Patents by Inventor Alisha Deshpande
Alisha Deshpande has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11928565Abstract: Methods and systems for building and maintaining model(s) of a physical process are disclosed. One method includes receiving training data associated with a plurality of different data sources, and performing a clustering process to form one or more clusters. For each of the one or more clusters, the method includes building a data model based on the training data associated with the data sources in the cluster, automatically performing a data cleansing process on operational data based on the data model, and automatically updating the data model based on updated training data that is received as operational data. For data sources excluded from the clusters, automatic building, data cleansing, and updating of models can also be applied.Type: GrantFiled: October 24, 2022Date of Patent: March 12, 2024Assignee: Chevron U.S.A. Inc.Inventors: Yining Dong, Alisha Deshpande, Yingying Zheng, Lisa Ann Brenskelle, Si-Zhao Qin
-
Publication number: 20230252348Abstract: Methods and systems for building and maintaining model(s) of a physical process are disclosed. One method includes receiving training data associated with a plurality of different data sources, and performing a clustering process to form one or more clusters. For each of the one or more clusters, the method includes building a data model based on the training data associated with the data sources in the cluster, automatically performing a data cleansing process on operational data based on the data model, and automatically updating the data model based on updated training data that is received as operational data. For data sources excluded from the clusters, automatic building, data cleansing, and updating of models can also be applied.Type: ApplicationFiled: October 24, 2022Publication date: August 10, 2023Applicants: Chevron U.S.A. Inc., University of Southern CaliforniaInventors: Yining DONG, Alisha DESHPANDE, Yingying ZHENG, Lisa Ann BRENSKELLE, Si-Zhao QIN
-
Patent number: 11507069Abstract: Methods and systems for building and maintaining model(s) of a physical process are disclosed. One method includes receiving training data associated with a plurality of different data sources, and performing a clustering process to form one or more clusters. For each of the one or more clusters, the method includes building a data model based on the training data associated with the data sources in the cluster, automatically performing a data cleansing process on operational data based on the data model, and automatically updating the data model based on updated training data that is received as operational data. For data sources excluded from the clusters, automatic building, data cleansing, and updating of models can also be applied.Type: GrantFiled: May 1, 2020Date of Patent: November 22, 2022Assignees: Chevron U.S.A. Inc., University of Southern CaliforniaInventors: Yining Dong, Alisha Deshpande, Yingying Zheng, Lisa Ann Brenskelle, Si-Zhao Qin
-
Patent number: 10876867Abstract: Methods and systems for detecting a fault in a data set from an industrial process are disclosed. One method includes forming a first data matrix at a data processing framework from time-series training data, and performing a principal component pursuit on the first data matrix to form an uncorrupted, unscaled matrix and a sparse matrix in the memory, and scaling the uncorrupted, unscaled matrix to form an uncorrupted scaled matrix. The method also includes performing a dynamic principal component analysis (DPCA) on the uncorrupted scaled matrix to form a DPCA model, and determining a squared prediction error from the DPCA model. Based on the squared prediction error, faults are detected in a different data set from operation of the industrial process. At least one of (1) correcting the one or more faults in the different data set or (2) performing a repair operation on a sensor is performed.Type: GrantFiled: November 13, 2017Date of Patent: December 29, 2020Assignees: Chevron U.S.A. Inc., University of Southern CaliforniaInventors: Alisha Deshpande, Si-Zhao J. Qin, Lisa Ann Brenskelle
-
Publication number: 20200348659Abstract: Methods and systems for building and maintaining model(s) of a physical process are disclosed. One method includes receiving training data associated with a plurality of different data sources, and performing a clustering process to form one or more clusters. For each of the one or more clusters, the method includes building a data model based on the training data associated with the data sources in the cluster, automatically performing a data cleansing process on operational data based on the data model, and automatically updating the data model based on updated training data that is received as operational data. For data sources excluded from the clusters, automatic building, data cleansing, and updating of models can also be applied.Type: ApplicationFiled: May 1, 2020Publication date: November 5, 2020Applicants: Chevron U.S.A. Inc., University of Southern CaliforniaInventors: Yining DONG, Alisha DESHPANDE, Yingying ZHENG, Lisa Ann BRENSKELLE, Si-Zhao QIN
-
Patent number: 10638013Abstract: Systems and methods for processing online data are disclosed. One such method includes receiving a plurality of data points in a time-series at a short term storage. The method also includes calculating at least one approximation coefficient based on the plurality of data points using a wavelet transform, including calculating a highest level approximation coefficient, and calculating estimated value based on the highest level approximation coefficient. The method further includes calculating differences between the estimated value and the plurality of data points of the short term storage, and determining whether a maximum difference among the calculated differences is less than a predetermined threshold. The method further includes, based on the maximum difference being greater than or equal to the predetermined threshold, storing the oldest data point of the short term storage in a long term storage.Type: GrantFiled: June 9, 2017Date of Patent: April 28, 2020Assignee: Chevron U.S.A. Inc.Inventors: Alisha Deshpande, Lisa Ann Brenskelle
-
Publication number: 20180136019Abstract: Methods and systems for detecting a fault in a data set from an industrial process are disclosed. One method includes forming a first data matrix at a data processing framework from time-series training data, and performing a principal component pursuit on the first data matrix to form an uncorrupted, unscaled matrix and a sparse matrix in the memory, and scaling the uncorrupted, unscaled matrix to form an uncorrupted scaled matrix. The method also includes performing a dynamic principal component analysis (DPCA) on the uncorrupted scaled matrix to form a DPCA model, and determining a squared prediction error from the DPCA model. Based on the squared prediction error, faults are detected in a different data set from operation of the industrial process. At least one of (1) correcting the one or more faults in the different data set or (2) performing a repair operation on a sensor is performed.Type: ApplicationFiled: November 13, 2017Publication date: May 17, 2018Applicants: Chevron U.S.A. Inc., University of Southern CaliforniaInventors: ALISHA DESHPANDE, SI-ZHAO J. QIN, LISA ANN BRENSKELLE
-
Publication number: 20170359478Abstract: Systems and methods for processing online data are disclosed. One such method includes receiving a plurality of data points in a time-series at a short term storage. The method also includes calculating at least one approximation coefficient based on the plurality of data points using a wavelet transform, including calculating a highest level approximation coefficient, and calculating estimated value based on the highest level approximation coefficient. The method further includes calculating differences between the estimated value and the plurality of data points of the short term storage, and determining whether a maximum difference among the calculated differences is less than a predetermined threshold. The method further includes, based on the maximum difference being greater than or equal to the predetermined threshold, storing the oldest data point of the short term storage in a long term storage.Type: ApplicationFiled: June 9, 2017Publication date: December 14, 2017Applicant: Chevron U.S.A. Inc.Inventors: Alisha Deshpande, Lisa Ann Brenskelle
-
Publication number: 20160179599Abstract: A computer-implemented method for reconstructing data includes receiving a selection of one or more input data streams at a data processing framework. The method can include determining existence of a fault in the input data stream(s). This determination can be based on receiving a definition of one or more analytics components at the data processing framework and applying a dynamic principal component analysis (DPCA) to the input data streams. Detection of the fault can be based at least in part on a prediction error and a variation in principal component subspace generated based on the DPCA. Detection of the fault can also be based on performing a wavelet transform to generate a set of coefficients defining the data stream, the set of coefficients including one or more coefficients representing a high frequency portion of data included in the data stream. The method can include reconstructing data at the fault.Type: ApplicationFiled: November 10, 2015Publication date: June 23, 2016Applicants: University of Southern California, Chevron U.S.A. Inc.Inventors: Alisha Deshpande, Yining Dong, Gang Li, Yingying Zheng, Si-Zhao Qin, Lisa Ann Brenskelle