CoChat

Spectrum Analysis Enabled Periodic Feature Reconstruction Based Automatic Defect Detection System for Electroluminescence Images of Photovoltaic Modules

Open access

The DOI matches its Crossref record; the references it cites are not checked yet.

Abstract

Electroluminescence (EL) imaging is a widely adopted method in quality assurance of the photovoltaic (PV) manufacturing industry. With the growing demand for high-quality PV products, automatic inspection methods based on machine vision have become an emerging area concern to replace manual inspectors. Therefore, this paper presents an automatic defect-inspection method for multi-cell monocrystalline PV modules with EL images. A processing routine is designed to extract the defect features of the PV module, eliminating the influence of the intrinsic structural features. Spectrum domain analysis is applied to effectively reconstruct an improved PV layout from a defective one by spectrum filtering in a certain direction. The reconstructed image is used to segment the PV module into cells and slices. Based on the segmentation, defect detection is carried out on individual cells or slices to detect cracks, breaks, and speckles. Robust performance has been achieved from experiments on many samples with varying illumination conditions and defect shapes/sizes, which shows the proposed method can efficiently distinguish intrinsic structural features from the defect features, enabling precise and speedy defect detections on multi-cell PV modules.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/mi13020332

Cites

Statistics

Figures

Figure 1 (a) The EL imaging system of a PV module inspection pipeline, which activates the EL effect on each module and converts infrared light into grayscale images; (b) the spectrum domain analysis-based method to exploit the periodic features and locate the defects; (c) normal PV cell in a defect-free module; (d) PV cell with cracks; (e) PV cell with cracks and breaks; (f) PV cell with speckles.
Figure 1 (a) The EL imaging system of a PV module inspection pipeline, which activates the EL effect on each module and converts infrared light into grayscale images; (b) the spectrum domain analysis-based method to exploit the periodic features and locate the defects; (c) normal PV cell in a defect-free module; (d) PV cell with cracks; (e) PV cell with cracks and breaks; (f) PV cell with speckles.CC BY · PubMed Central
Figure 2 Simulation of the proposed method. Fourier transform spectrum magnitude and reconstructed image after spectrum filtering of (a) normal stripe feature, the spectrum is concentrated values along the horizontal axis; (b) only defect feature, the spectrum energy is scattered along the horizontal axis; (c) normal feature and defect combined, the spectrum is the sum of first two; (d) small speckle defect; (e) large area defect; (f) multiple defects; (g) defects on horizontal stripes, filtered with only vertical frequencies; defects can hardly be seen in the reconstructed image although the original defect size is big.
Figure 2 Simulation of the proposed method. Fourier transform spectrum magnitude and reconstructed image after spectrum filtering of (a) normal stripe feature, the spectrum is concentrated values along the horizontal axis; (b) only defect feature, the spectrum energy is scattered along the horizontal axis; (c) normal feature and defect combined, the spectrum is the sum of first two; (d) small speckle defect; (e) large area defect; (f) multiple defects; (g) defects on horizontal stripes, filtered with only vertical frequencies; defects can hardly be seen in the reconstructed image although the original defect size is big.CC BY · PubMed Central
Figure 3 (a) detected defect pixels under different values of C. Some false detections are highlighted with red a circle. With a higher C value, true defects are eroded. (b) Precision, recall and f1-score change according to C value upon a training set of 20 samples.
Figure 3 (a) detected defect pixels under different values of C. Some false detections are highlighted with red a circle. With a higher C value, true defects are eroded. (b) Precision, recall and f1-score change according to C value upon a training set of 20 samples.CC BY · PubMed Central
Figure 4 (a) reconstruction with only the first harmonic; (b) reconstruction with the wrong frequency selection; (c) reconstruction with all harmonics of frequency T = 12.
Figure 4 (a) reconstruction with only the first harmonic; (b) reconstruction with the wrong frequency selection; (c) reconstruction with all harmonics of frequency T = 12.CC BY · PubMed Central
Figure 5 (a) The resulting spectrum of the Fourier transform, with the origin point shifted to center; (b) vertical reconstruction and defect extraction process.
Figure 5 (a) The resulting spectrum of the Fourier transform, with the origin point shifted to center; (b) vertical reconstruction and defect extraction process.CC BY · PubMed Central
Figure 6 (a) Defect-free samples, the method is robust for illumination variations among different samples; (b) detected defects and located pixels.
Figure 6 (a) Defect-free samples, the method is robust for illumination variations among different samples; (b) detected defects and located pixels.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

The citation lists are queued

They are fetched later and appear here then.

References 22 · Cited by 14

Metadata

Authors
Yu, J., Yang, Y., Zhang, H., Sun, H., Zhang, Z., Xia, Z., Zhu, J., Dai, M., & Wen, H.
Affiliations
Southeast University (CN)
Corresponding author
  • Zhang, Zhisheng
  • Xia, Zhijie
  • Zhu, Jianxiong
Venue
Micromachines
Publisher
MDPI AG
Published
2022-02-19
Volume
13
Issue
2
Pages
332
ISSN
2072-666X (ISSN-L)
OpenAlex
W4220762544
Cited by
14
References
22
Citations by year
2026: 2 · 2025: 2 · 2024: 4 · 2023: 4 · 2022: 2
FWCI
1.38
Type
journal article
Language
en
Open access
Locations
  • Micromachines (publishedVersion, cc-by)
  • SSRN Electronic Journal (acceptedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
National Natural Science Foundation of China (51775108)
Topics
  • Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
  • Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Silicon and Solar Cell Technologies
Keywords
electroluminescence imaging, photovoltaic module defect detection, automated inspection, spectral filtering, cell segmentation, crack detection, speckle detection, automated visual inspection

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Spectrum Analysis Enabled Periodic Feature Reconstruction Based Automatic Defect Detection System for Electroluminescence Images of Photovoltaic Modules. https://app.cochat.ai/papers/10.3390/mi13020332
The paper
Yu, J., Yang, Y., Zhang, H., Sun, H., Zhang, Z., Xia, Z., Zhu, J., Dai, M., & Wen, H. (2022). Spectrum Analysis Enabled Periodic Feature Reconstruction Based Automatic Defect Detection System for Electroluminescence Images of Photovoltaic Modules. Micromachines. https://doi.org/10.3390/mi13020332

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.