Abstract: A battery-powered tracking component may be attached to a sterilization case. The tracking component may collect, store and transmit usage information associated with the sterilization case. The supplying of power to the tracking component may be temporarily stopped during autoclave processes. As the high temperatures and pressurized steam of autoclave processes may drain an active battery, the lifespan of the battery may be elongated by deactivating the battery during the autoclave processes. A temperature sensor may detect when the temperature of the sterilization case rises above a threshold indicating a start of the autoclave process, and when the temperature of the sterilization case falls below a threshold indicating an end of the autoclave process. The usage information may include a count of autoclave processes and durations of time periods between autoclave processes. The usage information may be used to determine times at which autoclave processes are performed.

Abstract: Systems and methods configured for receiving, from a user device associated with a user, a first request to associate the user with a target and account information associated with the user; retrieving the target from a database to associate the user with the retrieved target; receiving, from an entity, event data associated with the account information; computing an amount of contribution based on the received event data; transmitting the computed amount of contribution to a distribution system configured to distribute the contribution to the associated target; updating the database by aggregating the computed amount of contribution to a stored contribution data associated with the user; retrieving pre-authenticated data of the user allowing transmission of a message to a public forum; generating the message based on the event data and the computed amount of contribution; and transmitting the message to one or more devices via the public forum.

Abstract: A tool system includes a portable tool, an image capturing unit, an orientation detection unit, and a processing unit. The tool includes a driving unit to be activated with power supplied from a power source. The image capturing unit is provided for the tool and generates a captured image. The orientation detection unit is provided for the tool and detects an orientation of the tool. The processing unit performs processing based on the captured image and the orientation.

Abstract: Distributed industrial process monitoring and analytics systems and methods are provided for operation within a process plant. A plurality of distributed data engines (DDEs) may be embedded within the process plant to collect and store data generated by data sources, such as process controllers. Thus, the data may be stored in a distributed manner in the DDEs embedded throughout the process plant. The DDEs may be connected by a data analytics network to facilitate data transmission by subscription or query. The DDEs may be configured as a plurality of clusters, which may further include local and centralized clusters. The local clusters may obtain streaming data from data sources and stream selected data to a data consumer. The centralized cluster may register the local clusters, receive data therefrom, and perform data analytic functions on the received data. The analyzed data may be further sent to a data consumer.

Abstract: A computer monitors a status of grid devices using sensor measurements. Sensor data is clustered using a predefined grouping distance value to define one or more sensor event clusters. A plurality of monitored devices is clustered using a predefined clustering distance value to define one or more asset clusters. A location is associated with each monitored device of the plurality of monitored devices. A distance is computed between each sensor event cluster and each asset cluster. When the computed distance is less than or equal to a predefined asset/sensor distance value for a sensor event cluster and an asset cluster, an asset identifier of the asset cluster associated with the computed distance is added to an asset event list. For each asset cluster included in the asset event list, an asset location of an asset is shown on a map in a graphical user interface presented in a display.

Abstract: Automated methods and systems for identifying problems associated with objects of a data center are described. Automated methods and systems are performed by an operations management server. For each object, the server determines a baseline distribution from historical events that are associated with a normal operational state of an object. The server determines a runtime distribution of runtime events that are associated with the object and detected in a runtime window of the object. The management server monitors runtime performance of the object while the object is running in the datacenter. When a performance problem is detected, the management server determines a root cause of a performance problem based on the baseline distribution and the runtime distribution and displays an alert in a graphical user interface of a display.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to receive a first time series of positions of a vehicle sensor mounted on a vehicle from at least one calibration sensor spaced from the vehicle, measured while vibrations are applied to the vehicle; receive a second time series of motion of the vehicle sensor based on data from the vehicle sensor measured while the vibrations are applied to the vehicle; fuse the first and second time series; and determine at least one calibration value for an adjustment model based on the fusion of the first and second time series. The adjustment model is a model of motion of the vehicle sensor relative to the vehicle resulting from motion of the vehicle.

Abstract: A control unit of processing apparatus includes a processing condition storing section that stores processing condition data of the processing apparatus and a display control section that causes a display part to display a processing condition screen relating to the processing condition data. The display control section causes the processing condition screen to display function objects that allow identification of functions to be executed on the basis of the processing condition data by the processing apparatus.

Abstract: One or more non-transitory computer-readable storage media having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to receive data corresponding to a first condition of a building component within a building, determine, based on the data, an actual or anticipated fault state of the building component, retrieve, from a graph data structure including a number of entities and a number of relationships between the entities, and wherein the graph data structure represents at least one of a space, person, component, or event, first context information corresponding to the building component and second context information corresponding to the building, and determine, based on the first and second context information, a service action for the building component.

Abstract: A system for autonomously creating subsequent physical objects using a 3-dimensional printer. The system includes a build platform which is ejected with a printed object adhered to it, with a replenishing mechanism to place a blank build platform into the expected build area such that printing a subsequent object may occur autonomously. The replenishing mechanism may draw from a plurality of stored blank build platforms which may be reusable in some embodiments and disposable in others.

Abstract: Mitigating the reality gap through optimization of one or more simulated hardware parameters for simulated hardware components of a simulated robot. Implementations generate and store real navigation data instances that are each based on a corresponding episode of locomotion of a real robot. A real navigation data instance can include a sequence of velocity control instances generated to control a real robot during a real episode of locomotion of the real robot, and one or more ground truth values, where each of the ground truth values is a measured value of a corresponding property of the real robot (e.g., pose). The velocity control instances can be applied to a simulated robot, and one or more losses can be generated based on comparing the ground truth value(s) to corresponding simulated value(s) generated from applying the velocity control instances to the simulated robot. The simulated hardware parameters and environmental parameters can be optimized based on the loss(es).

Abstract: An industrial device supports device-level data modeling that pre-models data stored in the device with known relationships, correlations, key variable identifiers, and other such metadata to assist higher-level analytic systems to more quickly and accurately converge to actionable insights relative to a defined business or analytic objective. Data at the device level can be modeled according to modeling templates stored on the device that define relationships between items of device data for respective analytic goals (e.g., improvement of product quality, maximizing product throughput, optimizing energy consumption, etc.). This device-level modeling data can be provided to higher level systems together with their corresponding data tag values to high level analytic systems, which discovers insights into an industrial process or machine based on analysis of the data and its modeling data.

Abstract: Methods and systems for providing weak pattern (or hotspot) detection and quantification are disclosed. A weak pattern detection and quantification system may include a wafer inspection tool configured to inspect a wafer and detect defects present on the wafer. The system may also include at least one processor in communication with the wafer inspection tool. The at least one processor may be configured to: perform pattern grouping on the detected defects based on design of the wafer; identify regions of interest based on the pattern grouping; identify weak patterns contained in the identified regions of interest, the weak patterns being patterns deviating from the design by an amount greater than a threshold; validate the weak patterns identified; and report the validated weak patterns or facilitate revision of the design of the wafer based on the validated weak patterns.

Abstract: A wire electric discharge machining apparatus is provided. The wire electric discharge machining apparatus includes an upper support that supports an upper guide unit that guides a wire electrode on an upper side. The upper support includes an arm having a lower end provided with the upper guide unit, an axis drive portion moving the arm in at least one axial direction and made of a material that has a larger coefficient of linear expansion than ceramics, and an adjustment block connecting the arm and the axis drive portion and made of ceramics. The adjustment block is fixed at a position where a displacement of the upper guide unit caused by expansion and contraction of the upper support is suppressed by a bimetal effect occurring on a fastening surface of the axis drive portion and the adjustment block.

Abstract: Balancing the observed signals used to train network intrusion detection models allows for a more accurate allocation of computing resources to defend the network from malicious parties. The models are trained against live data defined within a rolling window and historic data to detect user-defined features in the data. Automated attacks ensure that various kinds of attacks are always present in the rolling training window. The set of models are constantly trained to determine which model to place into production, to alert analysts of intrusions, and/or to automatically deploy countermeasures. The models are continually updated as the features are redefined and as the data in the rolling window changes, and the content of the rolling window is balanced to provide sufficient data of each observed type by which to train the models. When balancing the dataset, low-population signals are overlaid onto high-population signals to balance their relative numbers.

Abstract: Data is received that is derived from each of a plurality of inspection camera modules forming part of a quality assurance inspection system. The data includes a feed of images of a plurality of objects passing in front of the respective inspection camera module. Thereafter, the received data is separately analyzed by each inspection camera module using at least one image analysis inspection tool. The results of the analyzing can be correlated for each inspection camera module on an object-by-object basis. The correlating can use timestamps for the images and/or detected unique identifiers within the images and can be performed by a cloud-based server and/or a local edge computer. Access to the correlated results can be provided to a consuming application or process.

Abstract: A slicer in a material drop ejecting three-dimensional (3D) object printer identifies the positions and local densities for a plurality of infill lines within a perimeter to be formed within a layer of an object to be formed by the printer. The local density of each infill line is filtered and a control law is applied to the filtered local density to identify an error in the local density compared to a target density. This process is performed iteratively until the error is within a predetermined tolerance range about the target local density. The error is used to generate machine ready instructions to operate the 3D object printer to achieve the target density for the infill lines.

Abstract: The present invention relates to an operation parameter regulation unit (50) for use with a bolting system having a plurality of networked electrically powered torque tools (10, 11) and/or drive portions of torque tools (10, 11) for simultaneous tightening of industrial threaded fasteners (40), the operation parameter regulation unit (50) including: a processing unit (53); an output unit (51) connected and/or integrated with the processing unit (53); an input unit (52) connected and/or integrated with the processing unit (53); an activation unit (55) connected and/or integrated with the processing unit (53) for activating operation units of the plurality of networked electrically powered torque tools (10, 11) and/or drive portions of torque tools (10, 11); and a control unit (54) for controlling operation parameters (41) of each of the plurality of networked electrically powered torque tools (10, 11) and/or drive portions of torque tools (10, 11) to maintain a difference between the operation parameters (41)

Abstract: A method for predicting a remaining life of a tool of a computer numerical control machine is provided. In the method, indirect measurement indicators of the tool are selected based on monitoring and analyzing a current state of the tool, a prediction model for the remaining life of the tool is established based on data de-noising, feature extraction and a multi-kernel W-LSSVM algorithm. Thereby, a method for predicting a remaining life of a tool of a computer numerical control machine is provided.

Abstract: To efficiently search a processing condition of giving a desired target processing result, there is provided a processing condition determination system including a processing apparatus that processes a sample, a processing monitor system that monitors the state of the processing in the processing apparatus, and an analysis system that sets the processing condition of the processing apparatus of giving a target processing result, wherein the system includes a processing condition and result database that stores a set of an explanatory variable that is a processing condition under which the processing apparatus processes a sample and an objective variable that is the processing result obtained by the processing apparatus' processing the sample, and when the processing apparatus processes the sample under the processing condition set using the correlation model derived from the database and it is determined that a probability of failure occurrence becomes high, based on the monitor data of the processing monito

Abstract: Provided is a method for monitoring 3D printing equipped with a 3D printing slicer and a recursive loop structure. A 3D printing method according to an embodiment of the present invention sets up a slicing environment for 3D printing of a 3D model, generates a mechanical code by performing slicing according to the setup environment, monitors the status of the 3D printing according to the generated mechanical code, and, depending on the monitoring result, determines whether or not to re-perform the setup and subsequent steps. Accordingly, by semi- or fully automating the 3D printing engineering process, the time and effort for engineering performance involving human participation are reduced, and the human resource is concentrated on a more important area, such that the effects of enhancing the 3D printing output quality and assuring the quality can be expected.

Abstract: The present disclosure provides systems and methods for controlling a semiconductor manufacturing equipment. A control system includes a sensor unit capturing a set of data related to a gas pressure in the equipment, a sensor interface receiving the set of data and generating at least one input signal for a database server, and a control unit. The control unit includes a front end subsystem, a calculation subsystem, and a message and feedback subsystem. The front end subsystem performs a front end process to generate a data signal. The calculation subsystem performs an artificial intelligence analytical process to determine, according to the data signal, whether a malfunction related to the gas pressure has occurred and generate an output signal. The message and feedback subsystem generates an alert signal and a feedback signal according to the output signal and transmits the alert signal to a user.

Abstract: [Problem] In an optical transmission system, a position and a cause of a failure are identified while avoiding tightness of processing on a network controller side. [Solution] An optical transmission system 1 includes a plurality of nodes 4i to 4k interconnected by an optical transmission line, a plurality of node controllers 3i to 3k that detect degradation of signal quality at the nodes 4i to 4k, respectively, and determine a degradation mode correlated with the signal quality, and a network controller 2 that identifies a node or a component in which failure has occurred based on a node for which the node controller 3i to 3k has detected degradation of the signal quality, the degradation mode, a network topology formed of the nodes, and an optical path set between the nodes.

Abstract: Disclosed is an interior tracking system for manufacturing control. The interior tracking system has multiple, fixedly installed transceivers for determining the position of multiple mobile units, the position being determined in particular by evaluating the propagation time of electromagnetic (radio) signals. The interior tracking system is used to assign one of the mobile units to one or more workpieces in an industrial manufacturing plant that processes steel and/or sheet metal, to determine the position of the assigned workpieces by localizing the assigned mobile unit using the interior tracking system and to integrate the interior tracking system into a manufacturing control system of the industrial manufacturing plant.

Abstract: A system for controlling interactions between a plurality of real and virtual robots, includes one or more real robots present in the real environment, one or more virtual robots present in a virtual environment corresponding to the real environment, and a processing device operable to control interactions between one or more of the real robots and one or more of the virtual robots, where the interactions between the real and virtual robots are dependent upon at least the positions of the one or more real robots in the real environment and the positions of the one or more virtual robots in the virtual environment.

Abstract: A method and apparatus for performing automated supervision and inspection of an assembly process. The method is implemented using a computer system. Sensor data is generated at an assembly site using a sensor system positioned relative to the assembly site. A current stage of an assembly process for building an assembly at the assembly site is identified using the sensor data. A context for the current stage is identified. A quality report for the assembly is generated based on the sensor data and the context for the current stage.

Abstract: A system for detection of an anomaly in a discrete manufacturing process (DMP) with human-robot teams executing a task. Receive signals including robot, worker and DMP signals. Predict a sequence of events (SOEs) from DMP signals. Determine whether the predicted SOEs in the DMP signals is inconsistent with a behavior of operation of the DMP described in a DMP model, and if the predicted SOEs from DMP signals is inconsistent with the behavior, then an alarm is to be signaled. Input worker data into a Human Performance (HP) model, to obtain a state of the worker based on previously learned boundaries of human state. The state of the HW is then input into the HRI model and the DMP model to determine a classification of anomaly or no anomaly. Update a Human-Robot Interaction (HRI) model to obtain a control action of a robot or a type of an anomaly alarm.

Abstract: The present disclosure provides a method for controlling a manufacturing process parameter, a manufacturing execution server, and an equipment interface server. The method includes: acquiring manufacturing process parameter information of an manufacturing equipment; and verifying the acquired manufacturing process parameter information according to reference ranges of manufacturing process parameter information of multiple manufacturing equipments which are registered in advance, and feeding back a verification result.

Abstract: An information management system includes: a storage section storing a data model created based on product manufacturing planning, the data model corresponding to an area where manufacturing achievement data from the manufacturing process is accumulated; an information collection section configured to collect various types of data forming the manufacturing achievement data from a data source involved in the manufacturing process; and a manufacturing management section configured to store the manufacturing achievement data in the associated data model. The manufacturing management section is configured to use the various types of data to create the manufacturing achievement data according to a data structure definition template for organizing the various types of data in association with a thing performed and a situation during the performance in the manufacturing process.

Abstract: Technologies for enhancing work scheduling of a big data framework. The technologies can include generating, in a database, configurable namespaces to be used by a work scheduling enhancement application to group together tasks of one or more big data clusters. The namespaces can be hierarchical. The technologies can also include linking in the database, by the application, related tasks with respective namespaces to categorize and group together the related tasks. The technologies can also include configuring, by the application, a display scheme for displaying error handling and root cause analysis of tasks of the one or more big data clusters. The technologies can also include generating or rendering, by the application, a GUI having a navigable hierarchal view for displaying the namespaces. The generation or rendering of the GUI can be based partially on the display scheme.

Abstract: A method and apparatus for determining differences between an automated installation and a digital twin of the automated installation and to an automated installation that includes the apparatus, wherein a sensor unit is fastened to a process material and passes through an automated installation together with the process material where, during this process, the sensor unit continuously records at least one measurement variable, a temporal profile of the recorded measurement variable is compared with a temporal profile of a corresponding simulated measurement variable and if there is a difference between the temporal profiles, then the location in the automated installation at which the difference is present is identified.

Abstract: A method verifies an authenticity, integrity, and provenance of outputs from steps in a process flow. One or more processor(s) validate one or more inputs to each step in a process flow by verifying at least one of a hash and a digital signature of each of the one or more inputs. The processor(s) then generate digital signatures that cover outputs of each step and the one or more inputs to each step, such that the digital signatures result in a chain of digital signatures that are used to verify an authenticity, an integrity and a provenance of outputs of the one or more steps in the process flow.

Abstract: The present invention provides a classification method for automatically identifying wafer spatial pattern distribution, comprising the following steps: performing statistical analysis to distribution of defects on a wafer, the defects being divided into random defects, repeated defects and cluster defects; performing denoising and signal enhancement to the cluster defects; performing feature extraction to the cluster defects after denoising and signal enhancement; and performing wafer spatial pattern distribution classification to the cluster defects after feature extraction. By performing statistical analysis and neural network training to a great amount of wafer defect distribution, the spatial patterns in defect distribution can be automatically identified, the automatic classification of wafer spatial patterns can be realized, the workload of engineers is effectively reduced and the tracing of the root cause of such spatial pattern is facilitated.

Abstract: Method of identifying a product which comprises cellulose, wherein in the method a data set is determined which is indicative for multiple constituents of the product or a preform of the product, and the data set which is correlated with the product or the preform is stored in a database.

Abstract: A method for accelerating calibration of a fabrication process model, the method including performing one or more iterations of: defining one or more fabrication process model terms; receiving predetermined information related to the one or more fabrication process model terms; generating a fabrication process model based on the predetermined information, the fabrication process model configured to generate one or more predictions related to a metrology gauge; determining whether a prediction related to a dimension of a gauge is within a predetermined threshold of the gauge as measured on a post-fabrication process substrate; and responsive to the prediction not breaching the predetermined threshold, optimizing the one or more fabrication process terms such that the prediction related to the dimension of the gauge is within the predetermined threshold of the gauge as measured on the post-fabrication process substrate.

Abstract: Critical network assets of a private computer are automatically identified by training a machine learning model with histograms of features obtained by aggregating data of log entries. The model is deployed in a private computer network and retrained using training data set of the private computer network. Data from log entries of a target network asset are aggregated, numerically transformed, and converted into features histograms. The features histograms are concatenated into a single file, which is provided to the machine learning model for prediction. The machine learning model outputs a prediction score that gives an indication of whether or not the target network asset is critical.

Abstract: An metal fabrication resource performance monitoring method includes: acquiring data representative of a plurality of parameters sampled during metal fabrication operations of a plurality of metal fabrication resources, the parameters comprising arc on time and wire deposition quantity; via at least one computer processor, analyzing a first subset of the acquired data and a second subset of the acquired data for the plurality of metal fabrication resources; via the at least one computer processor, populating a user viewable page with graphical indicia representative of at least the arc on time and the wire deposition quantity, the user viewable page facilitating a visual comparison of the analysis of the first subset of the acquired data and the analysis of the second subset of the acquired data; and transmitting the user viewable dashboard page to a user viewable display.

Abstract: Aspects of recovery of an application from an error. An error notification is received from an agent associated with an application, the error notification being indicative of an error encountered during execution of the application. The error notification is compared with error patterns stored in a database to determine a matching error pattern. Further, a recovery action is ascertained and the recovery action is provided to the agent to recover the application from the error.

Abstract: A method includes, for each data object of a plurality of data objects, performing a measurement on a plurality of instances of the data object to generate a plurality of measurement values for the data object, and generating a distribution of the measurement values for the data object. The method further includes generating an aggregate distribution based on each of the distributions of the measurement values generated for the data objects, and scoring a first data object of the plurality of data objects based on the distribution of the measurement values for the first data object and the aggregate distribution.

Abstract: Mitigating the reality gap through optimization of one or more simulated hardware parameters for simulated hardware components of a simulated robot. Implementations generate and store real navigation data instances that are each based on a corresponding episode of locomotion of a real robot. A real navigation data instance can include a sequence of velocity control instances generated to control a real robot during a real episode of locomotion of the real robot, and one or more ground truth values, where each of the ground truth values is a measured value of a corresponding property of the real robot (e.g., pose). The velocity control instances can be applied to a simulated robot, and one or more losses can be generated based on comparing the ground truth value(s) to corresponding simulated value(s) generated from applying the velocity control instances to the simulated robot. The simulated hardware parameters and environmental parameters can be optimized based on the loss(es).

Abstract: A work management device manages a board work line having multiple board work machines for performing work on a board. The work management device includes a problem detection section configured to detect that a problem has occurred in any of the multiple board work machines; a handling method database configured to accumulate handling methods for problems; an updating section configured to update handling methods for problems at any time; and a work instruction section configured to extract and indicate to an operator a handling method for a problem from the handling method database when the problem detection section detects that the problem has occurred.

Abstract: A device and method for generating scan data and/or slice data for use in an additive manufacturing process, in which an energy beam is scanned across layers of flowable material to consolidate the material in a layer-by-layer manner to build a part. The device includes a display and a processor. The processor is arranged to determine scan data for slices and/or slices of the part to be built in the additive manufacturing process and cause the display to display scan data and/or slices that has been determined whilst determining scan data for other ones of the slices and/or other ones of the slices from the geometric data.

Abstract: The present technology provides a system, method and computer-readable medium for configuration pattern recognition and inference, directed to a device with an existing configuration, through an extensible policy framework. The policy framework uses a mixture of python template logic and CLI micro-templates as a mask to infer the intent behind an existing device configuration in a bottom-up learning inference process. Unique values for device/network identifiers and addresses as well as other resources are extracted and accounted for. The consistency of devices within the fabric is checked based on the specific policies built into the extensible framework definition. Any inconsistencies found are flagged for user correction or automatically remedied by a network controller. This dynamic configuration pattern recognition ability allows a fabric to grow without being destroyed and re-created, thus new devices with existing configurations may be added and automatically configured to grow a Brownfield fabric.

Abstract: Systems and methods are provided for increasing employee productivity in a production process. One or more machines for accomplishing a production activity and in communication with a database which includes pay rates and predetermined thresholds for the production activity. Data acquiring devices associated with each machine measure production rates in substantially real time. A processor retrieves the pay rate and the production rate to determine a real-time-pay rate. A display provides a ranking and visualization reflecting each employee's real-time-pay and a graphic indicating whether each employee's real-time-pay rate exceeds one or more of the predetermined thresholds.

Abstract: To evaluate a semiconductor-fabrication process, a semiconductor wafer is obtained that includes die grouped into modulation sets. Each modulation set is fabricated using distinct process parameters. The wafer is optically inspected to identify defects. A nuisance filter is trained to classify the defects as DOI or nuisance defects. Based on results of the training, a first, preliminary process window for the wafer is determined and die structures having DOI are identified in a first group of modulation sets bordering the first process window. The trained nuisance filter is applied to the identified defects to determine a second, revised process window for the wafer. A third, further revised process window for the wafer is determined based on SEM images of specified care areas in one or more modulation sets within the second, revised process window. A report is generated that specifies the third process window.

Abstract: An assembly method is provided by orienting a cylinder-head at a first orientation. A first plurality of spring caps and a first plurality of retainer keys are installed into the cylinder-head in the first orientation by a first robot. A first plurality of valves is installed into the cylinder-head in the first orientation by a second robot, into engagement with the first plurality of retainer keys. An end effector is provided with an actuator supported upon an adapter plate. A shaft extends from the actuator with a mating surface to engage a spring cap. Porting is provided through the shaft to convey pressurized air upon a plurality of retainer keys within the spring cap. A plurality of gripper fingers extend from the distal end of the shaft to grip a valve spring while retaining a spring cap between the valve spring and the mating surface of the shaft.

Abstract: Systems and methods for automatic correction of drift between inspection and design for massive pattern searching are disclosed herein. Defects are identified in a scan of a wafer. The defects are associated with tool coordinates. An SEM review tool captures centered images of the defects. The SEM review tool is aligned with the wafer using design polygons in an imported design file. Design coordinates are exported and used to define patterns of interest and identifying locations of those patterns of interest.

Abstract: There are provided system and method of segmentation a fabrication process (FP) image obtained in a fabrication of a semiconductor specimen. The method comprises: upon obtaining a Deep Neural Network (DNN) trained to provide segmentation-related data, processing a fabrication process (FP) sample using the obtained trained DNN and, resulting from the processing, obtaining by the computer segments-related data characterizing the FP image to be segmented, the obtained segments-related data usable for automated examination of the semiconductor specimen. The DNN is trained using a segmentation training set comprising a plurality of first training samples and ground truth data associated therewith, each first training sample comprises a training image; FP sample comprises the FP image to be segmented.

Abstract: An image processing method, an electronic device and a computer readable storage medium are described. The image processing method may include: obtaining an image to be detected, and inputting the image to be detected to a neural network; detecting the image to be detected via the neural network to obtain confidence levels of image categories for a background image in the image and confidence levels of object categories for a foreground target in the image; determining an image category of the background image according to the confidence levels of the image categories for the background image and a confidence level threshold; and determining an object category of the foreground target according to the confidence levels of the object categories for the foreground target and the confidence level threshold.

Abstract: A state determination device includes: a primary determination learning model that has learned an outline of a state of a manufacturing device based on a state variable acquired from a manufacturing operation of a product of the manufacturing device; and a secondary determination learning model that has learned a state of the manufacturing device based on a state variable acquired from a predetermined operation pattern set in advance and maintenance information. Then, a primary determination is made on the outline of the state of the manufacturing device using the primary determination learning model based on the state variable acquired from the manufacturing operation of the product, and further, a secondary determination is made on the state of the manufacturing device using the secondary determination learning model based on the state variable acquired from the predetermined operation pattern.