Finding Faults in PV Systems: Supervised and Unsupervised Dictionary Learning With SSTDR

This article explains the use of supervised and unsupervised dictionary learning approaches on spread spectrum time domain (SSTDR) data to detect and locate disconnections in a PV array consisting of five panels. The aim is to decompose an SSTDR reflection signature into different components where each component has a physical interpretation, such as noise, environmental effects, and faults. In the unsupervised dictionary learning approach, the decomposed components are inspected to detect and localize faults. The maximum difference between actual and predicted location of the fault is 0.44 m on a system with five panels connected to an SSTDR box with a leader cable of 59.13 m and total length of 67.36 m including the effective length of the panels. In the supervised dictionary learning approach, the dictionary components are used to classify the SSTDR data to their respective fault types. Our results show a 97% accuracy using the supervised learning approach.

Automated summary

This article discusses the use of supervised and unsupervised dictionary learning approaches for detecting and locating disconnections in a PV array. The unsupervised approach focuses on detecting and localizing faults, while the supervised approach is used for classifying data to identify fault types.