DIGITAL QUALITY MANAGEMENT LOOP BASED ON KPI, CAPA AND ARTIFICIAL INTELLIGENCE AT A NUCLEAR INDUSTRY ENTERPRISE

The article presents a methodological approach to the development of a digital quality management loop at a nuclear industry enterprise based on KPI standardization, management of corrective and preventive actions (CAPA), and the use of artificial intelligence analytical tools. The study is based on data for 2020-2024, including occupational health and industrial safety indicators, LTIFR, dose monitoring of Group A personnel, environmental indicators, as well as a scenario-based economic assessment of the implementation of the digital quality loop.

It is shown that safety, radiation and environmental monitoring indicators can be considered practical metrics of the stability of the quality management system. During the analyzed period, the number of accidents decreased from 1-2 cases in 2020-2021 to zero values in 2022-2024, while the LTIFR indicator decreased from 0.28 to 0.00. Radiation indicators remained below the control level of 10 mSv/year; however, maximum doses of up to 5.2 mSv confirm the need to manage local episodes rather than relying only on average values. Environmental KPIs demonstrate year-to-year volatility, which justifies the need for threshold control and analysis of the causes of deviations.

The paper proposes the logic of the digital loop «KPI – thresholds – deviation – CAPA – effectiveness verification – audit», in which artificial intelligence is used as an additional tool for anomaly detection, prioritization of reviews, and classification of causes. The economic assessment shows that with CAPEX of 30 million tenge and OPEX of 6 million tenge per year, the estimated payback period is approximately 1.67 years, and about 2.5 years in the conservative scenario. The obtained results confirm the feasibility of a phased implementation of the digital quality loop: from data and CAPA standardization to analytics and predictive models.

1. Gueorguiev T. An approach to integrate Artificial Intelligence in ISO 9001-based quality management systems / T. Gueorguiev // Measurement: Sensors. – 2025. – Article 101787. https://doi.org/10.1016/j.measen.2024.101787.

2. The Quality 4.0 Roadmap: Designing a capability roadmap toward quality management in Industry 4.0 / A.M. Carvalho et al // Quality Management Journal. – 2024. – Vol. 31(2). – P. 117-137. https://doi.org/10.1080/10686967.2024.2317478.

3. Sader S. A review of quality 4.0: definitions, features, technologies, applications, and challenges / S. Sader, I. Husti, M. Daroczi // Total Quality Management & Business Excellence. – 2022. – Vol. 33(9-10). – P. 1164-1182. https://doi.org/10.1080/14783363.2021.1944082.

4. Tercan H. Machine learning and deep learning based predictive quality in manufacturing: a systematic review / H. Tercan, T. Meisen // Journal of Intelligent Manufacturing. – 2022. – Vol. 33. – P. 1879-1905. https://doi.org/10.1007/s10845-022-01963-8.

5. Artificial Intelligence in manufacturing: State of the art, perspectives, and future directions / R.X. Gao et al // CIRP Annals. – 2024. – Vol. 73(2). – P. 723-749. https://doi.org/10.1016/j.cirp.2024.04.101.

6. A review of explainable artificial intelligence in smart manufacturing / A. Puthanveettil Madathil et al // International Journal of Production Research. – 2025. – Vol. 63(23). – P. 8654-8697. https://doi.org/10.1080/00207543.2025.2513574.

7. Human-in-the-loop machine learning: a state of the art / E. Mosqueira-Rey et al // Artificial Intelligence Review. – 2023. – Vol. 56. – P. 3005-3054. https://doi.org/10.1007/s10462-022-10246-w.

8. Data Quality Assessment in Smart Manufacturing: A Review / T. Peixoto et al // Systems. – 2025. – Vol. 13(4), Article 243. https://doi.org/10.3390/systems13040243.

9. Data governance & quality management-Innovation and breakthroughs across different fields / B.M.V. Bernardo et al // Journal of Innovation & Knowledge. – 2024. – Vol. 9(4), Article 100598. https://doi.org/10.1016/j.jik.2024.100598.

10. Arunagiri T. Enhancing Pharmaceutical Product Quality With a Comprehensive Corrective and Preventive Actions (CAPA) Framework: From Reactive to Proactive / T. Arunagiri, K.P. Kannaiah, M. Vasanthan // Cureus. – 2024. – Vol. 16(9). – P. e69762. https://doi.org/10.7759/cureus.69762.