Predictive Modeling of Packaging Seal Strength: A Hybrid Vision and Process Data Approach for Non-Destructive Quality Assurance
Source abstract
Abstract
A method for quality inspection of food packaging based on hybrid imaging and machine-learning techniques is presented. The proposed inspection system integrates thermal and visible-light imaging, enabling detection and classification of faults such as weak seals, creases and contamination. For the purpose of the study data acquisition is automated with the use of an industrial manipulator, ensuring repeatability and consistent positioning of samples. Using the acquired images, the temperature distribution in the sealing area and selected process parameters, a predictive model for burst-pressure testing was developed. The proposed workflow includes attribute selection, hyperparameter optimization and the application of regression algorithms. The proof-of-concept results demonstrate a strong alignment between predicted and measured values, as well as high model stability. The best-performing model, ElasticNet, achieved an R2 of 0.815 and an MAE of 0.028 kgf/cm2, confirming its potential for non-destructive quality control of packaging.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Material Properties and Processing · Industrial Vision Systems and Defect Detection · Spectroscopy and Chemometric Analyses
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Łukasiewicz Research Network—Institute for Sustainable Technologies, K. Pułaskiego 6/10, 26-600 Radom, Poland
Department of Applied Mechanics and Robotics, Faculty of Mechanical Engineering and Aeronautics, Rzeszow University of Technology, al. Powstańców Warszawy 8, 35-959 Rzeszów, Poland
Funding
Polish Ministry of Science and Higher Education
References (40)
Show source-provided references
1. D’Almeida, A.P., and de Albuquerque, T.L. (2024). Innovations in Food Packaging: From Bio-Based Materials to Smart Packaging Systems. Processes, 12.10.20944/preprints202409.1036.v1 ↗
2. Understanding the factors affecting the seal integrity in heat sealed flexible food packages: A review10.1002/pts.2564 ↗
3. Deep Learning for the Quality Control of Thermoforming Food Packages10.1038/s41598-021-01254-x ↗
4. (2025, October 07). Inspecting Transparent Materials for Material Defects—Vision Development Module. NI.com. Available online: https://www.ni.com/en/shop/data-acquisition-and-control/add-ons-for-data-acquisition-and-control/what-is-vision-development-module/inspecting-transparent-materials-for-material-defects.html.
5. Benouis, M., Medus, L.D., Saban, M., Ghemougui, A., and Rosado-Muñoz, A. (2021). Food Tray Sealing Fault Detection in Multi-Spectral Images Using Data Fusion and Deep Learning Techniques. J. Imaging, 7.10.3390/jimaging7090186 ↗
6. (2025, October 07). Case Study: 3D Vision Automates Inspection of Heat-Sealed Bags in Food Processing Industry. Manufacturing.net, Available online: https://www.manufacturing.net/home/article/13164990/case-study-3d-vision-automates-inspection-of-heatsealed-bags-in-food-processing-industry.
7. 3D Imaging Methods in Quality Inspection Systems
8. Infrared Thermography for Seal Defects Detection on Packaged Products: Unbalanced Machine Learning Classification with Iterative Digital Image Restoration
9. Hao, Z., Chen, Y., Yu, Z., Qian, Y., and Zhao, L. (2025). Thermal Imaging-Based Defect Detection Method for Aluminum Foil Sealing Using EAC-Net. Appl. Sci., 15.10.3390/app15189964 ↗
10. Sioma, A. (2023). Vision System in Product Quality Control Systems. Appl. Sci., 13.10.3390/app13020751 ↗
11. Applications of Artificial Intelligence and Machine Learning in Food Quality Control and Safety Assessment10.1007/s12393-023-09363-1 ↗
12. Deep learning-based production forecasting in manufacturing: A packaging equipment case study10.1016/j.promfg.2020.01.033 ↗
13. Cutulenco, G., Ciceri, M., and Biron, J. (2025, October 07). Predictive Quality: The Future of Quality in Manufacturing. Available online: https://acerta.ai.
14. Liakos, K.G., Athanasiadis, V., Bozinou, E., and Lalas, S.I. (2025). Machine Learning for Quality Control in the Food Industry: A Review. Foods, 14.10.3390/foods14193424 ↗
15. Szybicki, D., Muszyńska, M., Pietruś, P., Burghardt, A., and Kurc, K. (2024). Creating Digital Twins of Robotic Stations Using a Laser Tracker. Electronics, 13.10.3390/electronics13214271 ↗
16. (2026, January 05). Smart Monitoring and Automated Real-Time Visual Inspection of Sealant Application (SMART-VIStA), Final Project Report. Available online: https://apps.dtic.mil/sti/citations/trecms/AD1198843.
17. Cao, Y. (2025). Multisensor Data Fusion-Driven Digital Twins in Computer Numerical Control Machining: A Review. Machines, 13.10.3390/machines13100921 ↗
18. Updating Digital Twins: Methodology for Data Accuracy Quality Control Using Machine Learning Techniques10.1016/j.compind.2023.103958 ↗
19. Multi-Wave and Hybrid Imaging Techniques: A New Direction for Nondestructive Testing and Structural Health Monitoring10.3390/s131216146 ↗
20. Automatization of Workspace Control Based on ToF Technology
21. Cinal, M., Sioma, A., and Lenty, B. (2023). The Quality Control System of Planks Using Machine Vision. Appl. Sci., 13.10.3390/app13169187 ↗
22. Waśniowska, J., and Sioma, A. (2023). Modelling the Interaction of Illuminations with a Sensor Matrix Used in Vision Systems. Appl. Sci., 13.10.3390/app131910641 ↗
23. Hyperspectral Imaging System for Food Safety Inspection
24. A Target-Oriented Image Fusion Method for Quality Inspection of Heat-Sealed Packages10.1007/978-3-032-01773-4_3 ↗
25. Madejski, G., Zbytniewski, S., Kurowski, M., Gradolewski, D., Kaoka, W., and Kulesza, W.J. (2024). Lens Distortion Measurement and Correction for Stereovision Multi-Camera System. Eng. Proc., 82.10.3390/ecsa-11-20457 ↗
26. Ajji, A., Jalali Dil, E., Saffar, A., and Kanani Aghkand, Z. (2023). Chapter 3. Seal Quality and Performance Evaluation Methods. Heat Sealing in Packaging: Materials and Process Considerations, De Gruyter.10.1515/9781501524592 ↗
27. Device for Inspection of Thermally Sealed Pouches
28. Pietrzkiewicz, P. (2025, October 07). Image Analysis Techniques for Industrial Inspection Systems; Adaptive Vision. Available online: https://www.adaptive-vision.com/download/mvg.pdf.
29. (2026, January 05). Seabron, Comparing Distributions. Available online: https://seaborn.pydata.org/.
30. Correlation and variable importance in random forests10.1007/s11222-016-9646-1 ↗
31. Artificial Intelligence-Based Techniques for Adulteration and Defect Detections in Food and Agricultural Industry: A Review
32. Ridge Regularization: An Essential Concept in Data Science10.1080/00401706.2020.1791959 ↗
33. Bhattacharyya, J. (2025). LASSO Regression—A Procedural Improvement. Psychology, Preprint.
34. Shrinkage priors for Bayesian penalized regression10.1016/j.jmp.2018.12.004 ↗
35. Machine learning analysis and simulation of pharmaceutical drying process based on prediction of concentration distribution and mass transfer10.1038/s41598-025-22276-9 ↗
36. Classification and Regression by RandomForest
37. Varma, S., and Simon, R. (2006). Bias in Error Estimation When Using Cross-Validation for Model Selection. BMC Bioinform., 7.10.1186/1471-2105-7-91 ↗
38. Internal Validation of Predictive Models: Efficiency of Some Procedures for Logistic Regression Analysis10.1016/S0895-4356(01)00341-9 ↗
39. Wen, H.-T., Wu, H.-Y., and Liao, K.-C. (2022). Using XGBoost Regression to Analyze the Importance of Input Features Applied to an Artificial Intelligence Model for the Biomass Gasification System. Inventions, 7.10.3390/inventions7040126 ↗
40. Aboneh, T., Rorissa, A., and Srinivasagan, R. (2022). Stacking-Based Ensemble Learning Method for Multi-Spectral Image Classification. Technologies, 10.10.3390/technologies10010017 ↗