A method implemented by a software for a multimodal evaluation engine stored on a memory is provided herein. The software is executable by a processor coupled to the memory to cause the method. The method includes receiving multimodal signatures of an object of interest from inspection elements and processing the multimodal signatures to transform the multimodal signatures into formats. The method also includes generating data representations of the formats and detecting whether anomalies are present within the object of interest based on the data representations.

Systems and methods for determining location of critical dimension (CD) measurement or inspection are disclosed. Real-time selection of locations to take critical dimension measurements based on potential impact of critical dimension variations at the locations can be performed. The design of a semiconductor device also can be used to predict locations that may be impacted by critical dimension variations. Based on an ordered location list, which can include ranking or criticality, critical dimension can be measured at selected locations. Results can be used to refine a critical dimension location prediction model.

There is provided an analysis apparatus including: an acquisition unit configured to acquire a plurality of measured values obtained by measuring a device under measurement; a machine learning unit configured to use the plurality of measured values to learn, by machine learning, a model of a position-dependent component that depends on a measured position in the device under measurement; and an analysis unit configured to separate, from the plurality of measured values, the position-dependent component which is calculated by using the model learned by the machine learning unit. Further, there is provided an analysis method. Further, there is provided a recording medium having recorded thereon an analysis program.

In order to analyze a plurality of measured values obtained by measuring a device under measurement and to effectively use the analyzed information, there is provided a recording medium having recorded thereon an analysis apparatus, the analysis apparatus including: an acquisition unit configured to acquire the plurality of measured values obtained by measuring the device under measurement via a jig; an analysis unit configured to analyze the plurality of measured values to calculate variation data which indicates a variation of a measured value in accordance with the number of times of contacts that the jig comes into contact with the device under measurement; and a management unit configured to manage a state of the jig based on the variation data.

There are provided a detection method and detection apparatus of an operating state of a circuit. The method includes: forming a neural network that acquires a state category of a circuit to be detected; measuring electrical characteristic parameters of at least one node in the circuit to be detected; inputting the measured electrical characteristic parameters of at least one node to the neural network, and obtaining the state category of the circuit to be detected through the neural network.

A method includes obtaining device data corresponding to a set of electronic devices, the set including a first, second, and third electronic device. The method includes grouping the set of electronic devices into a first cluster and a second cluster, wherein the first cluster includes the first and second electronic devices, and the second cluster includes the third electronic device. The method includes obtaining first signature data comprising one or more first electrical parameters of the first electronic device and second signature data comprising one or more second electrical parameters of the second electronic device. The method includes determining that a first electrical parameter of the first signature data matches a second electrical parameter of the second signature data. The method includes regrouping the set of electronic devices such that the first cluster includes the first electronic device and the second cluster includes the second and third electronic devices.

A technique for non-invasively assessing current drawn by a device under test (DUT) by monitoring a supply voltage to the DUT. Frequency data for the DUT may be generated and used to form a current estimation model. First and second voltages are simultaneously measured using first and second test probes electrically connected to the DUT, while the first test probe is connected at a current source, and while the second test probe is connected at a DUT load that is configured to draw current from the current source. The current drawn by the DUT is then assessed by applying the current estimation model to the measured first and second voltages. In one case, the current drawn by the DUT is estimated without insertion of a circuit component into the DUT or extraction of a circuit conductor from the DUT.

A system and method are provided for testing features of an embedded system. The system includes a low-powered computing device communicatively coupled to a control application interface, a sensor interface, and a robotic interface. The low-powered computing device may receive sensor signals generated during a test, provide sensor data corresponding to the sensor signals, receive commands for the test, and provide instructions for movement of a robotic handler corresponding to at least one of the commands for the test. The system also includes a computing device communicatively coupled to the control application interface, an image processing interface, and a database interface. The computing device may receive sensor data, receive image data corresponding to images of the embedded system captured during the test, receive tests capable of being performed, and provide commands for the test.

An example method comprises receiving historical sensor data from sensors of components of wind turbines, training a set of models to predict faults for each component using the historical sensor data, each model of a set having different observation time windows and lead time windows, evaluating each model of a set using standardized metrics, comparing evaluations of each model of a set to select a model with preferred lead time and accuracy, receive current sensor data from the sensors of the components, apply the selected model(s) to the current sensor data to generate a component failure prediction, compare the component failure prediction to a threshold, and generate an alert and report based on the comparison to the threshold.

An audio and vibration based power distribution equipment condition monitoring system and method is provided. The system incudes an IAA device and a sensing assembly. The IAA device has computer executable instructions such as an audio data processing algorithms configured to identify and predict impending anomalies associated with one or more power distribution equipment using one or more neural networks.