Abstract: A disposition manager configured to identify a damaged component of a damaged assembly by determining a measured first property value of a set of measured property values associated with the damaged component and obtained by a sensor is not within a range of acceptable first property values according to a specification of the damaged component. The disposition manager further configured to estimate a performance characteristic of the damaged component and a salvage value of the damaged component. The disposition manager further configured to present, to a user interface, the performance characteristic and the salvage value for the damaged component.

Abstract: An inspecting and repairing device of additive manufacturing technology and a method thereof are provided. The inspecting and repairing device has a powder bed unit, a repairing unit, and an inspection unit. The powder bed unit has a powder platform, a powder spreading mechanism and a laser unit. The repairing unit has a processing mechanism. The inspection unit has a camera and a controller. According to an image of the powder platform captured by the camera, the controller can determine whether spreading powders, whether being overcome a powder spreading defect, or whether driving the processing mechanism to repair a surface of a workpiece.

Abstract: A board inspecting apparatus include a measuring section, a processing section and a display section. The measuring section obtains measurement data for at least a portion of a board. The processing section compares the measurement data and reference data of the board, based on selection feature objects, by associated selection feature objects, to perform distortion compensation for the board, and inspects the board with distortion compensation. The display section distinguishably displays a first area with the distortion compensation successful and a second area with the distortion compensation failed. The processing section compares a number of recognizable effective feature objects with a reference number, and determine the distortion compensation as failed when the number of the recognizable effective feature objects is below the reference number.

Abstract: Disclosed are methods and systems for detecting an abnormal stress condition in a subject or group of subjects. Included is a risk evaluation system monitoring people, wherein a control unit in a stress management system obtains mental health information and records same in a measurement information database. The control unit then specifies a pattern in a reference pattern database and obtains the measurement information relating to this pattern from the measurement information database. The control unit in the stress management system (20) then revises a standard pattern based on individual attributes or work attributes. Next, the control unit performs pattern matching and determines whether or not attention is required. If the determination is that attention is required, the control unit presents an alert and an advice. This enables work, organization, and member risks to be appropriately evaluated based on changes in mental health information.

Abstract: Methods and systems for evaluating the geometric characteristics of patterned structures are presented. More specifically, geometric structures generated by one or multiple patterning processes are measured by two or more metrology systems in accordance with a hybrid metrology methodology. A measurement result from one metrology system is communicated to at least one other metrology systems to increase the measurement performance of the receiving system. Similarly, a measurement result from the receiving metrology system is communicated back to the sending metrology system to increase the measurement performance of the sending system. In this manner, measurement results obtained from each metrology system are improved based on measurement results received from other cooperating metrology systems. In some examples, metrology capability is expanded to measure parameters of interest that were previously unmeasurable by each metrology system operating independently.

Abstract: Examples are disclosed that relate to computing devices and methods for simulating light passing through one or more lenses. In one example, a method comprises obtaining a point spread function of the one or more lenses, obtaining a first input raster image comprising a plurality of pixels, and ray tracing the first input raster image using the point spread function to generate a first output image. Based on ray tracing the first input raster image, a look up table is generated by computing a contribution to a pixel in the first output image, wherein the contribution is from a pixel at each location of a subset of locations in the first input raster image. A second input raster image is obtained, and the look up table is used to generate a second output image from the second input raster image.

Abstract: Methods manage non-destructive evaluation (“NDE”) data. NDE data for an asset is received and at least one alignment algorithm to align the NDE data to a simulated model associated therewith is determined. The NDE data is automatically aligned to the simulated model, a display representation that visually represents the aligned NDE data on the simulated model is generated, and information about the aligned NDE data is exported. Additionally, second NDE data associated with the at least a portion of the asset may also be received, at least one alignment algorithm to align the data determined, and the second NDE data aligned. Respective indications associated with the first and second NDE data may be determined and visually represented on the simulated model. Moreover, a shot descriptor file may be analyzed to determine whether additional NDE data is required to complete an alignment of NDE data.

Abstract: A method of inspecting the wear of a turbine engine part includes, by means of a calculator: a reference plane is defined; by measuring said part to be inspected, a modelling of at least a portion of said part is acquired in the form of a three-dimensional inspection grid; the three-dimensional inspection grid is inspected with the reference plane, using a dedicated algorithm using a projection of points (10; 10.1, 10.2, . . . , 10.n); if the result of the comparison is included in a predetermined tolerance range, the part is defined as compliant; otherwise, the part is non-compliant.

Abstract: Techniques and systems are provided for processing image data using one or more neural networks. For example, a patch of raw image data can be obtained. The patch can include a subset of pixels of a frame of raw image data, and the frame can be captured using one or more image sensors. The patch of raw image data includes a single color component for each pixel of the subset of pixels. At least one neural network can be applied to the patch of raw image data to determine a plurality of color component values for one or more pixels of the subset of pixels. A patch of output image data can then be generated based on application of the at least one neural network to the patch of raw image data. The patch of output image data includes a subset of pixels of a frame of output image data, and also includes the plurality of color component values for one or more pixels of the subset of pixels of the frame of output image data.

Abstract: Provided is a method of evaluating a semiconductor substrate, which evaluates quality of the semiconductor substrate by a photoluminescence measurement, wherein the evaluation by the photoluminescence measurement includes, after subjecting a surface of an evaluation-target semiconductor substrate to a pretreatment, irradiating the surface with excitation light, and then detecting emission obtained from the surface having been irradiated with the excitation light, and the pretreatment includes subjecting the surface of the evaluation-target semiconductor substrate to be irradiated with the excitation light to an oxide film formation treatment and charging the surface of the formed oxide film by corona discharge.

Abstract: The present disclosure relates to systems and processes for inspecting and evaluating qualities of printed regions on substrates, wherein the systems and methods may be configured to eliminate subjective aspects relating to human involvement in performing visual checks when evaluating print quality. The systems may include one or more communication networks connecting one or more sensors with an analyzer. In operation, ink is applied to a substrate to create at least one printed region, and the sensors are configured to inspect the printed region. The sensors may be configured to communicate measurements and/or images to the analyzer. And the analyzer may then calculate one or more quality subscores based on respective measurements and/or images. In turn, a full print quality score may be calculated based on one or more of the quality subscores. The analyzer may then execute a control action based on the full print quality score.

Abstract: Aspects of this disclosure relate to detecting and recording information associated with electrical overstress (EOS) events, such as electrostatic discharge (ESD) events. For example, in one embodiment, an apparatus includes an electrical overstress protection device, a detection circuit configured to detect an occurrence of the EOS event, and a memory configured to store information indicative of the EOS event.

Abstract: An image inspection apparatus includes an imaging section including a light-condensing optical system configured to condense reflected light of illumination light and a line camera for receiving the reflected light, an imaging inclination sensor capable of outputting, a direction orthogonal to a Z axis and parallel to an arranging direction of imaging elements is represented as an X axis, and a direction orthogonal to the X axis and the Z axis is represented as a Y axis, values indicating inclinations of the X axis, the Y axis, and the Z axis of the imaging section with respect to a horizontal direction or a gravity direction, and a display control section for causing a display section to display figures or values indicating degrees of at least any two inclinations among the inclinations of the X axis, the Y axis, and the Z axis of the imaging section.

Abstract: Pattern centric process control is disclosed. A layout of a semiconductor chip is decomposed into a plurality of intended circuit layout patterns. For the plurality of intended circuit layout patterns, a corresponding plurality of sets of fabrication risk assessments corresponding to respective ones of a plurality of sources is determined. Determining a set of fabrication risk assessments for an intended circuit layout pattern comprises determining fabrication risk assessments based at least in part on: simulation of the intended circuit layout pattern, statistical analysis of the intended circuit layout pattern, and evaluation of empirical data associated with a printed circuit layout pattern. A scoring formula is applied based at least in part on the sets of fabrication risk assessments to obtain a plurality of overall fabrication risk assessments for respective ones of the plurality of intended circuit layout patterns.

Abstract: A workpiece processing apparatus includes: a first rotational distance information storage unit that stores multiple pieces of first rotational distance information, each of which is information having, in association with each other, a rotational angle, and first distance information regarding a distance from a rotation center to an edge of a circular workpiece corresponding to the rotational angle, in a case where the workpiece is rotated; an acquiring unit that acquires information for positioning the workpiece, information for specifying an orientation of the workpiece, and information regarding a defective portion at the edge of the workpiece, using the multiple pieces of first rotational distance information stored in the first rotational distance information storage unit; and an output unit that outputs the information for positioning the workpiece, the information for specifying the orientation of the workpiece, and the information regarding the defective portion, which are acquired by the acquiring u

Abstract: According to the present invention, the work status at an actual site is represented using a combination of component statuses. A degree of damage that takes into account the manner of use at the actual site is predicted by associating test data collected in a component status test. The objective of the present invention is to estimate, with high accuracy, the degree of damage to a device operating in an actual environment.

Abstract: An activity monitor comprising one or more acoustic transducers (100) and a computation component (104) that is arranged to identify events from acoustic signals received by the acoustic transducers (100).

Abstract: A system and a method for determining an association of one or more biological features with a medical condition provides empirical results and simulations confirming that the involvement of both L1/2-regularized logistic regression and L2-regularized logistic regression in the regression model is highly competitive against usual approaches like Lasso, L1/2, SCAD-L2, and Elastic net in analyzing high dimensional and low sample sizes data.

Abstract: Systems and methods for antenna pattern measurement are provided. One system includes a plurality of wireless sensors arranged in an array, wherein the wireless sensors are configured to be powered by radio-frequency (RF) signals at different power levels. The system also may include a controller configured to wirelessly transmit the RF signals at different power levels and measure responses from the wireless sensors at the different power levels. The system may further include a processor configured to calculate a radiation pattern of an antenna under test using the measured responses.

Abstract: According to one embodiment, a manufacturing control system includes a reference data creating unit, first, second and third data storing units, first, second and third data extracting units. The reference data creating unit creates reference data including a reference time related to a product. The first data storing unit stores data related to parts acceptance inspection and related to assembly of the product. The second data storing unit stores data related to inspection in manufacturing. The third data storing unit stores data related to quality assurance inspection and of acceptance inspection at a customer site. The first data extracting unit extracts data related to latest parts acceptance inspection and related to latest assembly of the product. The second data extracting unit extracts data related to inspection in latest manufacturing. The third data extracting unit extracts data related to latest quality assurance inspection and of latest acceptance inspection.

Abstract: A wafer shipping device includes a box body having a first slot, a cover body having a second slot, and a sensing circuit module having a first sensor, a second sensor, an indication circuit and a warning device. The first slot and the second slot are used to collaboratively hold a semiconductor wafer. The first sensor and the first sensor are located in the box body for independently sensing whether the semiconductor wafer is inserted in the first slot and the second slot respectively. The indication circuit is electrically connected to the first sensor, the second sensor and the warning device, and correspondingly issued one of types of indication signals to the warning device in response to sensing results obtained from the first sensor and the second sensor respectively.

Abstract: In a method of controlling a lithographic apparatus, historical performance measurements are used to calculate a process model relating to a lithographic process. Current positions of a plurality of alignment marks provided on a current substrate are measured and used to calculate a substrate model relating to a current substrate. Additionally, historical position measurements obtained at the time of processing the prior substrates are used with the historical performance measurements to calculate a model mapping. The model mapping is applied to modify the substrate model. The lithographic apparatus is controlled using the process model and the modified substrate model together. Overlay performance is improved by avoiding over- or under-correction of correlated components of the process model and the substrate model. The model mapping may be a subspace mapping, and dimensionality of the model mapping may be reduced, before it is used.

Abstract: A virtual model display method, device and system are provided. The method includes: receiving a first identification information list sent by an entity equipment; sending the first identification information list to a server. The first identification information list is used for triggering the server to determine a second identification information list according to the first identification information list. The method also includes receiving the second identification information list fed back by the server. The second identification information list includes identification information in the first identification information list and verified by the server. The method also includes acquiring one or more virtual images corresponding to the identification information in the second identification information list; and assembling the one or more virtual images to obtain a virtual model corresponding to the entity equipment.

Abstract: Sonar rendering systems and methods are described herein. One example is an apparatus that includes a transducer element, position sensing circuitry, processing circuitry, and a display device. The processing circuitry may be configured to receive raw sonar data and positioning data, convert the raw sonar data into range cell data based at least on amplitudes of the return echoes, make a location-based association between the raw sonar data and the positioning data, plot the range cell data based on respective positions derived from the positioning data and rotate the range cell data based on a direction of movement of the watercraft to generate adjusted range cell data. The processing circuitry may be further configured to convert the adjusted range cell data into sonar image data, and cause the display device to render the sonar image data with a presentation of a geographic map.

Abstract: Methods for performing a structured collection procedure by utilizing a collection device are disclosed herein, in which a collection procedure is initiated for performing one or more data collections for one or more data event instances occurring according to a schedule of events. Each data event instances comprises a data collection pertaining to a biomarker to be performed according to one or more conditions of an adherence criterion. Each data event instance is determined to be successful or unsuccessful on the basis of actual performance of the data collection and meeting certain conditions of the predetermined adherence criteria for the data event instance. Contextual information for successful data collections is generated and a data file generated for storing records relating to successful data collections.

Abstract: Methods and systems for detecting defects on a specimen are provided. One system includes a generative model. The generative model includes a non-linear network configured for mapping blocks of pixels of an input feature map volume into labels. The labels are indicative of one or more defect-related characteristics of the blocks. The system inputs a single test image into the generative model, which determines features of blocks of pixels in the single test image and determines labels for the blocks based on the mapping. The system detects defects on the specimen based on the determined labels.

Abstract: Methods and systems for detecting anomalies in images of a specimen are provided. One system includes one or more computer subsystems configured for acquiring images generated of a specimen by an imaging subsystem. The computer subsystem(s) are also configured for determining one or more characteristics of the acquired images. In addition, the computer subsystem(s) are configured for identifying anomalies in the images based on the one or more determined characteristics without applying a defect detection algorithm to the images or the one or more characteristics of the images.

Abstract: An inspection method includes, with a sensor mounted in an infrastructure, measuring drive assisting information that is to be used to perform a drive assisting operation of a target vehicle that uses the infrastructure, transmitting the drive assisting information to the target vehicle, receiving, from the target vehicle, information of the infrastructure measured by the target vehicle, and inspecting the infrastructure using the information of the infrastructure.

Abstract: A method of assessing concentration of analyte ion(s) in a liquid can include contacting the liquid with a plurality of electrodes, each of which is configured to generate a signal in response to sensing a selected ion in the liquid. The signal received from each of the electrodes can be processed using a neural network algorithm trained to calculate ion interference between the selected ion and other ions in the liquid sensed at one of the electrodes and/or electrode interference between ones of the electrodes sensing a same selected ion based on a result of a comparison of training data. The ion interference and/or electrode interference can be compensated for, and the concentration of the analyte ion(s) in the liquid can be assessed on the basis of a compensated output from the neural network algorithm.

Abstract: Methods and systems for accurately locating buried defects previously detected by an inspection system are described herein. A physical mark is made on the surface of a wafer near a buried defect detected by an inspection system. In addition, the inspection system accurately measures the distance between the detected defect and the physical mark in at least two dimensions. The wafer, an indication of the nominal location of the mark, and an indication of the distance between the detected defect and the mark are transferred to a material removal tool. The material removal tool (e.g., a focused ion beam (FIB) machining tool) removes material from the surface of the wafer above the buried defect until the buried defect is made visible to an electron-beam based measurement system. The electron-beam based measurement system is subsequently employed to further analyze the defect.

Abstract: Provided are a plant management system and a plant management method, which do not entail a substantial workload, cost, construction period, or installation space; enable a system to be easily constructed, altered and expanded; have a small maintenance load; enable processing systems to be distributed and arranged in geographically separate locations and in locations where connecting the processing systems is not easy; and are capable of preventing the occurrence of large-scale problems. A plant management system 100 has: a plurality of processing systems 140, 150; and memory tags 112, 122, wherein processing systems 140, 150 include reader-writers 142, 152, 153 and processing devices 141, 151, and, by writing plant management data into the memory tag 112 by means of the reader-writer 142 and then reading the plant management data by the reader-writer 152 of the processing system 150, the plant management data is transferred between the processing systems 140, 150.

Abstract: The system comprises a controller comprising software components for determining the difference between the amount of energy determined by the smart grid agent to be delivered to and from the cluster over a predetermined period of time and the amount of energy measured by the meter actually delivered to the cluster over the predetermined period of time, the controller comprising software components for simulating a virtual smart grid participating device based on the determined difference and for providing the smart grid agent with information based on the determined difference such that the smart grid agent is configured to determine the amount of electrical energy in function of time to be delivered to and from the electrical grid for both the smart grid participating and non-participating devices of the cluster based on information of both the devices of the cluster and the smart grid and such that the difference is reduced.

Abstract: Methods and systems for generating simulated images from design information are provided. One system includes one or more computer subsystems and one or more components executed by the computer subsystem(s), which include a generative model. The generative model includes two or more encoder layers configured for determining features of design information for a specimen. The generative model also includes two or more decoder layers configured for generating one or more simulated images from the determined features. The simulated image(s) illustrate how the design information formed on the specimen appears in one or more actual images of the specimen generated by an imaging system.

Abstract: An inherent pattern image (100, 100F) of a test object (10) is recorded when the test object is illuminated with uniform illumination light, and a projection pattern image (200, 200F) is recorded when the test object is illuminated with a spatially modulated projection pattern. A planar displacement vector field (110, 110F) is calculated from the inherent pattern image, and a shape (210, 210F) is calculated from the projection pattern image. An image of the first type is recorded at time (tT), and images of the second type are recorded at times (tT?; tT+) before and after the time (tT). A representation of the test object at the test time (tT) is estimated by averaging. A spatial displacement vector field (300) is based on the calculated representation of the test object of the first image type and the representation of the test object estimated from the images of the second type.

Abstract: A control apparatus in an automaton that operates in cooperation with a peripheral device, includes: an operating time accumulator regarding the output time of a control signal to the peripheral device or the output time of an operating signal from the peripheral device as operating time and determining cumulative operating time by adding up the operating times; a time-at-inspection recorder recording the cumulative operating time when inspection is performed as the cumulative operating time at inspection; a cumulative operating time comparator comparing the difference between the current cumulative operating time and the cumulative operating time at inspection, the cumulative operating time from the latest inspection, or the cumulative operating time after inspection, with a preset inspection interval; and, a maintenance request output unit outputting a maintenance request to the outside when the cumulative operating time after inspection obtained as a result of the comparison exceeds the preset inspection i

Abstract: A method and apparatus for managing a configuration of a vehicle structure. Data sets are compared each representing the configuration of the vehicle structure at different phases in a lifecycle of the vehicle structure. Each of the data sets includes identifications of components for the vehicle structure. Differences are identified between the identifications of the components in the data sets.

Abstract: Systems and methods of the disclosed subject matter provide to detect the signature of a light source through either electrical signature on a circuit or external light signatures output by the light source, and a switch can change modes and features to match the capabilities of the connected light source. Embodiments of the disclosed subject matter provide a light source, a sensor to determine a type of the light source, and a switch, including a processor, to determine a set of operations according to the determined type of light source, and to control the light source to perform a selected operation from the determined set of operations.

Abstract: A sensor for indirect estimation of breast milk intake by an infant, the sensor comprising: a housing configured to be externally attached to an incontinence product worn by a subject, said housing comprising: a light-emitting diode (LED) configured to illuminate the incontinence product; a photodetector configured to output an indication of the amount of light reflected from the incontinence product; and an integrated circuit configured to: (a) receive the indication from said photodetector, (b) compute, based on the indication, an amount of urine secreted by the subject into the incontinence product, and (c) estimate the amount of breast milk intake by the infant based on the amount of urine secreted by the subject into the incontinence product.

Abstract: According to some aspects, a system and method for processing messages in a plurality of successive cycles is provided. One such system may include a plurality of first circuits, each first circuit configured to output a message, the plurality of first circuits configured to operate synchronously, a first plurality of buffers, each buffer associated with a respective first circuit and configured to store a message output by the respective first circuit, a communication path configured to receive the plurality of messages from the buffers and to perform aggregation of the messages, thereby generating an aggregated indication, and one or more second circuits. The one or more second circuits are configured to operate synchronously and to receive the aggregated indication, wherein buffers of the first plurality of buffers are configured to store messages from respective first circuits for different times.

Abstract: A method implemented by at least one processor includes receiving a plurality of operating parameters of a pumping system, wherein the pumping system has a plurality of pump-units powered by a generator-unit. The operating parameters include a pump-unit parameter and a generator-unit parameter. The method also includes receiving reference data of the pumping system, wherein the reference data includes measurements from the pumping system representative of performance of the plurality of pump-units. The method also includes determining one or more health parameters corresponding to one or more pump-units based on the plurality of operating parameters and the reference data. The method further includes modifying one or more input parameters of the generator-unit based on the one or more health parameters for continued operation of the pumping system.

Abstract: The present application relates to set top boxes and relates to the inclusion of a diagnostic function in the set top box which may be activated remotely or respond internally to the detection of faults or changes in status. The diagnostic function may emulate key presses from an infrared remote control to perform a test.

Abstract: A muon tracker includes a drift tube detector having a plurality of drift tube arrays, a detection time-difference calculation circuit configured to calculate a detected time-difference between a plurality of time data detected at least two of the drift tubes, a time-difference information database that stores a relationship between a plurality of predetermined tracks of the muon passing the drift tube detector and a predetermined time-difference of possible detected time data to be detected at least two of the drift tubes where each of the plurality of predetermined tracks passes, a time-difference referring circuit configured to refer the detected time-difference calculated at the detection time-difference calculation circuit with the predetermined time-difference stored in the time-difference information database, and a muon track determining circuit configured to determine a muon track as the predetermined track of the muon corresponding to the predetermined time-difference that matches the best with the

Abstract: A method for generating a color mapping for a printing apparatus is described. The printing apparatus includes a plurality of colorants including a first colorant configured to reflect radiation having a first set of wavelengths and a second colorant configured to absorb radiation having a second set of wavelengths and emit radiation having a third set of wavelengths. The method includes obtaining spectral characteristics for the plurality of colorants, computing a gamut of colors available to the printing apparatus and determining a color mapping from an input color space to an output color space.

Abstract: A monitoring device is for a block of building material. The monitoring device may include an electric supply line configured to be buried in the block of building material and having a flexible main cable, and flexible jumper cables coupled to the flexible main cable and extending outwardly. The monitoring device may include sensor devices configured to be buried in the block of building material and coupled to respective ones of the flexible jumper cables. Each sensor device may include a primary inductor coupled to the electric supply line at a position based upon peaks of a stationary waveform when the electric supply line is alternating current (AC) powered, and a monitoring circuit. The monitoring circuit may include an integrated sensor, and a secondary inductor magnetically coupled to the primary inductor and configured to supply the integrated sensor, and communicate through the electric supply line.

Abstract: A method and system are presented for use in inspection of via containing structures. According to this technique, measured data indicative of a spectral response of a via-containing region of a structure under measurements is processed, and, upon identifying a change in at least one parameter of the spectral response with respect to a spectral signature of the via-containing region, output data is generated indicative of a possible defect at an inner surface of the via.

Abstract: In one embodiment, a system including a memory and processor is provided. The memory stores a plurality of quality rules and control rules. The processor receives a request comprising a plurality of parameters and data elements. The processor determines that the request is missing a first data element and that a second data element of the plurality of data elements is corrupt. The processor determines that a first number of data elements should have been communicated and a third number of data elements should have been processed. The processor determines that a second number of data elements were communicated and a fourth number of data elements were processed. The processor generates a report indicating that: the plurality of parameters is missing the first data element, the second data element is corrupt, the first number is less than the second number, and the fourth number is less than the third number.

Abstract: Building and maintaining an accurate and up-to-date global inventory of hardware, software, and telecommunications assets deployed throughout an organization is described. A global inventory warehouse (GIW) receives an identification and physical location of these assets from multiple source systems. Some of these source systems contain information pertaining to the assets that has been manually entered into the source system by a human administrator. Other source systems, meanwhile, contain information that has been automatically collected by the source systems without human intervention. The GIW receives this information from the source systems and stores it within a GIW database. The GIW database may thus contain a global inventory of all or nearly all of the hardware, software, and telecommunications assets distributed throughout the organization. This database may also contain an identification of physical locations within the organization of all or substantially all of these assets.

Abstract: Methods, systems, and computer program products for determining severity of a geomagnetic disturbance on a power grid using similarity measures are provided herein. A method includes extracting multiple features of activity associated with geomagnetically induced currents from multiple heterogeneous data streams; comparing the extracted features to historical data related to geomagnetically induced currents to determine a level of similarity between each of the extracted features and the historical data; assigning a level of severity to one or more of the extracted features having a level of similarity with the historical data above a given threshold; and generating a notification comprising (i) a prediction of activity associated with geomagnetically induced currents based on the extracted features having a level of similarity with the historical data above the given threshold, and (ii) the level of severity assigned thereto.

Abstract: Metrology may be implemented during semiconductor device fabrication by a) modeling a first measurement on a first test cell formed in a layer of a partially fabricated device; b) performing a second measurement on a second test cell in the layer; c) feeding information from the second measurement into the modeling of the first measurement; and after a lithography pattern has been formed on the layer including the first and second test cells, d) modeling a third and a fourth measurement on the first and second test cells respectively using information from a) and b) respectively.

Abstract: Described is a method and system for measuring parameters of a structure on a substrate, such as a via or a through-silicon via (TSV) using an imaging X-ray metrology system. A previously-trained Support Vector Machine (SVM) model is used to extract structure parameters from the acquired structure X-ray images. Training of the Support Vector Machine (SVM) model is accomplished by using a library of actual or simulated X-ray images, or a combination of the two image types, paired with structure parameter sets.