# US 2023/0418998 A1 · Scalable system and engine for forecasting wind turbine failure

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

- Number: US 2023/0418998 A1
- Document ID: US20230418998A1
- Status: Published application
- Kind: A1
- Application number: 18/465,096
- Filed: 2023-09-11
- Published: 2023-12-28
- Earliest claimed: 2018-12-27
- Assignees: Utopus Insights, Inc.
- Applicants: Utopus Insights, Inc.
- Inventors: Yajuan Wang; Gabor Solymosi; Ede Szarka; Younghun Kim
- Web page: https://patentgrep.com/patent/US20230418998A1

## CPC

- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- F03D 17/00: Monitoring or testing of wind motors, e.g. diagnostics (testing during commissioning of wind motors F03D13/30)
- G05B 23/0205: {by means of a monitoring system capable of detecting and responding to faults}
- G06N 20/00: Machine learning
- H02J 3/38: Arrangements for feeding a single network from two or more generators or sources in parallel; Arrangements for feeding already energised networks from additional generators or sources in parallel
- F05B 2260/84: Modelling or simulation
- G06F 2119/02: Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/20: Ensemble learning
- H02J 2103/30: Simulating, planning, modelling, reliability check or computer assisted design [CAD] of electric power networks
- Y02E 10/76: Power conversion electric or electronic aspects
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H02J: ELECTRIC POWER NETWORKS; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- 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
- Y02E: REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION

## Abstract

An example method utilizing different pipelines of a prediction system, comprises receiving event and alarm data from event logs, failure data, and asset data from SCADA system(s), retrieve patterns of events, receiving historical sensor data from sensors of components of wind turbines, training a set of models to predict faults for each component using the patterns of events and historical sensor data, each model of a set having different observation time windows and lead time windows, evaluating each model of a set using standardized metrics, comparing evaluations of each model of a set to select a model with preferred lead time and accuracy, receive current sensor data from the sensors of the components, apply the selected model(s) to the current sensor data to generate a component failure prediction, compare the component failure prediction to a threshold, and generate an alert and report based on the comparison to the threshold.

## Claims

### Claim 1

A non-transitory computer readable medium comprising executable instructions, the executable instructions being executable by one or more processors to perform a method, the method comprising:
receiving by a model selection pipeline of a component failure prediction system, event and alarm data from event logs of one or more SCADA systems that monitor any number of wind turbines, the event and alarm data being generated during a first period of time;
receiving by the model selection pipeline, historical wind turbine component failure data and wind turbine asset data from the one or more SCADA systems during the first period of time;
creating by the model selection pipeline, cohort instances based on the wind turbine failure data and wind turbine asset data, each cohort representing a subset of the wind turbines, the subset of the wind turbines including a same type of controller and a similar geographical location, the geographical location of the wind turbines of the subset of wind turbines being within the wind turbine asset data;
generating by the model selection pipeline, an event and alarm vendor agnostic representation of the event and alarm data creating a feature matrix, wherein the feature matrix includes a unique feature identifier for each feature of the event and alarm data and one or more features from the event and alarm data;
extracting by the model selection pipeline, patterns of events based on the feature matrix;
receiving by a model training and testing pipeline of the component failure prediction system, first historical sensor data of the first time period, the first historical sensor data including sensor data from one or more sensors of one or more components of the any number of renewable energy assets, the first historical sensor data indicating at least one first failure associated with the one or more components of the renewable energy asset during the first time period;
generating by the model training and testing pipeline, a first set of failure prediction models using the first historical sensor data and the patterns of events, each of the first set of failure prediction models being trained using different amounts of first historical sensor data based on different observation time windows and different lead time windows, each observation time window including a time period during which first historical data is generated, the lead time window including a period of time before a predicted failure;
evaluating by the model training and testing pipeline, each of the first set of failure prediction models using at least a confusion matrix including metrics for true positives, false positives, true negatives, and false negatives as well as a positive prediction value;
comparing by the model training and testing pipeline, the confusion matrix and the positive prediction value of each of the first set of failure prediction models;
selecting by the model training and testing pipeline, at least one failure prediction model of the first set of failure prediction models based on the comparison of the confusion matrixes, the positive prediction values, and the lead time windows to create a first selected failure prediction model, the first selected failure prediction model including the lead time window before a predicted failure;
receiving by a model scoring pipeline of the component failure prediction system, first current sensor data of a second time period, the first current sensor data including sensor data from the one or more sensors of the one or more components of the renewable energy asset;
applying by the model scoring pipeline, the first selected failure prediction model to the current sensor data to generate a first failure prediction a failure of at least one component of the one or more components;
comparing by the model scoring pipeline, the first failure prediction to a trigger criteria; and
generating and transmitting by the model scoring pipeline, a first alert based on the comparison of the failure prediction to the trigger criteria, the alert indicating the at least one component of the one or more components and information regarding the failure prediction.
