Abstract: To predict a failure condition in a power module of a vehicle, it is determined whether a discontinuity in statistical data characterizing physical measurements of the power module meets a threshold criterion. Responsive to the discontinuity meeting the threshold criterion, a data offset in the physical measurements is computed at the discontinuity. A shift correction is applied to the physical measurements in accordance with the computed data offset responsive to a determination that the discontinuity is attributable to a restart of the power module. Other statistical data characterizing the shift-corrected physical measurements are computed and the statistical data and the other statistical data are provided to a machine learning processor that predicts the failure condition in the power module.

Abstract: A system and method for statistical fingerprinting of structured datasets begins by dividing the structured database into groups of data subsets. These subsets are created based on the structure of the data; for example, data delineated by columns and rows may be broken into subsets by designating each column as a subset. A fingerprint is derived from each subset, and then the fingerprint for each subset is combined in order to create an overall fingerprint for the dataset. By applying this process to a “wild file” of unknown provenance, and comparing the result to a data owner's files, it may be determined if data in the wild file was wrongfully acquired from the data owner.

Abstract: Systems and methods for determining aircraft component phase position are provided. In one embodiment, a method can include receiving a set of data from a data acquisition system associated with a component. The method can include identifying a plurality of phase reference points based, at least in part, on the set of data. Each phase reference point can be indicative of a phase position of the component relative to the data acquisition system at a respective point in time. The method can include generating a model based, at least in part, on the plurality of phase reference points. The model can be indicative of the phase position of the component relative to the data acquisition system at a plurality of times. The method can include determining the phase position of the component at one or more points in time based, at least in part, on the model.

Abstract: Evaluating dose performance of a radiographic imaging system with respect to image quality using a phantom, a channelized hotelling observer module as a model observer, and a printer, a plaque, or an electronic display includes scanning and producing images for a plurality of sections of the phantom using the radiographic imaging system, wherein the plurality of sections represent a range of patient sizes and doses and wherein the sections of the phantom contain objects of measurable detectability. Also included is analyzing the images to determine detectability results for one or more of the contained objects within the images of the plurality of sections of the phantom, wherein the analyzing includes using a channelized hotelling observer (CHO) module as a model observer; and displaying, via the printer, the plaque, or the electronic display, a continuous detectability performance measurement function using the determined detectability results.

Abstract: An intelligent identification method for a vibration characteristic of rotating machinery, the steps providing converting a speed or acceleration time domain signal of mechanical vibration to a frequency domain envelope spectrum by signal processing, extracting a frequency upper limit value fmax of the envelope spectrum; at least screening out a high energy harmonic with a frequency range within fmax/Nmax by amplitude comparison. Nmax is a frequency multiple upper limit multiple for performing a frequency multiple check on the high energy harmonic. Then, extracting at least one set of characteristic parameters, based on respective amplitudes and/or frequencies, of 1-fold to Nmax-fold frequency region peaks of each high energy harmonic. The 1-fold frequency region peak of the high energy harmonic is the high energy harmonic itself. Finally, inputting the at least one set of characteristic parameters of each high energy harmonic into a machine learning intelligent algorithm to perform training and calculation.

Abstract: A method of controlling an operation of a mechanical transmission system includes receiving motor-load data corresponding to the mechanical transmission system. The method further includes receiving, by a digital motor unit, one or more motor input parameters and generating motor parameter estimates of one or more of the plurality of motor parameters. The method also includes receiving, by a digital load unit, one or more motor parameter estimates from the digital motor unit and generating load parameter estimates corresponding to one or more load parameters. The digital motor unit and the digital load unit is a real-time operational model of the motor unit and the load unit respectively. The method also includes controlling the operation of the mechanical transmission system based on one or more of the motor-load data, motor parameter estimates and load parameter estimates.

Abstract: An apparatus, methods and systems for collecting data related to an industrial environment are disclosed. A monitoring system can include a data collector communicatively coupled to a plurality of input channels relating to an aspect of an industrial production process, a data storage structured to store a plurality of detection values, a data analysis circuit structured to interpret a subset of the detection values to determine a state value comprising at least one of a process state or a component state, an optimization circuit structured to analyze a subset of the detection values and the state value, using at least one of a neural net or an expert system, to provide an adjustment recommendation, and an analysis response circuit structured to adjust the industrial production process in response to the adjustment recommendation.

Abstract: Example systems may relate to component failure prediction. A non-transitory computer readable medium may contain instructions to analyze a plurality of features corresponding to a component of a system. The non-transitory computer readable medium may further contain instructions to determine which of the plurality of features to use to model a failure of the component. The non-transitory computer readable medium may contain instructions to generate a plurality of models to model the failure of the component and assemble the plurality of models into a single model for predicting component failure. The non-transitory computer readable medium may further contain instructions to extract data associated with a component failure predicted by the single model and correlate the data associated with the predicted component failure with the single model.

Abstract: A technique includes, for each storage drive of a plurality of storage drives, determining a metric associated with the storage drive based at least in part on a plurality of attributes associated with the storage drive; and determining a health of a given storage drive of the plurality of storage drives based at least in part on the metric associated with the given storage drive and the metric associated with at least one other storage drive of the plurality of storage drives.

Abstract: The invention provides for a magnetic resonance imaging system (100) comprising a memory (134) for storing machine executable instructions (140) and pulse sequence commands (142). The pulse sequence commands are configured for controlling the magnetic resonance imaging system according to a DCE Magnetic Resonance Imaging protocol. The magnetic resonance imaging system further comprises a user interface (200) and a processor (130) for controlling the magnetic resonance imaging system.

Abstract: Techniques are described for generating prediction metrics that describe one or more predicted characteristics and/or outcomes of a software development project. Implementations employ machine learning (ML) algorithms to develop prediction models to predict characteristics of a project. For example, the models can be employed to predict a number of defects that may be present in a software product that is produced by a software development project. A model can be trained using input data captured from previous software projects, such as data describing the feature set of a software product, the timeline for its development, the particular type or domain of software, a number of modules, functions, etc., the particular number and/or identity of personnel working on the project, and so forth. Such input data can be analyzed to extract features that are provided as training data to train a model that is used to predict project metrics.

Abstract: A method, a client, and a system for testing an application. A webpage file includes codes for simulating a malicious attack. The method includes providing, by the test client, a network address of the webpage file to the tested application, wherein when the tested application loads the webpage file according to the network address, the tested application executes the codes comprised in the webpage file to attempt to read content of a private file in a private directory of the tested application. When the tested application successfully reads the content of the private file, the tested application transmits a message carrying the content of the private file to a test server through a local terminal device, wherein the test server determines whether the tested application has a security loophole according to the message transmitted by the tested application.

Abstract: A computer-implemented method includes: detecting, by a computing device, a failure event for a primary data collection device that is currently collecting and providing data; discontinuing, by the computing device, use of the primary data collection device based on the detecting the failure event; selecting, by the computing device, an alternate data collection device based on the discontinuing the use of the primary data collection device; receiving, by the computing device, data collected by the alternate data collection device; receiving, by the computing device, failure related data associated with the primary data collection device after discontinuing use of the primary data collection device; and updating, by the computing device, a hazard function based on the failure related data, wherein the hazard function is used to detect future failures of a same type of primary data collection device.

Abstract: A method and apparatus for generating a fault tree for a failure mode of a complex system including a plurality of components, the method includes the steps of providing component fault tree, CFT, elements of the components; linking the components according to their failure dependencies within the complex system; and generating the fault tree by incorporating for each dependency link from a first component to a second component the output failure modes of the component fault tree element of the second component into the component fault tree element of the first component to trigger the output failure modes of the first component.

Abstract: A system for providing a targeted recall includes a metrology sub-system for performing in-line measurements on semiconductor dies after one or more fabrication steps to generate in-line measurement profiles, a failure analysis sub-system for determining a manufacturing fingerprint of a failed die, and a controller. The metrology sub-system may further perform one or more measurements of the semiconductor dies after one or more packaging steps to generate package characterization profiles. The controller may generate manufacturing fingerprints for the semiconductor dies based on the in-line measurement profiles and the package characterization profiles, which are referenced to unique electronic chip identifiers. The controller may further identify at-risk dies by comparing the manufacturing fingerprints of the semiconductor dies with the manufacturing fingerprint of the failed die and direct a targeted recall for the one or more at-risk dies.

Abstract: Machine learning based methods for vehicle maintenance are disclosed. In one aspect, there is a method that includes uploading a flight dataset. The flight dataset includes timestamped vectors of kinematic and behavioral sensor data elements acquired by on-board sensors. The method further includes assigning each timestamped vector of the flight dataset to a kinematic cluster. The method further includes identifying behavioral sensor data that is anomalous for the assigned kinematic cluster of the timestamped vector. The method further includes generating an alert criticality score for each combination of kinematic cluster and behavioral sensor with anomalous sensor data.

Abstract: Provided are a failure classifying device, a failure classifying method, and a failure classifying program capable of specifying the causes of failures even when a controller does not generate an alarm. A failure classifying device includes: a failure unit acquiring unit that acquires a data set in which a failure unit of a machine is correlated with one or a plurality of constituent parts; a failure history acquiring unit that acquires a failure history including events of failures that occurred in the past and countermeasure parts; and a correlating unit that stores information on one or a plurality of events in correlation with the failure unit by matching the constituent part to the countermeasure part.

Abstract: A similarity between a pattern distribution of selected state patterns of system state descriptions in a first set of system state descriptions and an average pattern distribution of the selected state patterns of the system state descriptions in a second set of system state description is determined. The similarity is compared with a plurality of such similarities between the pattern distributions within the second set of system state descriptions and the average pattern distribution in the second set of system state descriptions. An abnormal state of the system is determined using this comparison.

Abstract: Systems and methods for detecting and scoring anomalies. In some embodiments, a method is provided, comprising acts of: (A) identifying a plurality of values of an attribute, each value of the plurality of values corresponding respectively to a digital interaction of the plurality of digital interactions; (B) dividing the plurality of values into a plurality of buckets; (C) for at least one bucket of the plurality of buckets, determining a count of values from the plurality of values that fall within the at least one bucket; (D) comparing the count of values from the plurality of values that fall within the at least one bucket against historical information regarding the attribute; and (E) determining whether the attribute is anomalous based as least in part on a result of the act (D).

Abstract: Technologies are disclosed for identifying and remediating correctable hardware errors. A firmware can detect a system management interrupt (“SMI”) generated by a hardware device responsive to the occurrence of a correctable error. Once the firmware has identified the device that generated the SMI, the firmware can determine whether an earliest recorded error generated by the identified device is longer ago than a threshold amount of time. If the earliest recorded error generated by the device is not longer ago than the threshold amount of time, the firmware can increment an error count for the device. The firmware can also determine whether the error count for the device exceeds a threshold. If the error count for the device exceeds the threshold, the firmware can generate an error notification for the device. The firmware can also implement a remedial action policy for the device.

Abstract: A method is provided for analyzing failure rates due to soft/hard errors in the design of a digital electronic device. The method includes creating an error injection point by introducing a fault into a code path having a plurality of levels; determining an error detection point at which the introduced fault becomes detectable; creating a list of all of the logic cells forming the cone of logic that forms the data input to the error detection point, thereby generating a first logic cone list; creating a list of all of the logic cells forming the cone of logic that forms the data input to the error injection point, thereby generating a second logic cone list; determining the intersection between the first and second logic cone lists; and conducting a failure rate analysis on the intersection between the first and second logic cone lists.

Abstract: An electronic component includes a member with marking having at least one marking area to be processed digitally, as well as a member other than the member with marking. The marking allows for tracing the production history of individual electronic components.

Abstract: The disclosed embodiments include a method performed by a computer system. The method includes receiving first user input defining a filter of an anomaly action rule, the filter defining at least one of an attribute of an anomaly or an attribute of a computer network entity. The method also includes receiving second user input defining an action of the anomaly action rule. The method further includes generating the anomaly action rule based on the first user input and the second user input, wherein the anomaly action rule causes performance of the action upon detecting an anomaly on the computer network that satisfies the anomaly action rule.

Abstract: Provided is a failure prediction method using a failure prediction apparatus, including: receiving time-series data about measured performance parameters from a device under test; encoding the time-series data with a plurality of symbols corresponding to a predetermined range; calculating a transition probabilities between the symbols of the encoded time-series data, and generating a transition matrix according to the transition probabilities; calculating an abnormal indicator, which is a difference between the transition matrix and a pre-stored database, and an increased value of the abnormal indicator; and comparing the increased value of the abnormal indicator and a predetermined threshold value, and if the increased value of the abnormal indicator is greater than the predetermined threshold value, predicting that failure of the device under test is to occur.

Abstract: Methods for providing the capability to resample computer system metrics, while providing improved accuracy over conventional techniques. The system and method conducts monitoring and measuring metrics of system resource consumption of a plurality of entities to generate resource consumption data, generating a report of the resource consumption data for the plurality of entities for each of a plurality of time periods, identifying a number, k, of the plurality of entities as top-k consumers of resources for each of the plurality of time periods, identifying at least one residual entity of the plurality of entities whose resource consumption is not included in the top-k entities based on residual resource consumption data of the entity, and resampling the reports of the resource consumption data corresponding to the top-k entities and to the at least one residual entity to form at least one report covering a time period.

Abstract: A system is disclosed, comprising a data processing device configured to receive an image of a pattern from an imaging system, calculate a bit sequence based on the pattern, and compare the bit sequence to a true bit sequence to generate an evaluation of the imaging system; and an output device configured to output the evaluation. An exemplary pattern comprises a first plurality of shapes having a first spectral characteristic and a second plurality of shapes having a second spectral characteristic, the plurality of first shapes and the plurality of second shapes being arranged in a pattern that is self-similar at different scales.

Abstract: Techniques facilitating determination and correction of physical circuit event related errors of a hardware design are provided. A system can comprise a memory that stores computer executable components and a processor that executes computer executable components stored in the memory. The computer executable components can comprise a simulation component that injects a fault into a latch and a combination of logic of an emulated hardware design. The fault can be a biased fault injection that can mimic an error caused by a physical circuit event error vulnerability. The computer executable components can also comprise an observation component that determines one or more paths of the emulated hardware design that are vulnerable to physical circuit event related errors based on the biased fault injection.

Abstract: Failing test pattern simulations are performed to determine initial defect suspects based on injecting faults to defect candidate sites which are derived based on test responses. Initial inter-cell bridge suspects are then determined from cells in the initial defect suspects based on layout information and electrical information of the circuit. Passing test pattern simulations are performed to determine inter-cell bridge suspects from the initial inter-cell bridge suspects.

Abstract: Analyzing communication network data set access of a data set group constituted by multiple data sets. The method includes the following steps: (i) determining, for a first interval, a first low access count value corresponding to an amount of data sets in the data set group that have been accessed, in the first interval, an amount of times that is no greater than a low access threshold value; (ii) determining, for a second interval, a second low access count value corresponding to an amount of data sets in the data set group that have been accessed, in the second interval, an amount of times that is no greater than the low access threshold value; and (iii) determining a delta value based, at least in part, on a difference between the first low access count value and the second low access count value.

Abstract: Disclosed herein are methods, systems, and processes for burn process data retrieval and notification. A burn process that is ongoing and that is initiated to generate burn data associated with a testing computing device is detected at a computing device. A determination is made that the burn data has been generated by the testing computing device as part of the burn process. The burn data associated with the burn process generated by the testing computing device is then retrieved.

Abstract: A first set of values for a set of metrics is obtained. A given metric of the set of metrics monitors a given component of a set of components of a computing system. The first set of values is obtained during a period of expected behavior of the computing system. One or more correlations are determined between values of the first set of values to establish one or more expected correlations between values of two or more metrics. A second set of values for the set of metrics is obtained. A determination is made as to whether values of the second set of values maintain the one or more expected correlations determined based on the first set of values.

Abstract: The present disclosure describes a new method to virtualize a plant facility with remote sites that are separated from a central site. The method includes: assembling, by a server computer located at the central site of the plant facility, an engineering package addressed to a particular remote site of the plant facility, the administrative package comprising a command script and a data component; and dispatching, by the server computer located at the central site of the plant facility and through a transport network of one or more transport vehicles, the engineering package to the particular remote site such that, when the engineering package arrives with a particular transport vehicle at the particular remote site, the command script is extracted and executed to perform control systems management and engineering tasks at the particular remote site for routine maintenance as if a human control system engineer is present to perform such systems management and engineering tasks on-site.

Abstract: An audio processing system is provided with a speaker, a plurality of microphones, and an audio processing device. The audio processing device includes a plurality of filters that allow audio signals of audio collected by the plurality of microphones to pass any respective first bands included in a band of the audio output from the speaker, a plurality of delayers that delay the audio signals passed through the plurality of filters by delay times corresponding to the first bands respectively, a correlation value calculator that calculates a correlation value of a plurality of audio signals delayed respectively by the plurality of delayers and an audio signal of the audio output from the speaker, and a determinator that determines presence or absence of abnormality in the plurality of microphones and the speaker based on the correlation value.

Abstract: A system of identifying a payload destination, the system including: one or more sensors; and an identifying module configured to: receive a plurality of inputs from the one or more sensors, the plurality of inputs being associated with payload delivery from a lifting machine; define a plurality of input destination identifiers based on the plurality of inputs; compare the plurality of input destination identifiers with stored identifiers in order to establish one or more destination match estimates; and identify the payload destination based on the one or more destination match estimates.

Abstract: A method and system for recognizing (and/or predicting) failures of sensors used in monitoring gas turbines applies a sparse coding process to collected sensor readings and defines the L-1 norm residuals from the sparse coding process as indicative of a potential sensor problem. Further evaluation of the group of residual sensor readings is perform to categorize the group and determine if there are significant outliers (“abnormal data”), which would be considered as more likely associated with a faulty sensor than noisy data. A time component is introduced into the evaluation that compares a current abnormal result with a set of prior results and making the faulty sensor determination if a significant number of prior readings also have an abnormal value. By taking the time component into consideration, the number of false positives is reduced.

Abstract: A hybrid-fabric apparatus comprises a black box memory configured to store a plurality of behavior metrics and an anomaly agent coupled to the black box. The anomaly agent determines a baseline vector corresponding to nominal behavior of the fabric, wherein the baseline vector comprises at least two different behavior metrics that are correlated with each other. The anomaly agent disaggregates anomaly detection criteria into a plurality of anomaly criterion to be distributed among network nodes in the fabric.

Abstract: A method and apparatus is presented. The apparatus comprises a parts library configured to store a plurality of part definition files; a database configured to store entries identifying a printing of parts using the plurality of part definition files; and a parts management system configured to request a payment in response to receiving an indication of a printing of a part using the part definition file.

Abstract: Computer log entries are processed to determine a plurality of baseline rank values associated with a ranking dimension. An overall baseline rank indicator is computed using the determined baseline rank values. For each log data component value combination included in a group of log data component value combinations, a comparison rank value associated with the ranking dimension is determined. Each of the comparison rank values is compared with the overall baseline rank indicator. Based at least in part on the comparisons, one or more log data component value combinations included in the group of log data component value combinations are identified as more anomalous than other log data component value combinations included in the group of log data component value combinations.

Abstract: A method is provided for clustering events. Messages are received at an extraction engine from managed infrastructure that includes managed infrastructure physical hardware that supports the flow and processing of information. Events are produced that relate to the managed infrastructure. The events are converted into words and subsets used to group the events that relate to failures or errors in the managed infrastructure, including the managed infrastructure physical hardware. One or more common characteristics of events are determined and clusters of events are produced relating to the failure or errors in the managed infrastructure. A source address is used for each event as is a graph topology of the managed infrastructure to assign a graph coordinate to the event. Membership in a cluster indicates a common factor of the events that is a failure or an actionable problem in the physical hardware managed infrastructure directed to supporting the flow and processing of information.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for storing and accessing data in a cloud system. One of the methods includes receiving an identification of log data that records occurrences of events; receiving a specification of a plurality of different event types to be indexed; indexing the log data according to the specification and group identifiers; receiving a query specifying a reference parameter and requesting one or more predicted events; searching the indexed groups to identify a plurality of groups having events associated with the reference parameter; computing one or more predicted events, from the identified plurality of groups, that are most likely to co-occur in the indexed groups with events associated with the reference parameter; and providing the computed one or more predicted events.

Abstract: A variable indication estimator which determines an output value representative of a set of input data. For example, the estimator can reduce input data to estimates of a desired signal, select a time, and determine an output value from the estimates and the time. In one embodiment, the time is selected using one or more adjustable signal confidence parameters determine where along the estimates the output value will be computed. By varying the parameters, the characteristics of the output value are variable. For example, when input signal confidence is low, the parameters are adjusted so that the output value is a smoothed representation of the input signal. When input signal confidence is high, the parameters are adjusted so that the output value has a faster and more accurate response to the input signal.

Abstract: A system, device, and method of deviation detection in at least one sensor dataset associated with one or more sensors in a technical system are provided. The method includes generating a best fit model of the technical system based on a target sensor dataset. The method also includes predicting a sensor dataset of the target sensor using the best fit model and non-target sensor datasets of non-target sensors, and determining a deviation tolerance by determining a difference between the predicted sensor dataset and the target sensor dataset. The method also includes detecting deviation in actual sensor dataset of the target sensor when a data-point in the actual sensor dataset exceeds the deviation tolerance and detecting deviation in the at least one sensor dataset of the one or more sensors by detecting deviation in each of the non-target sensor datasets.

Abstract: Detecting anomalous user behavior is provided. User activity is logged for a set of users. The user activity is divided into distinct time intervals. For each distinct time interval, logged user activity is converted to a numerical representation of each user's activities for that distinct time interval. A clustering process is used on the numerical representations of user activities to determine which users have similar activity patterns in each distinct time interval. A plurality of peer groups of users is generated based on determining the similar activity patterns in each distinct time interval. Anomalous user behavior is detected based on a user activity change in a respective peer group of users within a distinct time interval.

Abstract: A system and method for monitoring performance of an HVAC unit by receiving outdoor temperature data from an outdoor temperature source and indoor temperature data from an indoor temperature source, tracking performance data of the HVAC unit based at least in part on the outdoor temperature data and the indoor temperature data, receiving power consumption data from the power measuring device, tracking the power consumption data based at least in part on the outdoor temperature data, determining whether there is a change in the performance data and the power consumption data, and generating a fault signal based at least in part on the change in the performance data and the power consumption data.

Abstract: Computerized characterization of cardiac wall motion is provided. Quantities for cardiac wall motion are determined from a four-dimensional (i.e., 3D+time) sequence of ultrasound data. A processor automatically processes the volume data to locate the cardiac wall through the sequence and calculate the quantity from the cardiac wall position or motion. Various machine learning is used for locating and tracking the cardiac wall, such as using a motion prior learned from training data for initially locating the cardiac wall and the motion prior, speckle tracking, boundary detection, and mass conservation cues for tracking with another machine learned classifier. Where the sequence extends over multiple cycles, the cycles are automatically divided for independent tracking of the cardiac wall. The cardiac wall from one cycle may be used to propagate to another cycle for initializing the tracking. Independent tracking in each cycle may reduce or avoid inaccuracies due to drift.

Abstract: A management system includes an interface board configured to provide bi-directional communication between a networking device and one or more devices, wherein the interface board is coupled to the networking device and connects to one or more devices via one or more communication protocols supported by one or more devices. The management system further includes a management module connected to the interface board with the management module configured to receive, from the interface board, data packets generated by the one or more devices, and transmit the data packets to a remote server.

Abstract: In an example, a submission of a confidential data value of a first confidential data type is received from a first user with one or more attributes. A plurality of previously submitted confidential data values of a first confidential data type for a cohort matching the one or more attributes of the first user are retrieved. Then, one or more intermediate cohorts are derived by generalizing each of the one or more attributes of the cohort up at least one level in a different taxonomy corresponding to each of the one or more attributes. One or more of the intermediate cohorts are selected, and a parameterized distribution is fitted to the previously submitted confidential data values that are contained within the selected one or more of the intermediate cohorts, outputting one or more estimated parameters for each of the selected one or more of the intermediate cohorts. A lower limit for the first confidential data type is then set based on the one or more estimated parameters.

Abstract: Various aspects of the disclosed technology relate to circuit defect diagnosis based on sink cell fault models. Defect candidates are determined based on path-tracing from failing bits into the circuit design. Based on the defect candidates and one or more conventional fault models, failing test pattern simulations are performed to determine initial defect suspects. Initial defective sink cell suspects are then determined by comparing driving strengths for fan-out cells of the initial defect suspects with driving strengths for corresponding driver cells. Defective sink cell suspects may be identified in the initial defective sink cell suspects based on fault effect propagations and passing test pattern simulations.

Abstract: The invention pertains to a method and information handling system (IHS) for predicting storage device failures. An embodiment of the method of the present invention begins by obtaining data regarding input and output of the at least one storage device. Next, the obtained data is normalized to determine a duty cycle of the at least one storage device. Finally, using the normalized data, a likelihood of failure of the at least one storage device is determined. In another example embodiment, a failure indicator is associated with the at least one storage device based upon the determined likelihood of failure.

Abstract: Estimating residual useful life of a rolling element bearing in an operating gas turbine engine is provided. A processor receives a vibration signal from a vibration sensor. The vibration signal includes a vibratory response of the rolling element bearing. Processor detects a vibratory pattern of the rolling element bearing from the vibration signal and compares the vibratory pattern to a reference vibratory pattern. Processor identifies a failure propagation stage in which the vibratory pattern matches the reference vibratory pattern. Processor correlates the failure propagation stage to the residual useful life remaining in the rolling element bearing and generates an output signal representing the residual useful life remaining in the rolling element bearing.