journal article·2024-08

Enhancing solar cell production line monitoring through advanced statistical analysis

Gaia M.N. Javier, Rhett Evans, Thorsten Trupke, Ziv Hameiri

Publisher page

Abstract

Efficient monitoring of solar cell performance in high-volume production lines is crucial to ensure consistency and stability. However, this task faces challenges as many manufacturing processes introduce efficiency variations. This study proposes a method, based on lag sequential analysis, to monitor and evaluate these variations. The proposed method is based on the analysis of time-series electrical measurements (such as open-circuit voltage, short-circuit current, fill factor, and efficiency) to identify the degree of randomness, trace process-induced batch variations, and assess line stability. Real-time application of the method can flag anomalies. Furthermore, the suggested method can be extended to image analysis by extracting relevant features from time-series luminescence images, enabling the study of whether cell defects in manufacturing exhibit a random pattern or possess distinguishable characteristics. With its various possible applications, the proposed method has significant potential in enhancing solar cell production line monitoring systems, enabling early identification of production issues and process improvement by manufacturers.
Source: expertdata · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Photovoltaic System Optimization Techniques · Silicon and Solar Cell Technologies · Industrial Vision Systems and Defect Detection

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (34)

Show source-provided references
1. Marrying quality assurance with design engineering – a winning partnership! But, a cultural divide?
2. Optimization of solar cell production lines using neural networks and genetic algorithms10.1021/acsaem.0c01207 ↗
3. Multivariate data analytics in PV manufacturing—four case studies using manufacturing datasets10.1109/JPHOTOV.2017.2778571 ↗
4. A combined numerical modeling and machine learning approach for optimization of mass-produced industrial solar cells10.1109/JPHOTOV.2020.3004930 ↗
5. A comprehensive methodology to evaluate losses and process variations in silicon solar cell manufacturing10.1109/JPHOTOV.2019.2926628 ↗
6. Distinguishing between common cause variation and special cause variation in a manufacturing system: a simulation of decision making for different types of variation10.1016/j.ijpe.2019.07.019 ↗
7. Half and full solar cell efficiency binning by deep learning on electroluminescence images10.1002/pip.3484 ↗
8. Contactless inline IV measurement of solar cells using an empirical model10.1002/solr.202200599 ↗
9. Quality control implementation in manufacturing companies: motivating factors and challenges
10. Status and perspectives of crystalline silicon photovoltaics in research and industry10.1038/s41578-022-00423-2 ↗
11. Solar simulators and I–V measurement methods10.1016/0379-6787(86)90124-9 ↗
12. Photographic surveying of minority carrier diffusion length in polycrystalline silicon solar cells by electroluminescence10.1063/1.1978979 ↗
13. Photoluminescence imaging of silicon wafers10.1063/1.2234747 ↗
14. Six-sigma design (quality control)10.1109/6.275174 ↗
15. pandas.DataFrame.resample — pandas 1.5.2 documentation. https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.resample.html.
16. A note on the influence of outliers on parametric and nonparametric tests10.1080/00221309.1994.9921213 ↗
17. Alarm rates for quality control charts10.1016/0167-7152(94)00174-7 ↗
18. Machine learning applications in production lines: a systematic literature review10.1016/j.cie.2020.106773 ↗
19. Machine learning techniques for anomaly detection application domains
20. Machine learning in manufacturing towards industry 4.0: from ‘for now’ to ‘four-know’10.3390/app13031903 ↗
21. Chapter 4 - Fundamentals of data processing
22. Automated defect detection and localization in photovoltaic cells using semantic segmentation of electroluminescence images10.1109/JPHOTOV.2021.3131059 ↗
23. Polycrystalline silicon wafer defect segmentation based on deep convolutional neural networks10.1016/j.patrec.2018.12.013 ↗
24. SIGAN: A novel image generation method for solar cell defect segmentation and augmentation
25. Allen · 2017
26. DeGroot · 2012
27. Advanced production line monitoring with time-lag sequential analysis
28. Geostatistics
29. Statistical process monitoring and feedback adjustment: A discussion10.2307/1270028 ↗
30. sklearn.ensemble.IsolationForest, scikit-learn. https://scikit-learn/stable/modules/generated/sklearn.ensemble.IsolationForest.html.
31. Isolation forest based anomaly detection: A systematic literature review
32. Six Sigma-based approach to optimise the diffusion process of crystalline silicon solar cell manufacturing10.1080/14786451.2013.861463 ↗
33. Detection of typical defects in silicon photovoltaic modules and application for plants with distributed MPPT configuration10.3390/en12234547 ↗
34. Deep learning methods for solar fault detection and classification: A review