Processing

Please wait...

Settings

Settings

Goto Application

1. WO2019214268 - PHOTOVOLTAIC ARRAY FAULT DIAGNOSIS METHOD BASED ON COMPOSITE INFORMATION

Publication Number WO/2019/214268
Publication Date 14.11.2019
International Application No. PCT/CN2019/000095
International Filing Date 07.05.2019
IPC
G06K 9/62 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
H02S 50/10 2014.1
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 MODULES
50Monitoring or testing of PV systems, e.g. load balancing or fault identification
10Testing of PV devices, e.g. of PV modules or single PV cells
CPC
G06K 9/6247
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6232Extracting features by transforming the feature space, e.g. multidimensional scaling; Mappings, e.g. subspace methods
6247based on an approximation criterion, e.g. principal component analysis
G06K 9/6256
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
G06K 9/6262
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6262Validation, performance evaluation or active pattern learning techniques
G06K 9/6268
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
G06K 9/6269
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
6269based on the distance between the decision surface and training patterns lying on the boundary of the class cluster, e.g. support vector machines
G06K 9/6288
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6288Fusion techniques, i.e. combining data from various sources, e.g. sensor fusion
Applicants
  • 北京理工大学 BEIJING INSTITUTE OF TECHNOLOGY [CN]/[CN]
  • 邓方 DENG, Fang [CN]/[CN]
  • 梁泽浪 LIANG, Zelang [CN]/[CN]
  • 丁宁 DING, Ning [CN]/[CN]
  • 樊欣宇 FAN, Xinyu [CN]/[CN]
  • 高欣 GAO, Xin [CN]/[CN]
  • 蔡烨芸 CAI, Yeyun [CN]/[CN]
  • 陈杰 CHEN, Jie [CN]/[CN]
Inventors
  • 邓方 DENG, Fang
  • 梁泽浪 LIANG, Zelang
  • 丁宁 DING, Ning
  • 樊欣宇 FAN, Xinyu
  • 高欣 GAO, Xin
  • 蔡烨芸 CAI, Yeyun
  • 陈杰 CHEN, Jie
Priority Data
201810439521.509.05.2018CN
Publication Language Chinese (zh)
Filing Language Chinese (ZH)
Designated States
Title
(EN) PHOTOVOLTAIC ARRAY FAULT DIAGNOSIS METHOD BASED ON COMPOSITE INFORMATION
(FR) PROCÉDÉ DE DIAGNOSTIC DE DÉFAILLANCE DE RÉSEAU PHOTOVOLTAÏQUE BASÉ SUR DES INFORMATIONS COMPOSITES
(ZH) 一种基于复合信息的光伏阵列故障诊断方法
Abstract
(EN) Disclosed in the present invention is a photovoltaic array fault diagnosis method based on composite information, belonging to the technical field of fault diagnosis. The method comprises: collecting composite working state information data of a photovoltaic array and performing preprocessing, the composite working state information data comprising photovoltaic array working state image data and photovoltaic array working state textual data; using the photovoltaic array working state image data to train a pre-established deep convolutional neural network fault classification model, obtaining an image-based fault classification model upon completion of training; using the photovoltaic array working state textual data to train a pre-established fault classification model based on a support vector machine, obtaining a text-based fault classification model upon completion of training; merging the image-based model and the text-based model using a logistic regression algorithm to obtain a merged model, and using the composite working state information data of the photovoltaic array to train the merged model, obtaining a photovoltaic array fault diagnosis model based on composite information upon completion of training.
(FR) La présente invention concerne un procédé de diagnostic de défaillance de réseau photovoltaïque basé sur des informations composites, appartenant au domaine technique du diagnostic de défaillance. Le procédé comprend les étapes consistant : à collecter des données d'informations d'état de travail composite d'un réseau photovoltaïque et effectuer un prétraitement, les données d'informations d'état de travail composite comprenant des données d'image d'état de travail de réseau photovoltaïque et des données textuelles d'état de travail de réseau photovoltaïque ; à utiliser les données d'image d'état de travail de réseau photovoltaïque pour entraîner un modèle de classification de défaillance de réseau neuronal convolutionnel profond préétabli, ce qui permet d'obtenir un modèle de classification de défaillance basé sur une image à la fin de l'apprentissage ; à utiliser des données textuelles d'état de travail de réseau photovoltaïque pour entraîner un modèle de classification de défaillance préétabli à partir d'une machine de vecteur de support, ce qui permet d'obtenir un modèle de classification de défaillance à base de texte lors de l'achèvement de l'apprentissage ; à fusionner le modèle à base d'image et le modèle à base de texte à l'aide d'un algorithme de régression logistique pour obtenir un modèle fusionné, et à utiliser les données d'informations d'état de travail composites du réseau photovoltaïque pour entraîner le modèle fusionné, ce qui permet d'obtenir un modèle de diagnostic de défaillance de réseau photovoltaïque en fonction d'informations composites lors de l'achèvement de l'apprentissage.
(ZH) 本发明公开了一种基于复合信息的光伏阵列故障诊断方法,属于故障诊断技术领域。该方法包括:采集光伏阵列工作状态复合信息数据并进行预处理,工作状态复合信息数据包括光伏阵列工作状态图像数据以及光伏阵列工作状态文本数据;利用光伏阵列工作状态图像数据进行训练预先建立的深度卷积神经网络故障分类模型,训练完成后得到图像故障分类模型;利用光伏阵列工作状态文本数据训练预先建立的基于支持向量机的故障分类模型,训练完成后得到文本故障分类模型;将图像故障分类模型和文本故障分类模型采用逻辑回归算法进行融合,得到融合模型,并利用光伏阵列工作状态复合信息数据对融合模型进行训练,训练完成得到基于复合信息的光伏阵列故障诊断模型。
Related patent documents
Latest bibliographic data on file with the International Bureau