Degradation Mechanism Detection in Photovoltaic Backsheets by Fully Convolutional Neural Network

Abstract

Materials and devices age with time. Material aging and degradation has important implications for lifetime performance of materials and systems. While consensus exists that materials should be studied and designed for degradation, materials inspection during operation is typically performed manually by technicians. The manual inspection makes studies prone to errors and uncertainties due to human subjectivity. In this work, we focus on automating the process of degradation mechanism detection through the use of a fully convolutional deep neural network architecture (F-CNN). We demonstrate that F-CNN architecture allows for automated inspection of cracks in polymer backsheets from photovoltaic (PV) modules. The developed F-CNN architecture enabled an end-to-end semantic inspection of the PV module backsheets by applying a contracting path of convolutional blocks (encoders) followed by an expansive path of decoding blocks (decoders). First, the hierarchy of contextual features is learned from the input images by encoders. Next, these features are reconstructed to the pixel-level prediction of the input by decoders. The structure of the encoder and the decoder networks are thoroughly investigated for the multi-class pixel-level degradation type prediction for PV module backsheets. The developed F-CNN framework is validated by reporting degradation type prediction accuracy for the pixel level prediction at the level of 92.8%.

Wet leakage resistance development of modules with various backsheet types

“…In accelerated lab tests, specific aging factors are analyzed for simulating environmental operating conditions 14–17 . A more recent approach uses fully convolutional neural networks to explain BS degradation 18 . First studies have been reported that bridge the gap between accelerated aging test in the lab and natural degradation in the field 2,19–24 .…”

“…[14][15][16][17] A more recent approach uses fully convolutional neural networks to explain BS degradation. 18 First studies have been reported that bridge the gap between accelerated aging test in the lab and natural degradation in the field. 2,[19][20][21][22][23][24] These studies comprise single observations though and lack the combination and transformation of the individual results to operating conditions in the PV power stations.…”

Application of Wireless Sensor Network Technology Using Intelligent Algorithm in Mismatch Detection of Photovoltaic Power Generation

“…Accordingly, some FDAs or technologies based on string current are proposed. Then, based on the current string characteristics, the paper proposes a PVA outlier detection (OD) algorithm combining "threshold method Hampel identifier (HI)" for mismatch detection and location [28][29][30].…”

PV modules and their backsheets - A case study of a Multi-MW PV power station

“…Gradual recognition of the fact that the degradation behavior of PV-module BSs depends strongly on the BS composition resulted in focused attention on BS failures specific for different polymer materials [1,2]. For example, many reports discuss particular issues of PAbased BS, including "chalking" (titania deposits), massive cracks in the BSs, a loss of mechanical strength and wet leakage resistance as well as potential reasons for degradation of PA-BSs [12][13][14]. In these studies, most analyses are carried out for single PV-modules in test labs.…”