Hybrid Machine Learning-Driven Automated Quality Prediction and Classification of Silicon Solar Modules in Production Lines
This research introduces a novel hybrid machine learning framework for automated quality prediction and classification of silicon solar modules in production lines. Unlike conventional approaches that rely solely on encapsulation loss rate (<i>ELR</i>) for performance evaluation—a method...
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Computation |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-3197/13/5/125 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This research introduces a novel hybrid machine learning framework for automated quality prediction and classification of silicon solar modules in production lines. Unlike conventional approaches that rely solely on encapsulation loss rate (<i>ELR</i>) for performance evaluation—a method limited to assessing encapsulation-related power loss—our framework integrates unsupervised clustering and supervised classification to achieve a comprehensive analysis. By leveraging six critical performance parameters (open circuit voltage (<i>V<sub>OC</sub></i>), short circuit current (<i>I<sub>SC</sub></i>), maximum output power (<i>P<sub>max</sub></i>), voltage at maximum power point (<i>VPM</i>), current at maximum power point (<i>IPM</i>), and fill factor (<i>FF</i>)), we first employ k-means clustering to dynamically categorize modules into three performance classes: excellent performance (<i>ELR</i>: 0–0.77%), good performance (0.77–8.39%), and poor performance (>8.39%). This multidimensional clustering approach overcomes the narrow focus of traditional <i>ELR</i>-based methods by incorporating photoelectric conversion efficiency and electrical characteristics. Subsequently, five machine learning classifiers—decision trees (DT), random forest (RF), k-nearest neighbors (KNN), naive Bayes classifier (NBC), and support vector machines (SVMs)—are trained to classify modules, achieving 98.90% accuracy with RF demonstrating superior robustness. Pearson correlation analysis further identifies <i>V<sub>OC</sub></i>, <i>P<sub>max</sub></i>, and <i>VPM</i> as the most influential quality determinants, exhibiting strong negative correlations with <i>ELR</i> (−0.953, −0.993, −0.959). The proposed framework not only automates module quality assessment but also enhances production line efficiency by enabling real-time anomaly detection and yield optimization. This work represents a significant advancement in solar module evaluation, bridging the gap between data-driven automation and holistic performance analysis in photovoltaic manufacturing. |
|---|---|
| ISSN: | 2079-3197 |