TY - GEN
T1 - Enhanced RF for Fault Detection and Diagnosis of Uncertain PV systems
AU - Dhibi, Khaled
AU - Fezai, Radhia
AU - Bouzrara, Kais
AU - Mansouri, Majdi
AU - Nounou, Hazem
AU - Nounou, Mohamed
AU - Trabelsi, Mohamed
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/3/22
Y1 - 2021/3/22
N2 - This paper proposes a new fault detection and diagnosis (FDD) approach based on Random Forest (RF) for uncertain Grid-Connected PV (GCPV) system. Firstly, to deal with uncertainties, interval RF based on upper and lower bounds of interval matrix \text{RF}-{UL} is proposed. To more improve the diagnosis accuracy, interval kernel PCA (IKPCA)-based RF classifier is developed. The enhanced scheme is so-called IKPCA-based RF and it is based on three major phases: feature extraction (FE), feature selection (FS) and fault classification (FC). The basic idea behind FE and FS phases is to use IKPCA model in order to select the most relevant and informative features from raw data. IKPCA aims to fit two KPCA models on the lower and upper bounds of the variables interval values. Then, the sensitive and significant interval-valued characteristics are transmitted to the RF model for classification purposes. The presented results demonstrate the effectiveness of the proposed interval-valued methods when applied to uncertain GCPV systems.
AB - This paper proposes a new fault detection and diagnosis (FDD) approach based on Random Forest (RF) for uncertain Grid-Connected PV (GCPV) system. Firstly, to deal with uncertainties, interval RF based on upper and lower bounds of interval matrix \text{RF}-{UL} is proposed. To more improve the diagnosis accuracy, interval kernel PCA (IKPCA)-based RF classifier is developed. The enhanced scheme is so-called IKPCA-based RF and it is based on three major phases: feature extraction (FE), feature selection (FS) and fault classification (FC). The basic idea behind FE and FS phases is to use IKPCA model in order to select the most relevant and informative features from raw data. IKPCA aims to fit two KPCA models on the lower and upper bounds of the variables interval values. Then, the sensitive and significant interval-valued characteristics are transmitted to the RF model for classification purposes. The presented results demonstrate the effectiveness of the proposed interval-valued methods when applied to uncertain GCPV systems.
KW - Fault Classification (FC)
KW - Fault Detection and Diagnosis (FDD)
KW - Feature Extraction
KW - Feature Selection
KW - Grid-Connected PV (GCPV)
KW - Interval-Valued Data
KW - Kernel Principal Component Analysis (KPCA)
KW - Machine learning (ML)
KW - Random Forest (RF)
UR - http://www.scopus.com/inward/record.url?scp=85107475930&partnerID=8YFLogxK
U2 - 10.1109/SSD52085.2021.9429418
DO - 10.1109/SSD52085.2021.9429418
M3 - Conference contribution
AN - SCOPUS:85107475930
T3 - 18th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2021
SP - 103
EP - 108
BT - 18th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2021
Y2 - 22 March 2021 through 25 March 2021
ER -