# US 2019/0170119 A1 · Adaptive control of a wind turbine by detecting a change in performance

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

- Number: US 2019/0170119 A1
- Document ID: US20190170119A1
- Status: Published application
- Kind: A1
- Application number: 16/306,850
- Filed: 2017-06-06
- Published: 2019-06-06
- Earliest claimed: 2016-06-07
- Assignees: Vestas Wind Systems A/S
- Applicants: Vestas Wind Systems A/S
- Inventors: Thomas S. Bjertrup NIELSEN
- Web page: https://patentgrep.com/patent/US20190170119A1

## CPC

- F03D 7/046: {with learning or adaptive control, e.g. self-tuning, fuzzy logic or neural network}
- F03D 7/0224: {Adjusting blade pitch}
- F03D 7/028: {controlling wind motor output power}
- G05B 19/042: using digital processors (G05B19/05 takes precedence)
- H02P 9/04: Control effected upon non-electric prime mover and dependent upon electric output value of the generator
- F05B 2270/20: to optimise the performance of a machine
- F05B 2270/335: Output power or torque
- G05B 2219/2619: Wind turbines
- G06N 20/00: Machine learning
- H02P 2101/15: for wind-driven turbines
- Y02E 10/72: Wind turbines with rotation axis in wind direction
- Y02P 80/10: Efficient use of energy, e.g. using compressed air or pressurized fluid as energy carrier
- F03D: WIND MOTORS
- 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)
- H02P: CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- F05B: INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- Y02E: REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

A controller for a wind turbine is disclosed, comprising: a processor; an input/output interface; and a memory including instructions that, when executed by the processor, cause the processor to: i) select a setting xi from a list of settings X1, . . . , XN; ii) operate the turbine according to setting Xi for a period of time t1; iii) record a power output signal over t1; iv) repeat steps i) to iii) for another setting in X1, . . . , XN until all N settings have been used; v) repeat steps i) to iv) for a number of cycles c; vi) calculate a summarized power output for each setting over all cycles; and vii) compare the summarized power outputs across settings and determine whether any setting X* results in a higher power output than other settings tested. A method of identifying power production improvements in a wind turbine, a computer program and a wind turbine are also disclosed.

## Claims

### Claim 1

A controller for a wind turbine comprising:
a processor;
an input/output interface; and
a memory including instructions that, when executed by the processor, cause the processor to:
i) select a setting xi from a list of settings X1, . . . , XN;
ii) operate the turbine according to setting Xi for a period of time t1;
iii) record a power output signal over t1;
iv) repeat steps i) to iii) for another setting in X1, . . . , XN until all N settings have been used;
v) repeat steps i) to iv) for a number of cycles c;
vi) calculate a summarised power output for each setting over all cycles;
vii) compare the summarised power outputs across settings and determine whether any setting X* results in a higher power output than other settings tested.

### Claim 2 (depends on 1)

The controller of claim 1, wherein the processor additionally executes instructions to operate the turbine with setting X* found at step vii) to result in a higher power output.

### Claim 3 (depends on 1)

The controller of claim 1, wherein between steps i) and ii) the processor additionally executes instructions to operate the turbine according to setting Xi for a time period t2 during which the power output is not recorded.

### Claim 4 (depends on 1)

The controller of claim 1, wherein a summarised power output is a cumulated power output value or an average power output value.

### Claim 5 (depends on 1)

The controller of claim 1, wherein a calibration run is performed to determine one or more of: a number of cycles c, the period of time t1, the period of time t2, the number of settings tested N, the difference threshold for a summarised power output to be considered higher than another.

### Claim 6 (depends on 5)

The controller of claim 5, wherein the calibration run is performed simultaneously with the test run, by repeating steps i) to iii) for the same setting in addition to the test settings.

### Claim 7 (depends on 1)

The controller of claim 1, wherein the processor also executes instructions to record additional data from one or more sensors for each period t1.

### Claim 8 (depends on 7)

The controller of claim 7, wherein the data from one or more sensors is indicative of the wind speed during each t1.

### Claim 9 (depends on 8)

The controller of claim 8, wherein the power output data is separated into wind speed bins according to the measured or estimated wind speed during each t1.

### Claim 10 (depends on 9)

The controller of claim 9, wherein the summarised power output computed at step vi) is computed separately for each wind speed bin.

### Claim 11 (depends on 1)

The controller of claim 1, wherein the summarised power outputs are compared at step vii) over a range of wind speeds, preferably below the rated wind speed of the wind turbine.

### Claim 12 (depends on 1)

The controller of claim 1, wherein the power output comprises measurements from a power output sensor and/or values indirectly obtained from other measured quantities, preferably wherein the other measurements comprise any of main shaft torsion measurements, main shaft torque measurements, gearbox shaft torsion measurements, blade strain measurements, blade load measurements, strain measurements on the blade bearings, strain measurements on the blade bolts, strain measurements on the hub, blade surface pressure measurements, blade tip mean deflection in edgewise direction, generator current, transformer power, transformer current, and/or tower lateral moment.

### Claim 13 (depends on 1)

The controller of claim 1, wherein the time period t1 is between 5 seconds and 5 minutes, or the time period t1+t2 is between 5 seconds and 5 minutes.

### Claim 14 (depends on 1)

The controller of claim 1, wherein the settings X1, . . . , XN comprise regulation relationships between pitch angle and/or rotor speed and wind speed.

### Claim 15

A method of identifying power production improvements in a wind turbine, the method comprising:
i) selecting a setting x; from a list of settings X1, . . . , XN;
ii) operating the turbine according to setting Xi for a period of time t1;
iii) recording a power output signal over t1;
iv) repeating steps i to iii for another setting in X1, . . . , XN until all N settings have been used;
v) repeating steps i to iv for a number of cycles c;
vi) calculating a summarised power output for each setting over all cycles;
vii) comparing the summarised power outputs across settings and determine whether any setting X* results in a higher power output than other settings tested.

### Claim 16

A computer program for a controller of a wind turbine, that when executed by the controller causes the controller to perform an operation of identifying power production improvements in the wind turbine, the operation comprising:
i) selecting a setting x; from a list of settings X1, . . . , XN;
ii) operating the turbine according to setting Xi for a period of time t1;
iii) recording a power output signal over t1;
iv) repeating steps i to iii for another setting in X1, . . . , XN until all N settings have been used;
v) repeating steps i to iv for a number of cycles c;
vi) calculating a summarised power output for each setting over all cycles;
vii) comparing the summarised power outputs across settings and determine whether any setting X* results in a higher power output than other settings tested.

### Claim 17

(canceled)

### Claim 18 (depends on 16)

The computer program of claim 16 wherein the operation further comprises operating the wind turbine with setting X* found at step vii) to result in a higher power output.

### Claim 19 (depends on 16)

The computer program of claim 16 wherein between steps i) and ii) the operation further comprises operating the wind turbine according to setting Xi for a time period t2 during which the power output is not recorded.

### Claim 20 (depends on 16)

The computer program of claim 16 wherein the operation further comprises performing a calibration run to determine one or more of: a number of cycles c, the period of time t1, the period of time t2, the number of settings tested N, the difference threshold for a summarised power output to be considered higher than another.

### Claim 21 (depends on 20)

The computer program of claim 20 wherein the calibration run is performed simultaneously with the test run, by repeating steps i) to iii) for the same setting in addition to the test settings.
