中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

61 records (took 0.031 seconds)

    STAGGERED-SAMPLING TECHNIQUE FOR DETECTING SENSOR ANOMALIES IN A DYNAMIC UNIVARIATE TIME-SERIES SIGNAL
    56.
    发明申请
    STAGGERED-SAMPLING TECHNIQUE FOR DETECTING SENSOR ANOMALIES IN A DYNAMIC UNIVARIATE TIME-SERIES SIGNAL 有权

    公开(公告)号：US20220300737A1

    公开(公告)日：2022-09-22

    申请号：US17205445

    申请日：2021-03-18

    Applicant: Oracle International Corporation

    Inventor： Neelesh Kumar Shukla ,  Saurabh Thapliyal ,  Matthew T. Gerdes ,  Guang C. Wang ,  Kenny C. Gross

    IPC: G06K9/00 ,  G06N20/00 ,  G06N5/04 ,  G06K9/62

    Abstract: The disclosed embodiments provide a system that detects sensor anomalies in a univariate time-series signal. During a surveillance mode, the system receives the univariate time-series signal from a sensor in a monitored system. Next, the system performs a staggered-sampling operation on the univariate time-series signal to produce N sub-sampled time-series signals, wherein the staggered-sampling operation allocates consecutive samples from the univariate time-series signal to the N sub-sampled time-series signals in a round-robin ordering. The system then uses a trained inferential model to generate estimated values for the N sub-sampled time-series signals based on cross-correlations with other sub-sampled time-series signals. Next, the system performs an anomaly detection operation to detect incipient sensor anomalies in the univariate time-series signal based on differences between actual values and the estimated values for the N sub-sampled time-series signals. Whenever an incipient sensor anomaly is detected, the system generates a notification.

    MAXIMIZING THE OPERATIONAL RANGE FOR TRAINING PARAMETERS WHILE SELECTING TRAINING VECTORS FOR A MACHINE-LEARNING MODEL
    57.
    发明申请
    MAXIMIZING THE OPERATIONAL RANGE FOR TRAINING PARAMETERS WHILE SELECTING TRAINING VECTORS FOR A MACHINE-LEARNING MODEL 有权

    公开(公告)号：US20220138499A1

    公开(公告)日：2022-05-05

    申请号：US17090112

    申请日：2020-11-05

    Applicant: Oracle International Corporation

    Inventor： Guang C. Wang ,  Kenny C. Gross ,  Zexi Chen

    IPC: G06K9/62 ,  G06F11/30 ,  G06N7/00 ,  G06N5/04 ,  H04L29/06

    Abstract: The disclosed embodiments relate to a system that trains an inferential model based on selected training vectors. During operation, the system receives training data comprising observations for a set of time-series signals gathered from sensors in a monitored system during normal fault-free operation. Next, the system divides the observations into N subgroups comprising non-overlapping time windows of observations. The system then selects observations with a local minimum value and a local maximum value for all signals from each subgroup to be training vectors for the inferential model. Finally, the system trains the inferential model using the selected training vectors. Note that by selecting observations with local minimum and maximum values to be training vectors, the system maximizes an operational range for the training vectors, which reduces clipping in estimates subsequently produced by the inferential model and thereby reduces false alarms.

    USING A DOUBLE-BLIND CHALLENGE TO EVALUATE MACHINE-LEARNING-BASED PROGNOSTIC-SURVEILLANCE TECHNIQUES
    58.
    发明申请
    USING A DOUBLE-BLIND CHALLENGE TO EVALUATE MACHINE-LEARNING-BASED PROGNOSTIC-SURVEILLANCE TECHNIQUES 有权

    公开(公告)号：US20220138090A1

    公开(公告)日：2022-05-05

    申请号：US17090151

    申请日：2020-11-05

    Applicant: Oracle International Corporation

    Inventor： Rui Zhong ,  Guang C. Wang ,  Kenny C. Gross ,  Ashin George ,  Zexi Chen

    IPC: G06F11/36 ,  G06N20/00 ,  G06F21/60

    Abstract: A double-blind comparison is performed between prognostic-surveillance systems, which are located on a local system and a remote system. During operation, the local system inserts random faults into a dataset to produce a locally seeded dataset, wherein the random faults are inserted into random signals at random times with variable fault signatures. Next, the local system exchanges the locally seeded dataset with a remote system, and in return receives a remotely seeded dataset, which was produced by the remote system by inserting different random faults into the same dataset. Next, the local system uses a local prognostic-surveillance system to analyze the remotely seeded dataset to produce locally detected faults. Finally, the local system determines a performance of the local prognostic-surveillance system by comparing the locally detected faults against actual faults in the remotely seeded fault information. The remote system similarly determines a performance of a remote prognostic-surveillance system.

    Synthesizing high-fidelity signals with spikes for prognostic-surveillance applications
    59.
    发明授权
    Synthesizing high-fidelity signals with spikes for prognostic-surveillance applications 有权

    公开(公告)号：US11308404B2

    公开(公告)日：2022-04-19

    申请号：US16215345

    申请日：2018-12-10

    Applicant: Oracle International Corporation

    Inventor： Guang C. Wang ,  Kenny C. Gross

    IPC: G06N5/04 ,  G01R23/20 ,  H04L9/40 ,  H04L29/06

    Abstract: The system receives original time-series signals from sensors in a monitored system. Next, the system detects and removes spikes from the original time-series signals to produce despiked original time-series signals, which involves using the original time-series data to optimize a damping factor, which is applied to a threshold for a spike-detection technique, and using the spike-detection technique with the optimized damping factor to detect the spikes. The system then generates despiked synthetic time-series signals, which are statistically indistinguishable from the despiked original time-series signals. The system also includes synthetic spikes, which have the same temporal, amplitude and width distributions as the spikes in the original time-series signals, in the despiked synthetic time-series signals to produce synthetic time-series signals with spikes. The system uses the synthetic time-series signals with spikes to train an inferential model, and uses the inferential model to perform prognostic-surveillance operations on subsequently-received signals from the monitored system.

    Automated calibration of EMI fingerprint scanning instrumentation for utility power system counterfeit detection
    60.
    发明授权
    Automated calibration of EMI fingerprint scanning instrumentation for utility power system counterfeit detection 有权

    公开(公告)号：US11275144B2

    公开(公告)日：2022-03-15

    申请号：US16820807

    申请日：2020-03-17

    Applicant: ORACLE INTERNATIONAL CORPORATION

    Inventor： Edward R. Wetherbee ,  Andrew Lewis ,  Michael Dayringer ,  Guang C. Wang ,  Kenny C. Gross

    IPC: G01R35/00 ,  G01R29/08

    Abstract: Systems, methods, and other embodiments associated with automated calibration of electromagnetic interference (EMI) fingerprint scanning instrumentation based on radio frequencies are described. In one embodiment, a method for detecting a calibration state of an EMI fingerprint scanning device includes: collecting electromagnetic signals with the EMI fingerprint scanning device for a test period of time at a geographic location; identifying one or more peak frequency bands in the collected electromagnetic signals; comparing the one or more peak frequency bands to assigned radio station frequencies at the geographic location to determine if a match is found; and generating a calibration state signal based at least in part on the comparing to indicate whether the EMI fingerprint scanning device is calibrated or not calibrated.

Patent Agency Ranking