# US 2016/0365735 A1 · Systems and Methods for Power Plant Data Reconciliation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2016/0365735 A1
- Document ID: US20160365735A1
- Status: Published application
- Kind: A1
- Application number: 14/734,691
- Filed: 2015-06-09
- Published: 2016-12-15
- Earliest claimed: 2015-06-09
- Assignees: General Electric Company
- Applicants: General Electric Company
- Inventors: Christopher Michael Raczynski; Larry William Swanson; Lisa Anne Wichmann; Matthew Colin Michael; Uttam Narasimhan
- Web page: https://patentgrep.com/patent/US20160365735A1

## CPC

- H02J 3/46: Controlling the sharing of generated power between the generators, sources or networks
- G05B 13/027: {using neural networks only}
- G05B 13/04: involving the use of models or simulators
- G05B 17/02: electric
- H02J: ELECTRIC POWER NETWORKS; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)

## Abstract

Systems and methods for power plant data reconciliation are provided. According to one embodiment of the disclosure, a system may include a controller and a processor in communication with the controller. The processor may be configured to run a power plant under a plurality of operational conditions. While the power plant is running, the processor may be configured to automatically collect operational data associated with the power plant. The collected data may be stored in a predefined location. Furthermore, the processor may be configured to select stable data from the operational data to coincide with output data associated with a power plant model. One or more parameters of the power plant model may be modified, and at least one difference may be minimized between the output data associated with the power plant model and a measured value in the power plant operational data. At least one control action for a power plant component using the power plant model may be determined

## Claims

### Claim 1

A method for implementing data reconciliation using a power plant model, comprising:
receiving, by at least one processor, power plant operational data;
selecting, by at least one processor, thermally stable data from the operational data to coincide with output data associated with a power plant model;
modifying, by at least one processor, one or more parameters of the power plant model, wherein at least one difference is minimized between the output data associated with the power plant model and a measured value in the power plant operational data; and
determining, by at least one processor, at least one control action for a power plant component using the power plant model.

### Claim 2 (depends on 1)

The method of claim 1, wherein the operational data comprises at least one of the following: gas turbine power, gas turbine compressor pressure and temperature, gas turbine exhaust temperature, gas turbine fuel flow rate, gas turbine inlet pressure drop, feedwater flow rates, steam turbine flow rates, steam turbine temperatures and pressures, admission temperatures, steam turbine power, condenser steam saturation temperature, and condenser cooling water temperatures.

### Claim 3 (depends on 1)

The method of claim 1, wherein the selecting stable data comprises checking the operational data and scoring the data points based at least in part on stability.

### Claim 4 (depends on 1)

The method of claim 1, wherein the modifying is based at least in part on performing: an initial analysis of gradient-based data reconciliation optimization, global-based data reconciliation optimization to remove any local minima, and one or more additional analysis of gradient-based data reconciliation optimization.

### Claim 5 (depends on 1)

The method of claim 1, wherein the power plant model is based at least in part on a neural-net surrogate model, wherein the neural-net surrogate model indicates plant component degradation by reconciling the operational data, determining data match multipliers (DMMs), and determining performance factors.

### Claim 6 (depends on 5)

The method of claim 5, wherein the neural net surrogate model is created based on a physics based model.

### Claim 7 (depends on 5)

The method of claim 5, wherein the control action is determined from the DMMs and the performance factors.

### Claim 8

A system for implementing data reconciliation using a power plant model, comprising:
a controller; and
a processor communicatively coupled to the controller and configured to:
receive power plant operational data;
select stable data from the operational data to coincide with output data associated with a power plant model;
modify one or more parameters of the power plant model, wherein at least one difference is minimized between the output data associated with the power plant model and a measured value in the power plant operational data; and
determine at least one control action for a power plant component using the power plant model.

### Claim 9 (depends on 8)

The system of claim 8, wherein the operational data comprises at least one of the following: gas turbine power, gas turbine compressor pressure and temperature, gas turbine exhaust temperature, gas turbine fuel flow rate, gas turbine inlet pressure drop, feedwater flow rates, steam turbine flow rates, steam turbine temperatures and pressures, admission temperatures, steam turbine power, condenser steam saturation temperature, and condenser cooling water temperatures.

### Claim 10 (depends on 8)

The system of claim 8, wherein the selecting stability data comprises checking the operational data and scoring the data points based at least in part on stability.

### Claim 11 (depends on 8)

The system of claim 8, wherein the modifying is based at least in part on performing a first analysis of gradient-based data reconciliation optimization, global-based data reconciliation optimization to remove any local minima, and one or more additional analysis of gradient-based data reconciliation optimization.

### Claim 12 (depends on 9)

The system of claim 9, wherein the power plant model is based at least in part on a neural-net surrogate model, wherein the neural-net surrogate model indicates plant component degradation by reconciling the operational data, determining data match multipliers (DMMs), and determining performance factors.

### Claim 13 (depends on 9)

The system of claim 9, wherein the neural net surrogate model is created based on a physics based model.

### Claim 14 (depends on 9)

The system of claim 9, wherein the control action is determined from the DMMs and the performance factors.

### Claim 15

A system comprising:
power plant equipment;
a controller in communication with the power plant equipment, wherein the controller includes a power plant control system; and
a processor in communication with the controller and configured to:
receive power plant operational data;
select stable data from the operational data to coincide with output data associated with a power plant model;
modify one or more parameters of the power plant model, wherein at least one difference is minimized between the output data associated with the power plant model and a measured value in the power plant operational data; and
determine at least one control action for a power plant component using the power plant model.

### Claim 16 (depends on 15)

The system of claim 15, wherein the selecting stability data comprises checking the operational data and scoring the data points based at least in part on stability.

### Claim 17 (depends on 15)

The system of claim 15, wherein the modifying is based at least in part on performing a first analysis of gradient-based data reconciliation optimization, global-based data reconciliation optimization to remove any local minima, and one or more additional analysis of gradient-based data reconciliation optimization.

### Claim 18 (depends on 15)

The system of claim 15, wherein the power plant model is based at least in part on a neural-net surrogate model, wherein the neural-net surrogate model indicates plant component degradation by reconciling the operational data, determining data match multipliers (DMMs), and determining performance factors.

### Claim 19 (depends on 15)

The system of claim 15, wherein the neural net surrogate model is created based on a physics based model.

### Claim 20 (depends on 15)

The system of claim 15, wherein the control action is determined from the DMMs and the performance factors.
