A Multimodal Convolutional Neural Network Framework for Intelligent Real-Time Monitoring of Etchant Levels in PCB Etching Processes
Abstract
1. Introduction
2. Related Work
3. Materials and Methods
- Data acquisition moduleReal-time sensor measurements of etchant+ concentration are collected at regular intervals, forming a time series that captures the dynamic behavior of the etching solution.
- Preprocessing and feature constructionA reference pattern representing the normal operating state is established. In this study, a reference normal pattern can be established using domain knowledge. In the context of PCB etching, process experts can define expected Cu2+ concentration ranges based on process specifications, historical experience, or industry standards. In our study, the data are aligned with the replenishment cycle, making it essential to preserve the original sequence length. Therefore, missing or null values were not removed but imputed. Residual values are computed by comparing the observed time series against this reference. These residuals are then segmented using a sliding window approach. Each segment is transformed into two parallel data representations: the original 1D residual time series and a 2D recurrence plot, which encodes temporal recurrences and state transitions. The 1D residual time series were standardized using Z-score normalization, and the 2D recurrence plot features were scaled to [0, 1]. Scaling parameters were computed from the training set and applied to the test set to prevent information leakage. These preprocessed features were input into the multimodal CNN, where separate streams were fused in a late fusion stage, ensuring effective integration and model convergence.
- Multimodal deep learning modelA multimodal convolutional neural network is employed to classify the solution concentration status as either normal or abnormal. A 1D-CNN branch extracts temporal features from the residual time series. A 2D-CNN branch processes the recurrence plots to extract spatial recurrence patterns. The outputs from both branches are concatenated and passed through dense layers for final classification.
- Model training and evaluationThe model is trained on labeled data containing both normal and abnormal concentration patterns. We evaluated model performance using the accuracy, precision, recall, F1-score, and G-measure. The G-measure is calculated as the square root of the product of sensitivity and specificity. While the F1-score balances precision and recall, emphasizing the model’s ability to correctly identify positive instances, the G-measure—defined as the geometric mean of recall and specificity—captures performance across both positive and negative classes. This makes it particularly valuable in imbalanced classification scenarios. A large discrepancy between the F1-score and G-measure indicates class-dependent behavior, suggesting that the confusion matrix should be examined to determine which class is being favored or overlooked.
- Online monitoring and decision supportOnce deployed, the framework continuously receives incoming sensor data, performs real-time classification, and triggers alerts when abnormal concentration trends are detected. This enables operators to take timely corrective actions, such as replenishing the etching solution or inspecting the chemical delivery mechanism.
3.1. Process Description and Data Collection
- A sudden increase in Cu2+ concentration may result from a higher number of boards being processed. Currently, the dosing formula does not account for the actual board count. The countermeasure is to revise the dosing formula.
- A sudden drop in Cu2+ concentration may be caused by improperly installed rollers, which allow water from the upstream tank to be carried into the micro-etching tank along with the boards, thereby diluting the Cu2+ concentration. The countermeasure is to inspect whether the rollers are operating smoothly or exhibit any wobbling.
- If the rate of Cu2+ concentration increase changes, one possible reason is a decrease in the number of boards being processed, which slows down the rate of Cu2+ increase. The countermeasure is to revise the dosing formula. If the board quantity has not decreased, then a possible reason could be a malfunction in the electrodes. In this case, the recommended countermeasure is to inspect whether the electrodes are functioning properly.
3.2. Recurrence Plot
3.3. Multimodal CNN Architecture
4. Experimental Setup and Implementation
Data Description and Preprocessing
5. Results and Discussion
6. Conclusions and Future Work
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Fawaz, H.I.; Forestier, G.; Weber, J.; Idoumghar, L.; Muller, P.A. Deep learning for time series classification: A review. Data Min. Knowl. Discov. 2019, 33, 917–963. [Google Scholar] [CrossRef]
- Taherkhani, A.; Cosma, G.; McGinnity, T.M. A deep convolutional neural network for time series classification with intermediate targets. SN Comput. Sci. 2023, 4, 832. [Google Scholar] [CrossRef]
- Wang, W.K.; Chen, I.; Hershkovich, L.; Yang, J.; Shetty, A.; Singh, G.; Jiang, Y.; Kotla, A.; Shang, J.Z.; Yerrabelli, R.; et al. A systematic review of time series classification techniques used in biomedical applications. Sensors 2022, 22, 8016. [Google Scholar] [CrossRef] [PubMed]
- Maden, E.; Karagoz, P. Enhancements for sliding window based stream classification. In Proceedings of the 11th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2019), Vienna, Austria, 17–19 September 2019. [Google Scholar] [CrossRef]
- Huang, Y.; Zheng, J.; Xu, B.; Li, X.; Liu, Y.; Wang, Z.; Feng, H.; Cao, S. An improved model using convolutional sliding window-attention network for motor imagery EEG classification. Front. Neurosci. 2023, 17, 1204385. [Google Scholar] [CrossRef]
- Chen, W.; Zheng, P.; Bu, Y.; Xu, Y.; Lai, D. Achieving real-time prediction of paroxysmal atrial fibrillation onset by convolutional neural network and sliding window on R-R interval sequences. Bioengineering 2024, 11, 903. [Google Scholar] [CrossRef]
- Falih, B.S.; Sabir, M.K.; Aydın, A. Impact of sliding window overlap ratio on EEG-based ASD diagnosis using brain hemisphere energy and machine learning. Appl. Sci. 2024, 14, 11702. [Google Scholar] [CrossRef]
- Song, W.; Wu, T.; Zhang, Y. A segmented sliding window-based comprehensive periodic feature extraction method for APT classification. In Proceedings of the 2024 IEEE 18th International Conference on Control & Automation (ICCA), Reykjavík, Iceland, 18–21 June 2024. [Google Scholar] [CrossRef]
- Botros, J.; Mourad-Chehade, F.; Laplanche, D. Explainable multimodal data fusion framework for heart failure detection: Integrating CNN and XGBoost. Biomed. Signal Process. Control 2025, 100, 106997. [Google Scholar] [CrossRef]
- Xing, Z.; Ma, G.; Wang, L.; Yang, L.; Guo, X.; Chen, S. Toward visual interaction: Hand segmentation by combining 3-D graph deep learning and laser point cloud for intelligent rehabilitation. IEEE Internet Things J. 2025, 12, 21328–21338. [Google Scholar] [CrossRef]
- Hatami, N.; Gavet, Y.; Debayle, J. Classification of time-series images using deep convolutional neural networks. In Proceedings of the 10th International Conference on Machine Vision (ICMV 2017), Vienne, Austria, 13–15 November 2017. [Google Scholar] [CrossRef]
- Gao, J.; Li, P.; Chen, Z.; Zhang, J. A survey on deep learning for multimodal data fusion. Neural Comput. 2020, 32, 829–864. [Google Scholar] [CrossRef]
- Sleeman, W.C.; Kapoor, R.; Ghosh, P. Multimodal classification: Current landscape, taxonomy and future directions. ACM Comput. Surv. 2022, 55, 1–31. [Google Scholar] [CrossRef]
- Callegari, M.; Carbonari, L.; Costa, D.; Palmieri, G.; Palpacelli, M.C.; Papetti, A.; Scoccia, C. Tools and methods for human robot collaboration: Case studies at i-labs. Machines 2022, 10, 997. [Google Scholar] [CrossRef]
- Mosqueira-Rey, E.; Hernández-Pereira, E.; Alonso-Ríos, D.; Bobes-Bascarán, J.; Fernández-Leal, A. Human-in-the-loop machine learning: A state of the art. Artif. Intell. Rev. 2023, 56, 3005–3054. [Google Scholar] [CrossRef]
- Ranipa, K.; Zhu, W.P.; Swamy, M.N.S. Multimodal CNN fusion architecture with multi-features for heart sound classification. In Proceedings of the 2021 IEEE International Symposium on Circuits and Systems (ISCAS), Daegu, Republic of Korea, 22–28 May 2021. [Google Scholar] [CrossRef]
- Ha, S.; Yun, J.M.; Choi, S. Multimodal convolutional neural networks for activity recognition. In Proceedings of the 2015 IEEE International Conference on Systems, Man, and Cybernetics, Hong Kong, China, 9–12 October 2015. [Google Scholar] [CrossRef]
- Ha, S.; Choi, S. Convolutional neural networks for human activity recognition using multiple accelerometer and gyroscope sensors. In Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada, 24–29 July 2016. [Google Scholar] [CrossRef]
- Radu, V.; Tong, C.; Bhattacharya, S.; Lane, N.D.; Mascolo, C.; Marina, M.K.; Kawsar, F. Multimodal deep learning for activity and context recognition. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 2018, 1, 1–27. [Google Scholar] [CrossRef]
- Cao, M.; Wan, J.; Gu, X. CLEAR: Multimodal human activity recognition via contrastive learning based feature extraction refinement. Sensors 2025, 25, 896. [Google Scholar] [CrossRef] [PubMed]
- Adarsh, V.; Gangadharan, G.R.; Fiore, U.; Zanetti, P. Multimodal classification of Alzheimer’s disease and mild cognitive impairment using custom MKSCDDL kernel over CNN with transparent decision-making for explainable diagnosis. Sci. Rep. 2024, 14, 1774. [Google Scholar] [CrossRef]
- Alorf, A. Transformer and convolutional neural network: A hybrid model for multimodal data in multiclass classification of Alzheimer’s disease. Mathematics 2025, 13, 1548. [Google Scholar] [CrossRef]
- Chen, J.; Wang, Y.; Zeb, A.; Suzauddola, M.D.; Wen, Y. Multimodal mixing convolutional neural network and transformer for Alzheimer’s disease recognition. Expert Syst. Appl. 2025, 259, 125321. [Google Scholar] [CrossRef]
- Muksimova, S.; Umirzakova, S.; Baltayev, J.; Cho, Y.I. Multi-modal fusion and longitudinal analysis for Alzheimer’s disease classification using deep learning. Diagnostics 2025, 15, 717. [Google Scholar] [CrossRef] [PubMed]
- Khan, M.A.; Ashraf, I.; Alhaisoni, M.; Damaševičius, R.; Scherer, R.; Rehman, A.; Bukhari, S.A.C. Multimodal brain tumor classification using deep learning and robust feature selection: A machine learning application for radiologists. Diagnostics 2020, 10, 565. [Google Scholar] [CrossRef]
- Qu, R.; Xiao, Z. An attentive multi-modal CNN for brain tumor radiogenomic classification. Information 2022, 13, 124. [Google Scholar] [CrossRef]
- Rohini, A.; Praveen, C.; Mathivanan, S.K.; Muthukumaran, V.; Mallik, S.; Alqahani, M.S.; AI-Rasheed, A.; Soufiene, B.O. Multimodal hybrid convolutional neural network based brain tumor grade classification. BMC Bioinform. 2023, 24, 382. [Google Scholar] [CrossRef]
- Jiang, H.; Liu, L.; Lian, C. Multi-modal fusion transformer for multivariate time series classification. In Proceedings of the 14th International Conference on Advanced Computational Intelligence (ICACI), Wuhan, China, 15–17 July 2022. [Google Scholar] [CrossRef]
- Moroto, Y.; Maeda, K.; Togo, R.; Ogawa, T.; Haseyama, M. Multimodal transformer model using time-series data to classify winter road surface conditions. Sensors 2024, 24, 3440. [Google Scholar] [CrossRef]
- Sadras, N.; Pesaran, B.; Shanechi, M.M. Event detection and classification from multimodal time series with application to neural data. J. Neural Eng. 2024, 21, 026049. [Google Scholar] [CrossRef]
- Liu, C.; Wei, Z.; Zhou, L.; Shao, Y. Multidimensional time series classification with multiple attention mechanism. Complex Intell. Syst. 2025, 11, 14. [Google Scholar] [CrossRef]
- Pei, X.; Zuo, K.; Li, Y.; Pang, Z. A review of the application of multi-modal deep learning in medicine: Bibliometrics and future directions. Int. J. Comput. Intell. Syst. 2023, 16, 44. [Google Scholar] [CrossRef]
- El Sakka, M.; Ivanovici, M.; Chaari, L.; Mothe, J. A Review of CNN Applications in smart agriculture using multimodal data. Sensors 2025, 25, 472. [Google Scholar] [CrossRef] [PubMed]
- Bhrad, F.; Abadeh, M.S. An overview of deep learning methods for multimodal medical data mining. Expert Syst. Appl. 2022, 200, 117006. [Google Scholar] [CrossRef]
- Jabeen, S.; Li, X.; Amin, M.S.; Bourahla, O.; Li, S.; Jabbar, A. A review on methods and applications in multimodal deep learning, ACM Trans. Multimed. Comput. Commun. Appl. 2023, 19, 1–41. [Google Scholar] [CrossRef]
- Tang, Q.; Liang, J.; Zhu, F. A comparative review on multi-modal sensors fusion based on deep learning. Signal Process. 2023, 213, 109165. [Google Scholar] [CrossRef]
- Montgomery, D.C. Introduction to Statistical Quality Control, 8th ed.; John Wiley & Sons: Hoboken, NJ, USA, 2020. [Google Scholar]
- Eckmann, J.P.; Kamphorst, O.S.; Ruelle, D. Recurrence plots of dynamical systems. Europhys. Lett. 1987, 4, 973–977. [Google Scholar] [CrossRef]
- Silva, D.F.; de Souza, V.M.A.; Batista, G.E.A.P.A. Time Series Classification Using Compression Distance of Recurrence Plots. In Proceedings of the IEEE 13th International Conference on Data Mining, Dallas, TX, USA, 7–10 December 2013; pp. 687–696. [Google Scholar] [CrossRef]
- Sipers, A.; Borm, P.; Peeters, R. On the unique reconstruction of a signal from its unthresholded recurrence plot. Phys. Lett. A 2011, 375, 2309–2321. [Google Scholar] [CrossRef]
- Iwanski, J.S.; Bradley, E. Recurrence plots of experimental data: To embed or not to embed? Chaos 1998, 8, 861–871. [Google Scholar] [CrossRef]
- Kiranyaz, S.; Avci, O.; Abdeljaber, O.; Ince, T.; Gabbouj, M.; Inman, D.J. 1D convolutional neural networks and applications: A survey. Mech. Syst. Signal Process. 2021, 151, 107398. [Google Scholar] [CrossRef]
- Vaezi Joze, H.R.; Shaban, A.; Iuzzolino, M.L.; Koishida, K. MMTM: Multimodal transfer module for CNN fusion. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 13–19 June 2020. [Google Scholar] [CrossRef]
- Jaafar, N.; Lachiri, Z. Multimodal fusion methods with deep neural networks and meta-information for aggression detection in surveillance. Expert Syst. Appl. 2023, 211, 118523. [Google Scholar] [CrossRef]
- Cheng, S.; Hou, R.; Li, M. The fusion strategy of multimodal learning in image and text recognition. In Proceedings of the 2024 International Conference on Physics, Photonics, and Optical Engineering (ICPPOE 2024), Singapore, 8–10 November 2024. [Google Scholar] [CrossRef]
- Pereira, L.M.; Salazar, A.; Vergara, L. A comparative analysis of early and late fusion for the multimodal two-class problem. IEEE Access 2023, 11, 84283–84300. [Google Scholar] [CrossRef]
- Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; et al. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 2011, 12, 2825–2830. [Google Scholar]
- Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
- Chen, T.; Guestrin, F. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016. [Google Scholar]
- Vapnik, V.N. Support-Vector Networks. Mach. Learn. 1995, 20, 273–297. [Google Scholar] [CrossRef]
- Chollet, F. Keras. 2015. Available online: https://github.com/keras-team/keras (accessed on 5 July 2025).
Algorithms | Accuracy | Precision | Recall | F1-Score | G-Mean |
---|---|---|---|---|---|
RF | 79.45 | 82.29 | 76.46 | 80.58 | 86.36 |
(1.02) | (1.39) | (1.35) | (1.39) | (1.41) | |
XGB | 81.25 | 82.93 | 76.84 | 77.69 | 84.25 |
(1.59) | (1.68) | (1.75) | (1.59) | (1.62) | |
MLP | 84.51 | 86.01 | 83.51 | 84.26 | 89.38 |
(1.91) | (1.86) | (1.91) | (1.89) | (1.98) | |
SVC | 86.35 | 89.04 | 84.51 | 85.95 | 89.82 |
(1.12) | (1.11) | (1.12) | (1.25) | (1.27) | |
1D CNN | 95.41 | 94.48 | 95.51 | 95.46 | 94.49 |
(0.53) | (0.49) | (0.52) | (0.51) | (0.49) | |
2D CNN | 92.73 | 92.75 | 93.96 | 93.42 | 95.62 |
(0.95) | (0.95) | (0.74) | (0.52) | (0.51) | |
Multimodal CNN | 98.36 | 98.41 | 98.44 | 98.42 | 99.13 |
(0.36) | (0.32) | (0.31) | (0.32) | (0.31) |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Cheng, C.-S.; Chen, P.-W.; Jen, H.-Y.; Wu, Y.-T. A Multimodal Convolutional Neural Network Framework for Intelligent Real-Time Monitoring of Etchant Levels in PCB Etching Processes. Mathematics 2025, 13, 2804. https://doi.org/10.3390/math13172804
Cheng C-S, Chen P-W, Jen H-Y, Wu Y-T. A Multimodal Convolutional Neural Network Framework for Intelligent Real-Time Monitoring of Etchant Levels in PCB Etching Processes. Mathematics. 2025; 13(17):2804. https://doi.org/10.3390/math13172804
Chicago/Turabian StyleCheng, Chuen-Sheng, Pei-Wen Chen, Hen-Yi Jen, and Yu-Tang Wu. 2025. "A Multimodal Convolutional Neural Network Framework for Intelligent Real-Time Monitoring of Etchant Levels in PCB Etching Processes" Mathematics 13, no. 17: 2804. https://doi.org/10.3390/math13172804
APA StyleCheng, C.-S., Chen, P.-W., Jen, H.-Y., & Wu, Y.-T. (2025). A Multimodal Convolutional Neural Network Framework for Intelligent Real-Time Monitoring of Etchant Levels in PCB Etching Processes. Mathematics, 13(17), 2804. https://doi.org/10.3390/math13172804