Machine learning-based process quality control of screen-printed titanium dioxide electrodes
AI-based quality control has gained attention in the manufacturing industry due to its ability to improve speed and accuracy. AI can analyze a printed electrode and classify it as either good or bad quality within milliseconds, much faster than humans and conventional methods (random sampling and co...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Results in Materials |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590048X25000378 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849434516239679488 |
|---|---|
| author | Anesu Nyabadza Lola Azoulay-Younes Mercedes Vazquez Dermot Brabazon |
| author_facet | Anesu Nyabadza Lola Azoulay-Younes Mercedes Vazquez Dermot Brabazon |
| author_sort | Anesu Nyabadza |
| collection | DOAJ |
| description | AI-based quality control has gained attention in the manufacturing industry due to its ability to improve speed and accuracy. AI can analyze a printed electrode and classify it as either good or bad quality within milliseconds, much faster than humans and conventional methods (random sampling and control charts). Herein, machine learning methods including Random Forest (RF), Support Vector Machine (SVM), and Feedforward Neural Network (FNN) are used to address a quality control problem involving the classification of screen-printed TiO2 electrodes based on image data. Multivariate data analysis techniques such as factor analysis were employed to evaluate the effectiveness of the features extracted from these images. Characterization techniques like FTIR, 4-point probe, and microscopy were used to study the printed electrodes and provide accurate labeling. A dataset comprising ∼300 electrodes was created to train the AI models. The SVM model demonstrated the best performance, achieving 100 % accuracy and recall, followed by the FNN model with 99 % accuracy. Models were optimized and accelerated through feature engineering and extraction techniques, allowing them to be trained in under 1 min. This rapid training capability makes these models highly suitable for real-world quality control applications where hundreds of electrodes are produced per minute. |
| format | Article |
| id | doaj-art-e1a9a6819e3d46628444c95311a3ff8c |
| institution | Kabale University |
| issn | 2590-048X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Materials |
| spelling | doaj-art-e1a9a6819e3d46628444c95311a3ff8c2025-08-20T03:26:38ZengElsevierResults in Materials2590-048X2025-06-012610069210.1016/j.rinma.2025.100692Machine learning-based process quality control of screen-printed titanium dioxide electrodesAnesu Nyabadza0Lola Azoulay-Younes1Mercedes Vazquez2Dermot Brabazon3I-Form Advanced Manufacturing Centre Research, Dublin City University, Glasnevin, Dublin 9, Ireland; Advanced Processing Technology Research Centre, Dublin City University, Glasnevin, Dublin 9, Ireland; Corresponding author. I-Form Advanced Manufacturing Centre Research, Dublin City University, Glasnevin, Dublin 9, IrelandAdvanced Processing Technology Research Centre, Dublin City University, Glasnevin, Dublin 9, Ireland; Conservatoire National des Arts et Métiers (CNAM), 61 Rue du Landy, 93210, Saint-Denis, FranceI-Form Advanced Manufacturing Centre Research, Dublin City University, Glasnevin, Dublin 9, Ireland; Advanced Processing Technology Research Centre, Dublin City University, Glasnevin, Dublin 9, IrelandI-Form Advanced Manufacturing Centre Research, Dublin City University, Glasnevin, Dublin 9, Ireland; Advanced Processing Technology Research Centre, Dublin City University, Glasnevin, Dublin 9, IrelandAI-based quality control has gained attention in the manufacturing industry due to its ability to improve speed and accuracy. AI can analyze a printed electrode and classify it as either good or bad quality within milliseconds, much faster than humans and conventional methods (random sampling and control charts). Herein, machine learning methods including Random Forest (RF), Support Vector Machine (SVM), and Feedforward Neural Network (FNN) are used to address a quality control problem involving the classification of screen-printed TiO2 electrodes based on image data. Multivariate data analysis techniques such as factor analysis were employed to evaluate the effectiveness of the features extracted from these images. Characterization techniques like FTIR, 4-point probe, and microscopy were used to study the printed electrodes and provide accurate labeling. A dataset comprising ∼300 electrodes was created to train the AI models. The SVM model demonstrated the best performance, achieving 100 % accuracy and recall, followed by the FNN model with 99 % accuracy. Models were optimized and accelerated through feature engineering and extraction techniques, allowing them to be trained in under 1 min. This rapid training capability makes these models highly suitable for real-world quality control applications where hundreds of electrodes are produced per minute.http://www.sciencedirect.com/science/article/pii/S2590048X25000378Machine learningQuality controlArtificial intelligence in manufacturingScreen printingElectrodesRandom forest |
| spellingShingle | Anesu Nyabadza Lola Azoulay-Younes Mercedes Vazquez Dermot Brabazon Machine learning-based process quality control of screen-printed titanium dioxide electrodes Results in Materials Machine learning Quality control Artificial intelligence in manufacturing Screen printing Electrodes Random forest |
| title | Machine learning-based process quality control of screen-printed titanium dioxide electrodes |
| title_full | Machine learning-based process quality control of screen-printed titanium dioxide electrodes |
| title_fullStr | Machine learning-based process quality control of screen-printed titanium dioxide electrodes |
| title_full_unstemmed | Machine learning-based process quality control of screen-printed titanium dioxide electrodes |
| title_short | Machine learning-based process quality control of screen-printed titanium dioxide electrodes |
| title_sort | machine learning based process quality control of screen printed titanium dioxide electrodes |
| topic | Machine learning Quality control Artificial intelligence in manufacturing Screen printing Electrodes Random forest |
| url | http://www.sciencedirect.com/science/article/pii/S2590048X25000378 |
| work_keys_str_mv | AT anesunyabadza machinelearningbasedprocessqualitycontrolofscreenprintedtitaniumdioxideelectrodes AT lolaazoulayyounes machinelearningbasedprocessqualitycontrolofscreenprintedtitaniumdioxideelectrodes AT mercedesvazquez machinelearningbasedprocessqualitycontrolofscreenprintedtitaniumdioxideelectrodes AT dermotbrabazon machinelearningbasedprocessqualitycontrolofscreenprintedtitaniumdioxideelectrodes |