🧪 🔬 Presented work

Paper 1. «Improving Predictive Maintenance in Bakery Digital Twins: A Hybrid Autoencoder-LSTM Framework with Adaptive Anomaly Thresholding»
Authors: Liya Bektemir Erbolkyzy, Nazly Yusubova Vidadikyzy, Bauyrzhan Amirkhanov, Gulshat Amirkhanova, Meruyert Sakypbekova

Summary: A hybrid autoencoder-LSTM (HAE-LSTM) model for predictive maintenance in a bakery digital twin. The adaptive anomaly threshold (AAT) mechanism dynamically adjusts to sensor drift, reducing false alarms in challenging production conditions.

Paper 2. «Closed-Loop Digital Twin for Energy-Efficient Scheduling in Food Manufacturing Systems»
Authors: Nazly Yusubova, Shyrailym Adilkyzy, Gulshat Amirkhanova, Alina Raeva, Bauyrzhan Amirkhanov, Baizhanova Dina

Summary: A hybrid digital twin architecture (HDTA) that combines discrete event simulation (DES), constraint programming (CP-SAT), and edge computing into a closed-loop control for energy-efficient bakery production planning.

Paper 3. «Detection of Industrial Process Anomalies Using Isolation Forest and DBSCAN in a Real Manufacturing Environment»
Authors: Shyrailym Adilkyzy, Gulshat Amirkhanova, Liya Bektemir, Bauyrzhan Amirkhanov, Tomiris Nurgazy, Alikhan Amirkhanov

Summary: A comparative analysis of two unsupervised learning algorithms, Isolation Forest and DBSCAN, for detecting anomalies in a real production environment, evaluating their effectiveness in identifying failures and determining the operating states of equipment.

Paper 4. «An AES-GCM–Based Secure Data Path for IIoT Using ESP32, MQTT, and Raspberry Pi»
Authors: Bauyrzhan Amirkhanov, Syrym Ismailov, Saltanat Adilzhanova, Alikhan Amirkhanov, Gulshat Amirkhanova, Gulnur Tyulepberdinova

Summary: A practical end-to-end secure data transfer channel for IIoT based on ESP32, MQTT, and Raspberry Pi. AES-GCM encryption at the application level protects data even from a compromised or nosy broker, where TLS only protects the transport.

Paper 5. «Web-Based Digital Twin Architecture: Integrating the Grafana Analytics Dashboard with a Unity 3D Model»
Authors: Tomiris Nurgazy, Gulshat Amirkhanova, Yem Vibol (University of Tsukuba, Япония), Yenlik Faruzkyzy, Gulnur Tyulepberdinova

Summary: A web-based digital twin architecture that combines a Grafana dashboard with a 3D model in Unity to monitor, analyze, and optimize complex physical systems.

🏆 Results of participation

• 📄 Five papers on project BR24992975 included in the CEII 2025 Proceedings
• 🌐 International co-authorship, including the University of Tsukuba (Japan)
• 🧩 A complete digital twin framework is presented: secure data transfer (AES-GCM), anomaly detection, predictive maintenance, energy-efficient planning and web visualization
• 📈 Published by CPS with indexing in EI Compendex and Scopus

📃 Publication

The articles were published in the CEII 2025 conference proceedings (Conference Publishing Services, CPS) and indexed in EI Compendex and Scopus.