AI extensions and intelligent model validation for an industrial digital twin

    公开(公告)号:US11900277B2

    公开(公告)日:2024-02-13

    申请号:US17744980

    申请日:2022-05-16

    CPC classification number: G06N5/048 G06N20/10

    Abstract: Industrial smart data tags conforming to structured data types serve as the basis for creating a digital twin of an industrial asset. The digital twin can comprise an automation model and a mechanical model or other type of non-automation model, both of which reference the smart tags in connection with digitally modeling the industrial asset. The structured data topology offered by the smart tags allows the digital twin to be readily interfaced with artificial intelligence (AI) systems. AI analysis can leverage the smart tags to discover new relationships between key performance indicators and other variables of the asset and encode these relationships in the smart tags themselves. These enhanced smart tags can also be leveraged to perform AI-based validation the digital twin. Additional contextualization provided by the enhanced smart tags can simplify AI analysis and assist in quickly converging on desired analytic results.

    DYNAMICALLY RECONFIGURABLE DATA COLLECTION AGENT FOR FRACKING PUMP ASSET

    公开(公告)号:US20220236724A1

    公开(公告)日:2022-07-28

    申请号:US17659512

    申请日:2022-04-18

    Abstract: A scalable industrial asset management system dynamically negotiates allocation of mobile industrial assets to industrial operation sites. The asset management system tracks and models the capabilities and availabilities of a pool of mobile industrial assets (e.g., truck-mounted assets or other such assets). Based on a defined demand of a scheduled industrial operation requiring mobile industrial assets (e.g., a fracking operation, a mining operation, etc.) the system selects a subset of the mobile industrial assets that are both available during the scheduled operation and are collectively capable of satisfying the demands of the industrial operation. Moreover, based on the asset models for the subset of mobile industrial assets, the system configures an on-premise cloud agent device to collect telemetry data from the mobile assets during the operation and to migrate the collected data to a cloud-based collection and analytics system.

    Predictive monitoring and diagnostics systems and methods

    公开(公告)号:US11079726B2

    公开(公告)日:2021-08-03

    申请号:US16666011

    申请日:2019-10-28

    Abstract: System and method for improving operation of an industrial automation system, which includes a control system that controls operation of an industrial automation process. The control system includes a feature extraction block that determines extracted features by transforming process data determined during operation of an industrial automation process based at least in part on feature extraction parameters; a feature selection block that determines selected features by selecting a subset of the extracted features based at least in part on feature selection parameters, in which the selected features are expected to be representative of the operation of the industrial automation process; and a clustering block that determines a first expected operational state of the industrial automation system by mapping the selected features into a feature space based at least in part on feature selection parameters.

    PREDICTIVE MONITORING AND DIAGNOSTICS SYSTEMS AND METHODS

    公开(公告)号:US20200064789A1

    公开(公告)日:2020-02-27

    申请号:US16666011

    申请日:2019-10-28

    Abstract: System and method for improving operation of an industrial automation system, which includes a control system that controls operation of an industrial automation process. The control system includes a feature extraction block that determines extracted features by transforming process data determined during operation of an industrial automation process based at least in part on feature extraction parameters; a feature selection block that determines selected features by selecting a subset of the extracted features based at least in part on feature selection parameters, in which the selected features are expected to be representative of the operation of the industrial automation process; and a clustering block that determines a first expected operational state of the industrial automation system by mapping the selected features into a feature space based at least in part on feature selection parameters.

    PREDICTIVE MONITORING AND DIAGNOSTICS SYSTEMS AND METHODS

    公开(公告)号:US20190004485A1

    公开(公告)日:2019-01-03

    申请号:US16123678

    申请日:2018-09-06

    Abstract: System and method for improving operation of an industrial automation system, which includes a control system that controls operation of an industrial automation process. The control system includes a feature extraction block that determines extracted features by transforming process data determined during operation of an industrial automation process based at least in part on feature extraction parameters; a feature selection block that determines selected features by selecting a subset of the extracted features based at least in part on feature selection parameters, in which the selected features are expected to be representative of the operation of the industrial automation process; and a clustering block that determines a first expected operational state of the industrial automation system by mapping the selected features into a feature space based at least in part on feature selection parameters.

    Optimization based controller tuning systems and methods

    公开(公告)号:US10139809B2

    公开(公告)日:2018-11-27

    申请号:US14996008

    申请日:2016-01-14

    Abstract: One embodiment of the present disclosure describes an industrial system, which includes a control system that controls operation of an industrial process by instructing an automation component in the industrial system to implement a manipulated variable setpoint. The control system includes a process model that model operation of the industrial process, control optimization that determines the manipulated variable setpoint based at least in part on the process model, a control objective function, and constraints on the industrial process, in which the control objective function includes a tuning parameter that describes weighting between aspects of the industrial process affected by the manipulated variable setpoint; and tuning optimization circuitry that determines the tuning parameter based at least in part on a tuning objective function, in which the tuning objective function is determined based at least in part on a closed form solution to an augmented version of the control objective function, which includes the constraints as soft constraints.

Patent Agency Ranking