This paper presents the design and implementation of a shadow-type digital twin applied to an automated industrial cell for printed circuit board (PCB) processing. The physical system, briefly described for contextual purposes, consists of an integrated robotic cell with CNC routing stations and multi-axis manipulators responsible for material handling and tray exchange. This setup serves as the real-world asset for validating the proposed digital twin architecture.

The core contribution of this work lies in the development of a digital twin based on the shadowing paradigm, in which operational data, process states, and event-driven information are continuously mirrored from the physical system to a virtual environment in real time. Unlike simulation-oriented or predictive digital twin approaches, the proposed model prioritizes high-fidelity synchronization between the physical asset and its digital counterpart, without exerting control over the production process. This strategy enables accurate process virtualization, state tracking, and historical memory construction while preserving system autonomy and operational safety.

The implemented digital twin provides enhanced capabilities for monitoring, traceability, and performance assessment, supporting data-driven analysis and decision-making at the supervisory level. Experimental observations indicate that the proposed approach improves operational transparency and establishes a scalable foundation for future extensions, including predictive maintenance, process optimization, and deeper integration with Industry 4.0 architectures. The results demonstrate that shadow-type digital twins represent a practical and effective solution for virtualizing complex industrial systems without disrupting existing control structures.

Surface-Mount Technology (SMT) manufacturing demands high operational reliability, as unexpected failures lead to costly production downtime. Predictive maintenance based on continuous sensor monitoring has emerged as a promising approach to anticipate failures; however, its effectiveness depends on robust and stable anomaly detection systems. In this industrial context, anomaly detection faces specific challenges, including the absence of labeled data for supervised training, the presence of multiple operational regimes with distinct electrical characteristics, and the need for temporal stability in alarm generation. Traditional global methods such as Isolation Forest, One-Class SVM (OCSVM), and Local Outlier Factor (LOF) assume a single operational context, failing to adapt detection behavior across different regimes and often producing unstable alarms that undermine system reliability.

This work proposes a hybrid, context-aware approach that combines K-Means clustering for the automatic segmentation of operational regimes with cluster-specific Isolation Forest models for anomaly detection. The method was validated using 47,493 samples of electrical sensor data (15 variables) collected over three months from an SMT insertion machine operating in a real production environment. The proposed approach was compared against three baselines: global Isolation Forest, K-Means with OCSVM, and K-Means with LOF. Performance was evaluated in terms of regime separability (Silhouette score), temporal stability (coefficient of variation), and anomaly score consistency (interquartile range).

The hybrid method identified three distinct operational contexts, achieving 53% higher separability than the global approach (Silhouette 0.63 vs. 0.41) and 37% greater temporal stability compared to global Isolation Forest (CV 0.96 vs. 1.52), effectively reducing erratic alarm peaks. Score consistency was substantially higher than OCSVM-based clustering (IQR 0.10 vs. 5.31), while maintaining an equivalent detection rate of 1.0%, confirming that performance gains arise from contextual adaptation rather than sensitivity increase.

These results demonstrate that adapting anomaly detection to operational regimes provides a methodological advantage for industrial predictive maintenance, balancing temporal stability and sensitivity in continuous monitoring.

Kurut is a traditional fermented dairy product that has been produced and consumed for centuries in Central Asia. Its dried form provides a long shelf life and ease of storage, which historically made it suitable for nomadic and semi-nomadic lifestyles. The name kurut originates from the Uzbek verb meaning to dry, emphasizing dehydration as the key technological stage of production [1].

From a nutritional standpoint, kurut is a concentrated dairy product containing proteins, minerals, vitamins, and bioactive compounds formed during fermentation. Low moisture content contributes to product stability and reduces the need for chemical preservatives. Despite these advantages, the basic technological principles of kurut production have changed little over time and remain largely based on manual operations.

One of the most critical stages of traditional kurut production is shaping. This operation is commonly performed by hand, resulting in variations in size, geometry, and surface characteristics of the final product. Manual handling also increases labor intensity and creates direct contact between the product and the surrounding environment, which raises the risk of microbiological contamination. These factors limit productivity and complicate compliance with modern hygienic and sanitary requirements.

In recent years, growing consumer demand for safe, standardized, and industrially scalable traditional foods has highlighted the need for technological modernization. The automation of key production stages is considered an effective approach to improving process efficiency, reducing human involvement, and ensuring reproducible product quality. Controlled processing conditions also allow better protection of the product from external contamination [2].

The objective of the present study is to further develop and evaluate an automated apparatus for kurut production based on previously proposed design concepts. Particular attention is given to the shaping stage, process stability, and hygienic safety. The proposed system aims to reduce labor intensity, improve the uniformity of the final product, and create a controlled processing environment overall [3].