VVVladimir Vychuzhanin

Vladimir Vychuzhanin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Vladimir Vychuzhanin has a total of 58 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Cumulative Thermal Accumulation in Transscleral Cyclophotocoagulation: Mathematical Modeling of Controlled Versus Destructive Thermal Effects in Secondary Neovascular Glaucoma

    by Olha Guzun, Petro Osadchuk, Volodymyr Vychuzhanin, Andrii Khomenko, Valeriu Cusnir

    Purpose. To quantitatively characterize the cumulative thermal dynamics of ciliary body tissue during serial transscleral cyclophotocoagulation and to evaluate the potential applicability of the thermal accumulation index (TAI) as a tool for predicting controlled coagulative and potentially destructive thermal effects in secondary neovascular glaucoma. Methods. Stepwise mathematical modeling of serial transscleral cyclophotocoagulation (20 applications of 2 s with 1 s inter-application intervals) was performed. For each cycle, initial tissue temperature (Tstart), maximum temperature (Tmax), temperature rise (ΔT), and inter-application heat loss (HeatLoss) were determined. Total time within coagulative (50–60 °C) and destructive (>60 °C) temperature ranges, as well as the area under the temperature curve within the coagulative range (AUTC), were assessed. The thermal accumulation index (TAI) was calculated as the mean increase of the initial temperature above the baseline level of 37 °C. Additional threshold and scenario analyses were performed by varying laser exposure parameters. Results. Serial laser exposure produced cumulative thermal dynamics characterized by gradual elevation of baseline tissue temperature from 37.0 °C to 42.7 °C. The cumulative temperature increase reached 57.0 °C, corresponding to TAI = 2.85 °C and indicating controlled thermal accumulation without transition to the destructive temperature range. Analysis of thermal profiles demonstrated that shorter inter-application intervals or higher energy delivery enhanced thermal accumulation. Within the mathematical model, TAI values exceeding 4.0 °C were associated with an increased risk of tissue overheating and transition to the destructive temperature range (>60 °C). Under simulated conditions, the continuous-wave 1 W mode corresponded to a profile of controlled low-power coagulation. Conclusions. Cumulative thermal accumulation represents an important component of tissue temperature response during serial TSCPC and is determined by incomplete cooling between consecutive applications. The proposed TAI enables quantitative characterization of inter-application heat accumulation and may be considered an integral indicator of cumulative thermal dynamics under different laser exposure regimes. Under simulated conditions, the low-power continuous-wave 1 W mode provided a controlled coagulative effect without transition to the destructive temperature range, consistent with the low-dose / slow coagulation concept. The obtained findings are model-based and require further experimental and clinical validation.

  • Open Access

    Adaptive uncertainty-aware hybrid digital twin architecture for predictive diagnostics of ship power plants

    by V.V. Vychuzhanin, A.V. Vychuzhanin

    Reliable prediction of the technical condition and remaining useful life of ship power plants (SPPs) remains a challenging task because operating conditions continuously change, degradation mechanisms are highly nonlinear, and sensor measurements are inevitably affected by uncertainty. Although hybrid digital twins (HDTs) have significantly expanded the capabilities of predictive maintenance, many existing implementations still employ fixed interaction schemes between physics-based and data-driven models, reducing their adaptability when the reliability of individual information sources varies during operation. The study develops a HDT architecture that combines a deterministic physical model, a CNN–LSTM prediction module, and a cognitive simulation model (CSM) within a single diagnostic framework. Instead of maintaining a fixed balance between analytical and empirical models, the architecture continuously adjusts their contribution according to the estimated uncertainty of the physical model. This makes it possible to retain physical consistency whenever analytical knowledge is reliable while allowing data-driven prediction to dominate when model uncertainty increases. The cognitive simulation component complements numerical prediction by explicitly representing causal relationships between degradation processes and diagnostic conclusions, providing engineering explanations that are difficult to obtain from conventional deep neural networks. Performance of the developed framework was investigated using hardware-in-the-loop (HIL) simulations reproducing representative operating regimes of SPP subsystems, including progressive degradation and stochastic sensor disturbances. Under these conditions, the hybrid architecture reduced remaining useful life prediction error by 32–36% relative to standalone physics-based models and by up to 19% compared with conventional deep-learning solutions. Fault classification reached an FI-score of 0.89 while maintaining stable operation under sensor noise levels of up to 30%. Real-time inference below 20 ms satisfies the requirements of onboard automation systems, whereas asynchronous federated learning enables scalable deployment across distributed fleets without increasing onboard computational load. The combination of adaptive uncertainty-aware model fusion, physics-informed learning, and cognitive reasoning extends the capabilities of current HDT technologies beyond conventional hybrid diagnostic frameworks. Besides improving prediction accuracy and robustness, the architecture enhances transparency of maintenance decisions and demonstrates practical feasibility for intelligent SPPs, with an estimated reduction in annual operating costs of approximately 27%. These results indicate that the developed framework represents a practical step toward reliable and explainable predictive maintenance of next-generation maritime energy systems.

  • Intelligent system for analysis and assessment of population health harm risks by air pollution level

    by Nickolay Rudnichenko, Vladimir Vychuzhanin, Denys Shvedov, Natalia Shibaeva, Igor Petrov

    Air pollution by fine particulate matter (PM2.5 , PM10 ), nitrogen dioxide (NO2 ), sulfur dioxide (SO2 ), carbon monoxide (CO) and ozone (O3 ) is among the leading environmental threats to public health in densely populated urban areas, yet the tools available to health authorities rarely combine heterogeneous monitoring data with interpretable risk estimates. This paper presents an intelligent system that assigns an observation to one of six air quality index (AQI) classes, used as a proxy for the level of harm to population health, together with a comparative evaluation of the six models behind it: a decision tree, a support vector machine, a random forest, XGBoost, a convolutional neural network (CNN) and a long short-term memory (LSTM) network. All six are trained on identically preprocessed data – the Air Pollution Image Dataset from India and Nepal, cross-checked with structured measurements from two open sources – and are compared at the evaluation stage rather than chained into a sequence. The system is implemented as a client-server application with a Python and Flask backend and a React frontend, whose dashboard provides exploratory data analysis, model inference and model comparison. The random forest and the CNN are the most accurate models (accuracy 0.988 and 0.987, macro-averaged F1-score 0.987 and 0.986), followed by the LSTM network (0.980 and 0.979), whereas the single decision tree falls to 0.856 because it does not separate the two most severe classes. Average training time ranges from 3 s for the decision tree to 67 s for the LSTM network, which makes the random forest the best compromise between accuracy and computational cost.

  • Open Access

    Practical IT/OT integration of an edge-cloud hybrid digital twin for ship power plants

    by Volodymyr Vychuzhanin, Oleksiy Vychuzhanin

    The increasing complexity and stringent real-time reliability requirements of modern ship power plants (SPPs) render conventional digital twins insufficient when relying solely on either physics-based or data-driven models. Furthermore, the lack of unified IT/OT integration and semantic consistency limits their practical deployment in operational maritime environments. The aim of this study was to develop and validate a hybrid digital twin (HDT) framework that ensures adaptive modelling, semantic interoperability, and secure real-time integration within the ship’s cyber-physical infrastructure. To achieve this, a cognitively adaptive HDT architecture was proposed. It merged physics-based thermodynamic models with data-driven CNN-LSTM components via a dynamic authority-shift mechanism governed by real-time uncertainty. The framework incorporated a cognitive simulation model (CSM) based on OWL 2.0 ontologies and SWRL rules for the semantic validation of physical constraints directly within the operational loop. Additionally, a semantic-functional dual exchange (SFDX) protocol was introduced to unify physical telemetry and ontological descriptors. This integration of cognitive validation and dynamic model balancing ensured robust operation under sensor degradation and cyber-physical disturbances. Experimental validation was performed using a Hardware-in-the-Loop testbed simulating real SPP conditions. The results demonstrated stable operation exceeding 10⁴ messages per second, with end-to-end latency below 0.25 seconds and data loss under 0.3%. The hybrid model reduced mean remaining useful life prediction error by 20-25% compared to standalone approaches, maintaining physical-semantic consistency below a 3% deviation threshold. Architectural evaluation confirmed the effectiveness of a distributed onboard-edge-cloud paradigm, executing real-time control locally while delegating computationally intensive retraining to higher tiers. The proposed framework established a scalable foundation for trustworthy and cognitively integrated SPP digital twins (DTs)

  • Open Access

    Selective transscleral cyclophotocoagulation: mathematical modeling for evaluating the efficacy-safety balance in neovascular glaucoma

    by Olga Guzun, Oleg Zadorozhnyy, Petr Osadchuk, Vladimir Vychuzhanin, Andrii Khomenko, Andrii Korol

    Purpose. To quantitatively evaluate the efficacy-safety balance of transscleral cyclophotocoagulation (TSCPC) through a mathematical modeling-based analysis of thermal tissue response in the ciliary body, and to determine the laser exposure parameters for achieving a selective coagulation effect in neovascular glaucoma (NVG). Material and Methods. A model of heat transfer in the ciliary body was developed using the Pennes bioheat transfer equation. Continuous Wave (CW) TSCPC and MicroPulse TSCPC at 1 W and 2W for a single 2-s application and a series of 2-s applications were subjected to analysis. The following parameters were determined: maximum temperature (Tmax), time to reach 50 °C (t50), time in the temperature range 50–60 °C (t50-60), and time in the temperature range above 60 °C (t(>60)). Integral thermal indices including the Therapeutic Exposure Index (TEI), Destructive Exposure Index (DEI), and Thermal Selectivity Index (TSI), and Safety Margin were calculated. Results. A single 2-s CW-TSCPC application at 1 W enabled achieving the coagulation temperature threshold (Tmax = 50.8 °C; t50 = 1.44 s) without a transition to the destructive temperature range (> 60 °C), whereas that at 2 W was accompanied by tissue overheating (Tmax = 61.8 °C; t50 = 0.4 s). A series of 2-s CW laser applications at 1 W enabled accumulation of the heat dose within the therapeutic window (t50–60 = 17.1 s; DEI = 0), whereas that at 2 W resulted in large t(>60) values (t(>60) = 39.7 s; DEI = 0.67). MicroPulse TSCPC did not result in reaching the coagulation threshold (Tmax ≤ 49 °C). The integral indices confirmed the optimal efficacy–safety balance for a CW-TSCPC application at 1 W. Conclusion. The 60 °C temperature threshold determines the transition from coagulative to destructive tissue injury. Therefore, CW-TSCPC at 1 W provides an optimal efficacy-safety balance due to a selective coagulative effect, and can be considered a pathophysiologically justified strategy for optimizing TSCPC parameters in NVG.


  • Integrated digital twin of ships

    by Vladimir Vychuzhanin, Alexey Vychuzhanin

    The monograph highlights the following: the architectural and methodological principles of designing cyber-physical systems for maritime autonomous surface ships; the development of physics-regularized hybriddigital twins that integrate machine learning with deterministic physical laws; the implementation of predictive analytics, degradation-aware routing, and cyber-resilience strategies within distributed macro-systems.The materials of this monograph will be valuable for researchers, postgraduate students, and engineering specialists in the fields of maritime IT, industrial artificial intelligence, and cyber-physical systems.

  • Open Access

    Systemic inflammatory markers predict treatment outcomes in secondary neovascular glaucoma: a 24-month follow-up study

    by O.V. Guzun, O.S. Zadorozhnyy, V.V. Vychuzhanin, L.M. Velychko, O.V. Bohdanova, A.R. Korol

    Background. Neovascular glaucoma remains one of the most aggressive forms of secondary glaucoma, and predic­ting treatment outcomes requires integration of clinical parameters with systemic biomarkers and advanced analytical approaches. The purpose was to evaluate the prognostic value of systemic inflammatory indices and endothelial activation markers (SII, SIRI, AISI, ICAM-1 (CD54)) for predicting treatment outcomes in secondary neovascular glaucoma at 24 months using multivariate statistical analysis and machine-learning approaches. Materials and me­thods. A retrospective analysis included 258 patients (258 eyes) with secondary neovascular glaucoma. The primary endpoint was the clinical treatment outcome at 24 months: clinical success group (achievement and maintenance of intraocular pressure < 22 mmHg without reduction in visual acuity) and group with ineffective treatment (failure). Systemic inflammatory indices (SII, SIRI, AISI) and the endothelial activation marker ICAM-1 (CD54) were assessed. Spearman correlation analysis, multivariate logistic regression, and machine-learning models (gradient boosting and multilayer perceptron) were applied. Results. Patients with treatment failure at 24 months demonstrated significantly higher baseline levels of SII, SIRI, AISI, and ICAM-1 (CD54) compared to the clinical success group, with a 1.3–2.2-fold increase (all p < 0.05). All systemic inflammatory indices and ICAM-1 (CD54) showed significant negative correlations with clinical treatment outcome (p < 0.05). Multivariate logistic regression and machine-learning models, based on systemic markers, provided moderate-to-high discriminative performance in predicting clinical success, with an area under the ROC curve of up to 0.83. SHAP analysis identified increased SIRI and AISI as the dominant negative contributors to treatment success probability. Conclusions. Systemic inflammation and endothelial activation markers in patients with secondary neovascular glaucoma have prognostic significance, are associated with long-term clinical treatment outcomes, and can be used for early risk stratification of treatment failure.


  • Open Access

    A hybrid A-UKF-PINN digital twin architecture for real-time state estimation in Smart Grids

    by Vladimir Vychuzhanin, Alexey Vychuzhanin

    The increasing variability, nonlinearity, and real-time operational requirements of Smart Grids (SGs) make static digital models insufficient for reliable state estimation and control of distributed assets such as Vehicle-toGrid (V2G) storage systems. The purpose of the study was a formal and model-based substantiation of the advantages of dynamic digital twins (DTs) over static data model (DM) in real-time lithium-ion storage system condition assessment tasks. To achieve this, a hybrid adaptive unscented Kalman filter – physics-informed neural network (A-UKF-PINN) architecture was proposed, combining an A-UKF (Adaptive Unscented Kalman Filter), which provided robust state estimation in the presence of noise and uncertainty, with a physics-informed PINN (Physics-Informed Neural Network) model that considers the dynamics and nonlinear processes of the battery cell. The originality of the study lies in the integration of these components into a single model that supports bidirectional synchronisation, which improves forecast stability and significantly reduces desynchronisation between the model and the physical object in SG conditions. Simulation validation was carried out on V2G operating cycles with modelled Phasor Measurement Unit / Internet of Things sensor noise. The obtained Root Mean Square Error (RMSE) of 0.87% demonstrated a 44% accuracy improvement compared to a traditional DM (ECM (equivalent circuit models) + UKF, RMSE 1.98%) and a 56% improvement relative to the baseline digital twin (pure PINN). The architectural assessment confirmed the necessity of using a hierarchical Edge-Cloud platform that ensures optimal distribution of computational workloads: PINN training in the cloud environment and high-frequency state estimation at the edge. The proposed architecture forms the basis for scalable dynamic DTs in SG, helps to reduce operational risks, supports the implementation of proactive maintenance strategies, and increases the efficiency of the energy infrastructure life cycle

  • Open Access

    Development of a hybrid (physics-informed) model of ship motion dynamics

    by V.V. Vychuzhanin, A.V. Vychuzhanin

    Improving the operational efficiency of marine vessels and the reliability of ship power plants requires the application of advanced methods for intelligent data analysis and modeling of complex dynamic processes. One of the most promising approaches is scientific machine learning, particularly physics-informed neural networks (PINNs), which combine physical laws governing technical systems with the capabilities of deep learning. The aim of this study is to investigate the potential of physics-informed neural networks for modeling hydrodynamic processes and for intelligent diagnostics of the technical condition of ship power plants. The paper analyzes modern approaches to computational hydrodynamics and machine learning methods used to describe ship motion dynamics and operational processes of marine energy systems. Special attention is given to the principles of constructing PINN models in which differential equations describing the physics of the investigated processes are incorporated directly into the neural network loss function. This approach improves prediction accuracy and model robustness when only limited experimental or operational data are available. It is shown that the use of physics-informed neural networks allows more accurate reproduction of nonlinear dynamic relationships between ship motion parameters, hydrodynamic characteristics, and the performance indicators of propulsion and power systems. Based on the analysis of recent scientific studies and published results, the advantages of the PINN approach compared with traditional computational fluid dynamics methods and purely data-driven machine learning algorithms are identified. It is demonstrated that the integration of physical models with neural network algorithms improves the reliability of predicting the technical condition of ship equipment and provides a foundation for developing intelligent monitoring and diagnostic systems for marine power plants. The obtained results confirm the перспективность of applying physics-informed neural networks to problems of ship hydrodynamics analysis, prediction of operational parameters, and improvement of technical diagnostic systems in marine engineering.


  • Open Access

    Three-scenario analysis of fault diagnosis accuracy in complex technical systems

    by Vladimir Vychuzhanin, Alexey Vychuzhanin

    The purpose of this study was to perform a three-scenario comparative analysis of the accuracy of intelligent fault diagnosis in complex technical systems using ship power plants (SPPs) as a representative case. The research sought to determine which diagnostic configuration ensures the highest accuracy and robustness under varying operational conditions. Three methodological configurations were analysed: a baseline model based on Case-Based Reasoning (CBR); CBR enhanced with probabilistic analysis using Bayesian networks and Markov chains; and a comprehensive integration of CBR with probabilistic models and simulation modelling of cascading failures. Experiments were conducted under three typical operational scenarios – nominal mode, high-load mode, and limited diagnostic data – reflecting real maritime conditions. Standard classification accuracy metrics were employed, including Accuracy, Recall, and F1-score. The results showed that the basic CBR configuration achieves an average accuracy of 82-85% under nominal conditions but significantly loses efficiency when data are incomplete. Integration with probabilistic models improves metric stability, increasing accuracy to 88-90%. At the optimal configuration of method weights (CBR – αd = 0.6, probabilistic models – βd = 0.2, simulation modelling – γd = 0.2), the minimum diagnostic error of 6% was achieved, and diagnostic accuracy exceeded 93% even under noisy or incomplete data. Analysis of confusion matrices and error visualisations revealed that integrated configurations reduce the number of type II errors by approximately 35% compared to isolated approaches. Three-dimensional plots of accuracy dependence on component weights confirmed a stable maximum in the balanced-parameter zone and highlighted the significance of the simulation component under complex operational conditions. The obtained results allowed formulating practical recommendations for selecting diagnostic configurations: CBR + Bayesian Networks for stable modes and full integration for overload or data-limited scenarios. The proposed methodology is adaptable to other intelligent diagnostic systems operating under uncertainty, variable load, and incomplete information, including cyber-physical and industrial systems. It represents a universal and scalable framework for applied diagnostics requiring high accuracy, adaptability, and robustness