Predictive Maintenance in Photovoltaic Plants with a Big Data Approach

TL;DR

This paper introduces a data-driven machine learning approach for predictive maintenance in photovoltaic plants, capable of early fault detection and classification using SCADA data, applicable across different plant sizes and inverter technologies.

Contribution

It presents a novel flexible fault prediction system combining unsupervised clustering and neural networks, enabling early detection of generic and specific faults in PV plants.

Findings

Predicts generic faults up to 7 days in advance with 95% sensitivity.

Anticipates specific fault damage from hours to 7 days.

Effective across multiple PV plant sizes and inverter brands.

Abstract

This paper presents a novel and flexible solution for fault prediction based on data collected from SCADA system. Fault prediction is offered at two different levels based on a data-driven approach: (a) generic fault/status prediction and (b) specific fault class prediction, implemented by means of two different machine learning based modules built on an unsupervised clustering algorithm and a Pattern Recognition Neural Network, respectively. Model has been assessed on a park of six photovoltaic (PV) plants up to 10 MW and on more than one hundred inverter modules of three different technology brands. The results indicate that the proposed method is effective in (a) predicting incipient generic faults up to 7 days in advance with sensitivity up to 95% and (b) anticipating damage of specific fault classes with times ranging from few hours up to 7 days. The model is easily deployable for on-line monitoring of anomalies on new PV plants and technologies, requiring only the availability of historical SCADA and fault data, fault taxonomy and inverter electrical datasheet. Keywords: Data Mining, Fault Prediction, Inverter Module, Key Performance Indicator, Lost Production