Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Tuesday 27.07.2021 at 12:00 PM CEST
Settings

Settings

Goto Application

1. WO2020140102 - SYSTEM AND METHOD FOR EVALUATING MODELS FOR PREDICTIVE FAILURE OF RENEWABLE ENERGY ASSETS

Publication Number WO/2020/140102
Publication Date 02.07.2020
International Application No. PCT/US2019/068840
International Filing Date 27.12.2019
IPC
G01R 31/08 2020.1
GPHYSICS
01MEASURING; TESTING
RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
31Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
08Locating faults in cables, transmission lines, or networks
G01R 31/14 2006.1
GPHYSICS
01MEASURING; TESTING
RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
31Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
12Testing dielectric strength or breakdown voltage
14Circuits therefor
CPC
G06F 17/16
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
10Complex mathematical operations
16Matrix or vector computation ; , e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
G06F 2113/06
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
2113Details relating to the application field
06Wind turbines or wind farms
G06F 30/20
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
30Computer-aided design [CAD]
20Design optimisation, verification or simulation
H02S 50/00
HELECTRICITY
02GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
SGENERATION OF ELECTRIC POWER BY CONVERSION OF INFRA-RED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
50Monitoring or testing of PV systems, e.g. load balancing or fault identification
Y02E 10/50
YSECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
EREDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
10Energy generation through renewable energy sources
50Photovoltaic [PV] energy
Applicants
  • WANG, Yajuan [US]/[US]
  • SOLYMOSI, Gabor [HU]/[HU]
  • KIM, Younghun [US]/[US]
Inventors
  • WANG, Yajuan
  • SOLYMOSI, Gabor
  • KIM, Younghun
Agents
  • KLOKE, Daniel
Priority Data
16/234,32927.12.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SYSTEM AND METHOD FOR EVALUATING MODELS FOR PREDICTIVE FAILURE OF RENEWABLE ENERGY ASSETS
(FR) SYSTÈME ET PROCÉDÉ D'ÉVALUATION DE MODÈLES POUR UNE DÉFAILLANCE PRÉDICTIVE D'ACTIFS ÉNERGÉTIQUES RENOUVELABLES
Abstract
(EN)
An example method comprises receiving historical sensor data from sensors of components of wind turbines, training a set of models to predict faults for each component using the 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.
(FR)
Un procédé donné à titre d'exemple consiste à recevoir des données de capteur historiques provenant de capteurs de composants de turbines éoliennes, à entraîner un ensemble de modèles pour prédire des défaillances pour chaque composant à l'aide des données de capteur historiques, à évaluer chaque modèle d'un ensemble ayant différentes fenêtres temporelles d'observation et fenêtres temporelles de connexion, à évaluer chaque modèle d'un ensemble à l'aide de métriques normalisées, à comparer des évaluations de chaque modèle d'un ensemble pour sélectionner un modèle avec un temps de connexion et une précision préférés, à recevoir des données de capteur de courant provenant des capteurs des composants, à appliquer le(s) modèle sélectionné(s) aux données de capteur de courant pour générer une prédiction de défaillance de composant, à comparer la prédiction de défaillance de composant à un seuil, et à générer une alerte et un rapport sur la base de la comparaison avec le seuil.
Also published as
Latest bibliographic data on file with the International Bureau