General Electric Company

Bl Technologies, Inc.

Ge Infrastructure Technology, LLC

Aditya Kumar

Mustafa Tekin Dokucu

Ruijie Shi

Hua Xia

Pierino Gianni Bonanni

Matthew Christian Nielsen

Kevin Thomas McCarthy

Avinash Vinayak Taware

Zhaoyang Wan

Kenneth Brakeley Welles

Harry Kirk Mathews, Jr

Weizhong Yan

Vitali Victor Lissianski

Walter Whipple

James Michael Storey

Guanghua Wang

Aaron John Avagliano

Ali Can

Joseph Lucian Smolenski

Justin Varkey John

Vladimir Zamansky

Austars Raymond Schnore, Jr

Jonathan Carl Thatcher

Nilesh Tralshawala

David Spencer Ewens

Allan John Connolly

Fernando Javier D'Amato

Ertan Yilmaz

Bruce Gordon Norman

Juntao Wu

Surinder Prabhjot Singh

Jeffrey Scott Goldmeer

Yu Zhao

Anthony John Murray

Anup Menon

Rajeeva Kumar

Nishith Pramod Vora

Vijaysai Prasad

Olugbenga Moses Anubi

James Patrick Francis Lyons

Richard Anthony Depuy

Brent Jerome Brunell

Ravindra Annigeri

Xingwei Yang

Gregory Jon Chiaramonte

Claudia C Pierce

Marc Gavin Lindenmuth

Steven Richard Levin

Difei Wang

Sangeeta Balram

Anthony Bruce Campbell

Donald Horn

Dongrui Wu

Katherine Tharp Nowicki

Michael William Bailey

Emrah Biyik

Junqiang Zhou

Cheryl Zhan

William Edwin Hurst

Sree Rama Raju Vetukuri

Mei Gao

Vivek Gandhi

Brett R Ellis

Ronald Plybon

Rodrigo Lopez-Negrete De La Fuente

Santanu Chatterjee

Donald J Horn

Ronald Cileman Plybon

Karthik Subramanyam

According to some embodiments, a system, method and non-transitory computer readable medium are provided comprising a memory storing processor-executable steps; and a processor to execute the processor-executable steps to cause the system to: receive a first data value of a plurality of data values from a data store, wherein the first data value is from a digital twin model of an industrial asset; determine, via a vulnerability module, whether the received at least one data value is a near boundary case or not a near boundary case; in a case it is determined the first data value is a near boundary case, generate one or more adversarial samples for the first data value; input each of the one or more adversarial samples to the digital twin model; execute the digital twin model to output a system response for each input adversarial sample; determine whether the system response to each input adversarial sample has a negative impact; in a case it is determined the system response has a negative impact for a given input adversarial sample, update a trained attack detection model with the given input adversarial sample; and generate a second decision boundary based on the updated trained attack detection model. Numerous other aspects are provided.

Vulnerability-driven cyberattack protection system and method for industrial assets

Methods, apparatus, systems, and articles of manufacture are disclosed to perform prognostic health monitoring of a turbine engine. An example apparatus includes a health quantifier calculator to execute a computer-generated model to generate first sensor data of a turbine engine, the first sensor data based on simulating a sensor monitoring the turbine engine using asset monitoring information, a parameter tracker to execute a tracking filter using the first sensor data and second sensor data to generate third sensor data corresponding to the turbine engine, the second sensor data based on obtaining sensor data from a sensor monitoring the turbine engine, the third sensor data based on comparing the first sensor data to the second sensor data, the health quantifier calculator to execute the computer-generated model using the third sensor data to generate an asset health quantifier of the turbine engine; and a report generator to generate a report including the asset health quantifier and a workscope recommendation based on the asset health quantifier when the asset health quantifier satisfies a threshold.

Methods and apparatus for prognostic health monitoring of a turbine engine

A dispatch optimization system leverages ambient and market forecast data as well as asset performance and parts-life models to generate recommended operating schedules for gas turbines or other power-generating plant assets that substantially maximize profit while satisfying parts-life constraints. The system generates operating profiles that balance optimal peak fire opportunities with optimal cold part-load opportunities within a maintenance interval or other operating horizon. During real-time operation of the assets, the optimization system can update the operating schedule based on actual market, ambient, and operating data. The system provides information that can assist operators in determining suitable conditions in which to cold part-load or peak-fire the assets in an optimally profitable manner without violating target life constraints.

Gas turbine dispatch optimizer real-time command and operations

A method of operating a waste water treatment plant (WWTP) having at least one of an aerobic digester (AD) and a membrane bioreactor (MBR) is described. The method of operating AD is comprised of monitoring and controlling AD in real-time using an online extended Kalman filter (EKF) having a online dynamic model of AD. The EKF uses real-time AD measured data, and online dynamic model of AD to update adapted model parameters and estimate model based inferred variables for AD, which are used for AD control by AD control system having supervisory and low-level control layers. The method of operating MBR is similar to that of AD. The supervisory control ensures the WWTP satisfying the effluent quality requirement while minimize the operation cost. A WWTP having at least one of AD or MBR is disclosed. The method of operating a WWTP can be implemented using a computer.

Wastewater treatment plant online monitoring and control

A cooling tower simulation system may receive a measurement from a cooling tower sensor and generate a predicted output of a cooling tower system based on a model of the cooling tower system. The simulation system may generate an estimated output using an extended Kalman filter with the measurement and the predicted output as inputs, wherein the estimated output represents a characteristic of the cooling tower system.

Dynamic monitoring, diagnosis, and control of cooling tower systems

In accordance with one aspect of the present technique, a method is disclosed. The method includes modifying one or more operational parameters of a gas turbine (GT) to increase an exhaust gas temperature above a standard start-up temperature. The method also includes receiving at least one of GT operational data, heat recovery steam generator (HRSG) operational data, and steam turbine (ST) operational data from a plurality of sensors. The method further includes predicting a ST roll-off time based on at least one of the GT operational data, the HRSG operational data, and the ST operational data. The method further includes modifying the one or more operational parameters of the GT to satisfy one or more ST roll-off permissives at the predicted ST roll-off time.

System and method for start-up of a combined cycle power plant

A plasma-assisted waste gasification system and process for converting waste stream reaction residues into a clean synthesis gas (syngas) is disclosed. The feedstock is fed into a reactor roughly one-third from the bottom through the use of a feed mechanism. The reactor has three zones; a bottom zone where melting occurs, a middle zone where gasification takes place, and a top zone with integrated plasma torches to control the temperature and polish the syngas. The residence times in the three zones are selected to optimize the syngas composition and melted products. The syngas leaves the reactor and is partially quenched with relatively cooler synthesis gas. The partially quenched syngas is further cooled to recover heat for steam generation and/or preheating the waste stream to the reactor. The cold syngas is then processed to remove pollutants. The clean synthesis gas is combusted in power generation equipment to generate electricity, or converted to other fuels by chemical processes.

Plasma-assisted waste gasification system

A method and system for online power management of a turbine engine is provided. The method includes operating an engine control system on a first bandwidth, filtering at least one data input from the engine control system to a second bandwidth, and receiving, by a power management system operating on the second bandwidth, the at least one filtered data input. The method also includes predicting an engine operating condition using the at least one filtered data input using a closed-loop engine model, determining an optimal engine power management based on the prediction, solving a constrained optimization for a desired optimization objective, and outputting the optimal engine power management to the engine control system.

Methods and systems for managing power of an engine

System and method to estimate variables in an integrated gasification combined cycle (IGCC) plant are provided. The system includes a sensor suite to measure respective plant input and output variables. An extended Kalman filter (EKF) receives sensed plant input variables and includes a dynamic model to generate a plurality of plant state estimates and a covariance matrix for the state estimates. A preemptive-constraining processor is configured to preemptively constrain the state estimates and covariance matrix to be free of constraint violations. A measurement-correction processor may be configured to correct constrained state estimates and a constrained covariance matrix based on processing of sensed plant output variables. The measurement-correction processor is coupled to update the dynamic model with corrected state estimates and a corrected covariance matrix. The updated dynamic model may be configured to estimate values for at least one plant variable not originally sensed by the sensor suite.

Method and system to estimate variables in an integrated gasification combined cycle (IGCC) plant

Control system and method for controlling an integrated gasification combined cycle (IGCC) plant are provided. The system may include a controller coupled to a dynamic model of the plant to process a prediction of plant performance and determine a control strategy for the IGCC plant over a time horizon subject to plant constraints. The control strategy may include control functionality to meet a tracking objective and control functionality to meet an optimization objective. The control strategy may be configured to prioritize the tracking objective over the optimization objective based on a coordinate transformation, such as an orthogonal or quasi-orthogonal projection. A plurality of plant control knobs may be set in accordance with the control strategy to generate a sequence of coordinated multivariable control inputs to meet the tracking objective and the optimization objective subject to the prioritization resulting from the coordinate transformation.

Model predictive control system and method for integrated gasification combined cycle power generation

A fiber sensor package is disclosed. The fiber sensor package includes an interconnection between a first optical fiber and a second optical fiber within a tubing such that the first and second optical fibers are at least partially disposed within that tubing. A bonding material is disposed across an edge of the interconnection around at least a part of the circumferential surfaces of the first and second fibers, holds rigid the interconnection of the first and second optical fibers. The methods of preparing the package, and the examples of systems benefiting from the fiber sensor package of this invention are also described.

Packaged sensors and harsh environment systems with packaged sensors

A fiber gas sensor includes a fiber core with first and second refractive index periodic modulated grating structures having different amplitude modulation profiles positioned about the fiber core. A fiber cladding is positioned about the first and second refractive index periodic modulated grating structures. A sensing layer is positioned about the fiber cladding of one of the refractive index periodic modulated grating structures. The sensing layer includes a sensing material made of a Pd-based alloy, such as nano-PdOx, nano-Pd(x)Au(y)Ni(1-x-y) or nano-Pd/Au/WOx. The fiber gas sensor provides a measurement of localized, temperature-corrected gas concentration and composition from a combustion environment. A reflection-based or a transmission-based sensing system with an array of one or more fiber gas sensors is also described.

Sensing system with fiber gas sensor

A method for dynamically controlling a multiple input, multiple output (MIMO) system having multiple input and output constraints, the method comprising. In an exemplary embodiment, the method includes configuring a MIMO tracking controller to implement closed loop tracking of multiple control reference inputs of the system, in the absence of input and output constraints, and configuring a MIMO constraint controller to enforce the input and output constraints of the MIMO system by generating a reference modification applied to the multiple control reference inputs.

Multivariable controller design method for multiple input/outputs systems with multiple input/output constraints

A method for estimating a temperature profile for individual combustion cans at an inlet of a gas turbine is disclosed. In an exemplary embodiment, the method includes determining an exhaust temperature profile of exhaust gas of the gas turbine, and inputting the exhaust temperature profile into a model-based estimator of turbine components through which turbine gas flows. The model-based estimator calculates an estimated inlet temperature profile at the gas turbine inlet, based upon the exhaust temperature profile and design parameters of the gas turbine, the estimate inlet temperature profile being indicative of the actual firing temperature of each of the individual combustion cans.

Method and system for temperature estimation of gas turbine combustion cans

Adaptive model-based control systems and methods are described so that performance and/or operability of a gas turbine in an aircraft engine, power plant, marine propulsion, or industrial application can be optimized under normal, deteriorated, faulted, failed and/or damaged operation. First, a model of each relevant system or component is created, and the model is adapted to the engine. Then, if/when deterioration, a fault, a failure or some kind of damage to an engine component or system is detected, that information is input to the model-based control as changes to the model, constraints, objective function, or other control parameters. With all the information about the engine condition, and state and directives on the control goals in terms of an objective function and constraints, the control then solves an optimization so the optimal control action can be determined and taken. This model and control may be updated in real-time to account for engine-to-engine variation, deterioration, damage, faults and/or failures using optimal corrective control action command(s).

Adaptive model-based control systems and methods for controlling a gas turbine

Growing community of inventors

Schenectady, NY, United States of America

Aditya Kumar