To provide an appearance inspection system capable of reduce labor for setting an imaging condition by a designer when a plurality of inspection target positions on a target is sequentially imaged. An appearance inspection system includes an imaging condition decision part and a route decision part. The imaging condition decision part decides a plurality of imaging condition candidates including a relative position between a workpiece and an imaging device for at least one inspection target position among a plurality of inspection target positions. The route decision part decides a change route of an imaging condition for sequentially imaging the plurality of inspection target positions by selecting one imaging condition among the plurality of imaging condition candidates so that a pre-decided requirement is satisfied.

A multiplexing device including a multistage slave configured to process control data transmitted from a master in an industrial network, a multiprocessing device configured to multiplex the control data transmitted from a first slave of the multistage slave, the first slave being disposed at an upstream side to the master of the multistage slave, and transmit the control data so multiplexed to a second slave of the multistage slave by way of a multiplex communication line, the second slave being situated at a downstream side of the multistage slave, and a control device configured to issue a disconnection command to disconnect a communication between the first slave and the multiprocessing device in response to a disconnection of the multiplex communication line.

Computer-based methods and systems provide automated batch data alignment for a batch production industrial process. An example embodiment selects a reference batch from batch data for a subject industrial process and configures batch alignment settings. In turn, a seed model configured to predict alignment quality given settings for one or more alignment hyperparameters is constructed. Collectively the selected reference batch, the configured batch alignment settings, the constructed seed model, and a set of representative batches, representative of the batch data for the industrial process, are used to perform at least one of: (i) automated active learning, (ii) interactive active learning, and (iii) guided learning to determine settings for the one or more alignment hyperparameters. Then, a batch alignment is performed using the determined settings for the one or more alignment hyperparameters and the configured batch alignment settings. The resulting aligned batch data of the subject industrial process enables improved modeling and control of batch productions by the subject industrial process.

An information processing device includes: a processor configured to: specify plural parts for manufacturing an ordered product; specify plural processes required from receiving an order of the product to completion of the product using plural parts; for an intermediate part generated by processing at least two of the plural parts, generate an intermediate object indicating intermediate part; for each of the plural parts, generate work objects indicating processes required for manufacturing the part; and create workflow information that arranges and displays, for each of the plural parts, the work objects indicating processes required for manufacturing the part in an order of the plural processes, and relates and displays, for each of the plural parts, work objects indicating processes executed continuously, in which in the workflow information, the intermediate object indicating intermediate part is associated with the work objects for the at least two parts used to generate the intermediate part.

Methods and systems enabling commercial opportunities for additive manufacturing workflow management including computerized processing of a plurality of three-dimensional CAD files received and aggregated by the system and organizing the plurality of three-dimensional CAD model files received and aggregated by the system and where the data corresponding to the three-dimensional CAD model(s) geometry contained within the 3D CAD Model files received by the system are analyzed by the system for production criteria. The analyzed 3D CAD Model files and their geometry are then organized by production criteria. Batches of the geometry contained within the analyzed and organized 3D CAD Model files are then analyzed for arrangement, by nesting and stacking system controllers to determine a solution for optimizing production resource utilization and packed, by the system as nested arrangements of CAD Model geometry and compiled as computer files called tray files, representing packed arrangements of 3D CAD Model geometry according to production criteria and a production capacity plan determined by the system. The tray files represent production jobs for production by additive manufacturing. The tray files are then scheduled and assigned, by the system to the production queue of indexed production resources defined in the system by the commercial user, according to the production criteria for each tray file. The tray files are then made available and or transmitted or routed to an additive manufacturing device for production of the geometry described within each tray file and where the Additive manufacturing device produces the geometry described within the tray file using the data in the tray file, at least in part to do so, such that the objects produced corresponds directly to the three-dimensional models received and processed by the system.

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.

A manufacturing plant with an MES system is controlled through the execution of a given workflow. a) A plant designer application models a representation of the manufacturing plant through a set of equipment objects and through a workflow, b) a complex entity (plugin) is provided for expanding the characteristics of an equipment object; the plugin exposing an interface with a configuration, a set of property elements, a set of functionality elements; c) at engineering time, designing a set of plugins usable by the set of equipment objects; d) at engineering time, for at least one equipment object, associating at least one plugin; e) defining, through the plant designer, a given workflow according to given customer requirements, the workflow including an interaction with an element of a plugin associated with an equipment object; f) at runtime, executing the given workflow and performing the interaction with the element of the plugin.

Provided is a process optimizer apparatus for optimizing dynamically an industrial production process of a production plant including physical production modules, the process optimizer including a watchdog component adapted to monitor the production modules of the production plant to detect configuration changes within the production plant; a model comparator component adapted to evaluate a production plant data model of the production plant including digital twin data models related to physical production modules of the production plant to identify automatically deviating model elements of digital twin data models related to physical production modules of the production plant affected by the configuration changes detected by the watchdog component; and a process resequencer component adapted to perform a dynamic process optimization of the at least one production process of the production plant depending on the deviating model elements identified by the model comparator component.

A method and system may generate a quality control profile to indicate an expertise level and one or more skills of a teleoperator(s). The control center evaluates optimization criteria for a workflow to assign performance of microtasks of the workflow to select teleoperators from a pool of teleoperators. Each teleoperator accesses teleoperation functionality for remote control of a plurality of types of equipment at one or more defined geographic areas and each teleoperator is remotely located from the defined geographic areas. The control center generates queues for each of the select teleoperators that include corresponding assigned microtasks.

A method and apparatus for manufacturing a product. The method comprises creating a product plan comprising time units during which manufacturing of the product occurs, wherein the time units are grouped into phases of the manufacturing. Further, the product plan also includes entities performing work on systems for the product and work items performed by the entities during the manufacturing days. The manufacturing of the product is controlled using the product plan.