Stockwell‐transform and random‐forest based double‐terminal fault diagnosis method for offshore wind farm transmission line

Abstract

Due to the difficulty and time-consumption in locating short-distance transmission lines for deep-sea offshore wind farm (DOWF),this paper proposes a novel double-terminal fault location method by using Stockwell-transform (ST) and random-forest (RF). After the fault type and branch are accurately determined, the accurate transmission line fault location is located. Firstly, Stockwell-transform is employed to extract fault eigenvalues from the collected wind turbine (WT) current signals, which will reduce the sensitivity of eigenvalues to noise. And the Pearson correlation coefficient (PCC) is introduced to remove duplicate eigenvalues. Secondly, the reserved fault eigenvalues are taken as inputs to the different random-forest to classify fault types and identify the fault branch, respectively. Finally, the double-terminal fault location principle is established in fault negative sequence network (only ABCG uses positive sequence components). Newton-Raphson method (NRM) is used to eliminate the influence of asynchrony data, which implies an accurate transmission line fault location for deep-sea offshore wind farm. More than 4000 fault cases data obtained by Simulink simulation verify the feasibility and performance of the proposed method. The results show that the proposed location method has a high fault recognition rate and is immune to fault inception angle, resistance, location and noise.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Visualization and Synthesis of LCCC Space Based on RF-SVM Optimization

“…The core of RF is to establish a multi-level, overlapping forest model, with each model selected from different forest models through independence and correlation of the dataset. RF can effectively process high-dimensional data and has strong scalability [4]. Furthermore, the RF algorithm does not require data normalizationwhich saves time.…”

Review on Monitoring, Operation and Maintenance of Smart Offshore Wind Farms

“…However, sufficient attention must be still be given to the research on data encryption and secure transmission. Since it is difficult and time-intensive to locate short-distance transmission lines for deep-sea offshore wind farms, Wang et al [17] proposed a Stockwell transform and random forest-based double terminal fault location method, in which the Stockwell transform method was used to extract the effective features, and random forest was used to train the data-driven classifier to classify the fault type and fault branch; however, the influence of load variation and line parameters should be further studied. Liu et al [18] discussed some classic intelligent fault diagnosis methods for power electronic converters and proposed a random forest and transient fault feature-based fault diagnosis method for the three-phase power electronics converters, but in-depth research should also be carried out in combination with the offshore operation environment.…”

Fault Detection of Wind Turbine Electric Pitch System Based on IGWO-ERF

“…Wang, X.D. [24] focused on the difficult and timeconsuming problem of the DOWF short-distance transmission line location, proposing a two terminal fault location method combining ST and RF. In order to do so, the fault features are first extracted from the collected wind turbine current signal through ST transform, and then the data are processed and transformed into the Random Forest model for diagnosis.…”