Integrating Production and Quality Data for Defect Analysis in the Agri Food Industry: A Data-Driven Approach
Main Article Content
Abstract
Quality control in food manufacturing requires robust analytical frameworks to identify defect patterns and their underlying causes. This study integrates Statistical Process Control (SPC) and multiple regression analysis to examine the relationship between production factors and defect rates in a food manufacturing facility. Objective to identify production factors contributing to quality control failures and validate the convergence between SPC signals and regression-based predictions. Methods A 30-day longitudinal study was conducted using complete census sampling (N=30). Daily defect rates were analyzed using p-chart control limits (3σ) following ISO 7870-2:2013 standards. Multiple linear regression examined four predictors: production volume, processing time, shift assignment, and production line. Convergence analysis tested whether out-of-control (OOC) days exhibited significantly elevated risk factor levels compared to in-control (IC) days. Results The p-chart identified 4 OOC days (13.3%) exceeding the upper control limit of 6.27%. Multiple regression explained 47% of defect rate variance (R²=0.47, F=11.6, p<0.001). All four predictors showed significant effects: production volume (β=0.00018, p<0.001), processing time (β=0.021, p=0.022), night shift (β=0.317, p=0.028), and Line B (β=0.286, p=0.030). Convergence analysis revealed OOC days had significantly higher production volume (+23.4%, p<0.001), processing time (+17.3%, p<0.001), night shift prevalence (+366.7%, p=0.009), and Line B usage (+180%, p=0.048). Risk factor accumulation averaged 2.60 factors on OOC days versus 0.60 on IC days. Conclusion: The convergence between SPC signals and regression predictions validates an integrated quality control framework. High production volume combined with extended processing time, night shift operations, and specific production line usage significantly increases defect probability, requiring targeted interventions.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Ahmed, S., Rahman, M. M., & Hasan, M. (2024). Artificial intelligence and data analytics applications in food safety and quality management: A systematic review. Journal of Food Safety, 44(1), e13045.
Ali, M., Khan, S., & Imran, M. (2021). Artificial intelligence-based quality inspection systems in food manufacturing: A review. Trends in Food Science & Technology, 110, 266–279.
Chen, Y., & Yu, H. (2022). Quality analytics and statistical process control for defect detection in food production. Computers and Industrial Engineering, 168, 108060.
Faisal, A., Rahmawati, D., & Pratama, R. (2025). Failure mode and effect analysis for quality improvement in food SMEs. Journal of Quality Engineering and Production Optimization, 9(1), 15–27.
Fitriana, N., Mahendra, R., & Sari, D. (2023). Analysis of defect rates in Indonesian food SMEs using statistical quality control. Jurnal Teknologi dan Industri Pangan, 34(2), 145–154.
Gaye, S., Ndiaye, M., & Fall, A. (2025). Data-driven quality control systems in the food industry: Challenges and opportunities. Food Control, 156, 110021.
Jedrusiak, A., & Weichert, F. (2020). Detection of foreign objects in food using machine vision techniques. Journal of Food Engineering, 278, 109939.
Lian, J. (2024). Proactive quality assurance frameworks in food manufacturing: A data integration perspective. International Journal of Quality & Reliability Management, 41(3), 512–529.
Mahendra, R., Fitriana, N., & Putri, A. (2023). Human, machine, material, and method factors influencing defects in food production. Journal of Manufacturing Systems, 69, 220–230.
Martínez, P., Gomez, R., & Silva, L. (2025). Food recall trends and contamination risks: Evidence from FDA reports. Food Policy, 124, 102589.
Nair, R., Kumar, S., & Patel, V. (2023). Non-conformity and quality compliance challenges in small-scale food manufacturing. Food Quality and Safety, 7, fyad019.
Psomas, E. L., & Fotopoulos, C. V. (2010). Total quality management practices and results in food companies. International Journal of Productivity and Performance Management, 59(7), 668–687.
Psomas, E. L., Kafetzopoulos, D. P., & Gotzamani, K. D. (2014). Determinants of quality management effectiveness in the food industry. International Journal of Quality & Reliability Management, 31(6), 686–706.
Retnowati, R., Sari, M., & Nugroho, A. (2022). Six Sigma implementation to improve production quality in food manufacturing. Journal of Industrial Engineering and Management, 15(2), 345–360.
Sugarindra, M. (2025). Application of statistical quality control for defect reduction in food processing industries. Journal of Food Quality Management, 12(1), 1–12.
Vanany, I., Tan, K. H., & Siswanto, N. (2020). Managing non-conformity risks in food supply chains. Supply Chain Management: An International Journal, 25(5), 651–664.
Yu, Z., Jung, J., & Kim, J. (2020). Blockchain-based real-time data integration for food safety management. Computers and Electronics in Agriculture, 176, 105709.
Zhao, X., Li, Y., & Wang, J. (2022). AI-enabled defect prediction in food manufacturing systems. Expert Systems with Applications, 187, 115880.
Zhu, Q., Liu, J., & Lai, K. H. (2021). Data analytics-driven quality performance in food manufacturing. International Journal of Production Economics, 235, 108102.