenomenon corresponding to an actual machining phenomenon with regard to a workpiece and the machine body. The program, when executed by the processor, causes the computer device to perform: acquiring a command value in synchronization with the control device, the command value for controlling the machine body by the control device; generating a future virtual machining phenomenon, which is the virtual machining phenomenon in a future, based on the command value; and outputting, to the control device, an optimal command value for correcting the command value based on the future virtual machining phenomenon.

A method for automatic quality inspection of an aeronautical part, includes detecting faults on an image of the aeronautical part using a trained artificial neural network; training an auto-encoder on a database, by projecting each image of the database onto a small mathematical space in which the images follow a predefined probability law; for each image of the database, calculating a plurality of metrics; supervised training of a classifier from the calculated metrics; detecting faults or anomalies in the image of the aeronautical part using the auto-encoder and the classifier.

A substrate processing condition setting method includes acquiring, causing, and setting. In the acquiring, a plurality of estimation processing results are acquired by inputting a plurality of processing conditions to a trained model that is subjected to machine training based on a training processing condition and a processing result obtained by processing a substrate under the training processing condition. In the causing, a display section is caused to display an image based on the estimation processing results. In the setting, one processing condition corresponding to one estimation processing result of the estimation processing results is set, as an actual processing condition in substrate processing, based on the image displayed on the display section.

A method for quality control in industrial manufacturing for one or more production processes for producing at least one workpiece and/or product includes creating a learning model for at least one production process for the at least one workpiece and/or product. The learning model is trained and initialized using a meta-learning algorithm, and the learning model is calibrated using normalized data of the at least one production process for the at least one workpiece and/or product. Currently generated data of the at least one production process for at least one currently produced workpiece/product is forwarded to the learning model. The data is generated by sensors. The learning model compares the currently generated data with the normalized data and finds deviations. The learning model scales the deviations between the currently generated data and the normalized data, and the learning model communicates presence of an anomaly for the currently produced workpiece/product.

An additive manufacturing system comprises an apparatus arranged to distribute layer of metallic powder across a build plane and a power source arranged to emit a beam of energy at the build plane and fuse the metallic powder into a portion of a part. The system includes a processor configured to steer the beam of energy across the build plane and receive data generated by one or more sensors that detect electromagnetic energy emitted from the build plane when the beam of energy fuses the metallic powder. The received data is converted into one or more parameters that indicate one or more conditions at the build plane while the beam of energy fuses the metallic powder. The one or more parameters are used as input into a machine learning algorithm to detect one or more defects in the fused metallic powder.

A system may include a first semiconductor processing station configured to deposit a material on a first semiconductor wafer, a second semiconductor processing station configured perform measurements indicative of a thickness of the material after the material has been deposited on the first semiconductor wafer, and a controller. The controller may be configured to receive the measurements from the second station; provide an input based on the measurements to a trained model that is configured to generate an output that adjusts an operating parameter of the first station such that the thickness of the material is closer to a target thickness; and causing the first station to deposit the material on a second wafer using the operating parameter as adjusted by the output.

The subject matter herein provides for AI-based prediction of production defects in association with a production system, such as a semiconductor manufacturing machine. In one embodiment, a method begins by receiving production data from the production system. The production data typically comprises non-homogeneous machine parameters and maintenance data, quality test data, and product and process data. Using the production data, a neural network is trained to model an operation of a given machine in the production system. Preferably, the training involves multi-task learning, transfer learning (e.g., using knowledge obtained with respect to a machine of the same type as the given machine), and a combination of multi-task learning and transfer learning. Once the model is trained, it is associated with the given machine operating environment, wherein it is used to provide quality assurance predictions.