General Electric Company

Achalesh Kumar Pandey

Vinay Bhaskar Jammu

Awadesh Kumar Tiwari

Scott Mordin Hoyte

Mahesh Kumar Asati

Subrat Nanda

David Lee Rogers

Vivek Venugopal Badami

Vinod Kumar

Chayan Mitra

Lisa Anne Wichmann

Ramu Sharat Chandra

Maria Cecilia Mazzaro

Sudhanshu Rai

Kunal Ravindra Goray

Sheri George

Hao Huang

Sanji Ekanayake

Canan Uslu Hardwicke

Rahul Jaikaran Chillar

Raub Warfield Smith

Weizhong Yan

Timothy Andrew Healy

Ravi Yoganatha Babu

Richard John Rucigay

Vinod Padmanabhan Kumar

Bhasker Rao Keely

Munish Vishwas Inamdar

Helena Goldfarb

Abhinav Saxena

Fuxiao Xin

Morgan Carthledge Salter

Jagmeet Singh

Christopher Michael Raczynski

Lucy Summerville Giametta

Kareem Sherif Aggour

Nirm Velumylum Nirmalan

Romano Patrick

Kamlesh Mundra

Julio Enrique Mestroni

Sidharth Abrol

Nidhi Naithani

Aninda Bhattacharya

Larry Swanson

Peter Alan Gregg

Ajay Kumar Behera

Shivappa Ningappa Goravar

John Brandon Laflen

Rahul Srinivas Prabhu

Soumen De

Christopher Eugene Long

Venkatesh Rajagopalan

Sameer Vittal

Eric J Kauffman

Necip Doganaksoy

Manoharan Venugopal

John Alexander Petzen, Iii

Atanu Talukdar

Eric Thomas Pool

Sascha Schieke

Wei Ning

Yoon Seok Choi

Vijay Shiv Kumar

John Edward Sholes, Jr

Charles William Weidner

Vijay Raghavendran Nenmeni

Rui Xu

Niranjan Gokuldas Pai

Gerald Bowden Wise

Shaddy Abado

Xiaohui Hu

Dwayne David McDuffie

John Edward Sholes

Wulang Edwien Chriswindarto

Abhay Harpale

Slawomir Marian Zaremba

Jianbo Yang

Matthew Francis Lemmon

Raul Munoz Medina

Charmin Patel

David Stephen Muench

Vikas Handa

Ajit Srivastava

Deepali Nitin Bhate

Viany Bhaskar Jammu

Suresh Pamujula

Richard Kleinhample

Daniel Kish

Isaac Alejandro Martinez Tovar

Jonathan David White

Rasika Suresh Kalwit

John Alexander Petzen

Awadaesh Kumar Tiwari

According to some embodiments, a system and method are provided to create a template associated with an industrial problem. The method comprises receiving one or more kernels from a machine learning library. The one or more kernels are then aggregated, via a processor, into a template. The template is integrated into a user interface where is may be executed.

Machine learning templates in a machine learning framework

According to some embodiments, a system and method are provided to model a sparse data asset. The system comprises a processor and a non-transitory computer-readable medium comprising instructions that when executed by the processor perform a method to model a sparse data asset. Relevant data and operational data associated with the newly operational are received. A transfer model based on the relevant data and the received operational data. An input into the transfer model is received and a predication based on data associated with the received operational data and the relevant data is output.

Method and system to model industrial assets using heterogenous data sources

According to some embodiments, system and methods for building a model are provided, comprising a display; a memory storing processor-executable process steps; and a processor to execute the processor-executable process steps to cause the system to: present a user interface on a display, the user interface including one or more user-entry fields to build a model, user-entry fields is associated with a selection of big data or small data for use with the model; receive at least one data source in a user-entry field associated with the model; determine if data in the data source includes big data or small data; and in response to the determination of big data or small data in the data source, execute the model with data from the data source in a big data or small data execution environment. Numerous other aspects are provided.

Multimodal, small and big data, machine tearing systems and processes

According to some embodiments, system and methods are provided, comprising receiving, at a machine health module, non-parametric data associated with operation of an installed product; generating, via the machine health module, a health status for at least one of a failure type and a remaining useful life of the installed product, based on the received non-parametric data; and generating an operating response of the installed product based on the generated health status. Numerous other aspects are provided.

Machine health monitoring, failure detection and prediction using non-parametric data

A method for estimating and managing life of a gas turbine is provided. The method includes estimating a remaining useful life of a component of a gas turbine, obtaining parameters of the gas turbine, at least one of which comprises the estimate of the remaining useful life of a component of the gas turbine, assigning operating weightages to the gas turbine parameters based a plant objective, generating a set point for operating the gas turbine based on the weighted gas turbine parameters, and adjusting an operating characteristic of the gas turbine to meet the set point.

System and method for predicting and managing life consumption of gas turbine parts

A system and method for associating equipment sensor tags with tags associated with analytic programs including embodiments that receive a list of equipment tag names and corresponding descriptions as well as a list of analytic tag names and descriptions. The equipment tag descriptions are normalized to create normalized equipment tag descriptions, and the analytic tag descriptions are normalized to create normalized analytic tag descriptions. A first matrix of vectors that associates content in a dictionary with aspects of the equipment tag names is created using corresponding normalized tag descriptions. A second matrix of vectors that associates the content in a dictionary with aspects of the normalized analytic tag description is created.

Apparatus and method for tag mapping with industrial machines

A control method for optimizing or enhancing an operation of a power plant that includes thermal generating units for generating electricity. The power plant may include multiple possible operating modes differentiated by characteristics of operating parameters. The method may include tuning a power plant model so to configure a tuned power plant model. The method may further include simulating proposed operating modes of the power plant with the tuned power plant model. The simulating may include a simulation procedure that includes: defining a second operating period; selecting the proposed operating modes from the possible operating modes; with the tuned power plant model, performing a simulation run for each of the proposed operating modes whereby the operation of the power plant during the second operating period is simulated; and obtaining simulation results from each of the simulation runs.

Methods and systems for enhancing control of power plant generating units

Systems and methods for generating solution recommendations for power plant operation can be provided by certain embodiments of the disclosure. In one embodiment, a system may include a processor configured to collect power plant operational data from power plant components. The power plant operational data may be analyzed to identify cost factors for the power plant components. Based at least in part on the power plant operational data and the cost factors, upgrade opportunities for the power plant components may be determined. Financial values may be calculated for the upgrade opportunities. Based at least in part on the financial values, recommendations may be generated using a product interaction database and provided as an electronic output to a user.

Systems and methods for generating solution recommendations for power plant operation

The present subject matter is directed to a system and method for optimizing wind turbine operation. For example, the present disclosure is configured to generate operating data for at least one operational parameter of the wind turbine for a predetermined time period. The system can then determine a robustness measurement of at least a portion of the operating data. In general, the robustness measurement indicates the tendency of the operating data to be affected by outliers present in the operating data. In addition, the robustness measurement is typically a function of a distribution of the operating data. The present disclosure is then configured to determine at least one optimal set point for the operational parameter as a function of the robustness measurement and a power production of the wind turbine. The wind turbine can then be operated based on the optimal set point.

System and method for robust wind turbine operation

A method for continuously monitoring the working condition of a heat recovery steam generator ('HRSG') using infrared thermography, comprising the steps of identifying target locations inside the HRSG, positioning one or more infrared cameras to continuously monitor and record the temperature at each target location, generating continuous thermographic images corresponding to selected components and locations at each target locations, comparing the continuous thermographic images to corresponding, stored base line images and generating a set of comparative data reports in real time for each target location in order to predict the life span or potential failure of HRSG components.

Continuous infrared thermography monitoring and life management system for heat recovery steam generators

A system for detecting an at-fault combustor includes a sensor that is configured to sense combustion dynamics pressure data from the combustor and a computing device that is in electronic communication with the sensor and configured to receive the combustion dynamics pressure data from the sensor. The computing device is programmed to convert the combustion dynamics pressure data into a frequency spectrum, segment the frequency spectrum into a plurality of frequency intervals, extract a feature from the frequency spectrum, generate feature values for the feature within a corresponding frequency interval over a period of time, and to store the feature values to generate a historical database. The computing device is further programmed to execute a machine learning algorithm using the historical database of the feature values to train the computing device to recognize feature behavior that is indicative of an at-fault combustor.

System and method for detecting an at-fault combustor

Systems and methods for improved control of a turbomachine system with a bottoming cycle system are presented. The systems and methods include a controller that utilizes modeling techniques to derive a plurality of load path curves. The controller utilizes a current load path, a minimum load path, and a constant efficiency load path. The systems and methods include a control process configured to receive a user input representative of a life cycle control modality and to execute a control action based on deriving a load efficiency by applying the current load path, the minimum load path, the constant efficiency load path, or a combination thereof, and the life cycle control modality. The control action is applied to control the turbomachine system and the bottoming cycle system fluidly coupled to the turbomachine system. Further, the life cycle control modalities may be selected by a user based upon known tradeoffs.

Systems and methods for improved combined cycle control

A method of controlling a water level in a steam drum includes predicting a transient in the steam drum based on plant characteristics including steam flow from the steam drum, drum pressure in the steam drum, and one or both of a gas turbine load and a position of a bypass valve configured to control the steam flow from the steam drum to two or more steam flow conduits. The method further includes generating a sliding setpoint to control the water level based on predicting the transient in the steam drum.

Controlling boiler drum level

Systems and methods for on-line monitoring of hot gas path components of a gas turbine are provided. According to one embodiment of the disclosure, a system may include a camera operable to monitor one or more hot gas path components of the gas turbine and a processor communicatively coupled to the camera. The processor is operable to receive realtime data from the camera monitoring the one or more hot gas path components of the gas turbine and compare the realtime data to reference data. Based on the comparison, the processor can determine that a difference between the realtime data and the reference data exceeds a predetermined threshold. If the difference exceeds the predetermined threshold, the processor can notify operators of an anomaly in the one or more hot gas path components.

On-line monitoring of hot gas path components of a gas turbine

Systems and methods provided herein. In one embodiment, a system includes an advisory system including a loss computation engine configured to derive a total system loss for an industrial plant based on a first sensor positioned in a first industrial plant component and on a first physical model of the first industrial plant component. The advisory system further includes a cost model configured to use a cost function to derive a cost based on the total system loss, and a control strategy system configured to derive an advisory report, a control correction factor, or a combination thereof, based on the cost, wherein a control system is configured to apply the control correction factor to control a process in the industrial plant.

Plant control systems and methods

Growing community of inventors

Greenville, SC, United States of America

Achalesh Kumar Pandey