Bohdan Koman
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Bohdan Koman has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Volodymyr Yuzevych
Karpenko Physico-Mechanical Institute of the NAS of Ukraine
7 shared publications - Ruslan Skrynkovskyy
Львівський університет бізнесу та права
3 shared publications - Igor B. Olenych
Ivan Franko National University of Lviv
2 shared publications - Larysa Yuzevych
Lviv Polytechnic National University
2 shared publications R. I. Bihun
Department of Electronics and Computer Technologies, Lviv Ivan Franko National University, Lviv, Ukraine
2 shared publications13 Pokrovs’Ka Str. Technical Center Nas Of Ukraine
1 shared publication
Latest Publications
- Open Access
- 20 February 2025
- Published by Private Company Technology Center in Technology audit and production reserves
- Vol. 1 (1(81)) , 58-74
Assessing the potential of artificial intelligence and machine learning for thermal management in electronic devices
The object of this study is the potential of artificial intelligence (AI) and machine learning (ML) techniques for thermal management in electronic devices. One of the most problematic aspects identified is the challenge of ensuring performance, reliability, and energy efficiency across diverse systems, including semiconductors, data centers, and consumer electronics. In the course of the research, the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology was used to systematically analyze 150 studies. These studies employed various approaches, such as predictive modeling, optimization algorithms, and real-time control systems. Our findings indicate that AI-driven thermal management can reduce energy consumption by up to 81.81 %, depending on the cooling method and optimization. Reinforcement learning-based HVAC control achieves 17.4 % energy savings, while ML-driven power management in manycore systems reduces energy use by 30 % and lowers peak chip temperatures by 17 °C. Neural network-based thermal forecasting achieves <1 % error, improving prediction accuracy. Additionally, LSTM models for thermal prognosis achieve a 3.45 % relative prediction error, outperforming traditional regression methods. These results highlight the potential of AI in optimizing thermal behavior across data centers, smart buildings, and manycore chip architectures. Key limitations were also identified, including limited data availability, challenges in model interpretability, and integration with legacy systems. The study provides a roadmap for scalable AI-driven thermal management. Emerging trends such as physics-informed ML models and the integration of cooling technologies promise innovation. Compared to conventional methods, these advancements deliver clear benefits in sustainability and adaptability.
- 20 February 2025
- Published by Private Company Technology Center in Technology audit and production reserves
- Vol. 1 (1(81)) , 58-74
Open AccessAssessing the potential of artificial intelligence and machine learning for thermal management in electronic devices
The object of this study is the potential of artificial intelligence (AI) and machine learning (ML) techniques for thermal management in electronic devices. One of the most problematic aspects identified is the challenge of ensuring performance, reliability, and energy efficiency across diverse systems, including semiconductors, data centers, and consumer electronics. In the course of the research, the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology was used to systematically analyze 150 studies. These studies employed various approaches, such as predictive modeling, optimization algorithms, and real-time control systems. Our findings indicate that AI-driven thermal management can reduce energy consumption by up to 81.81 %, depending on the cooling method and optimization. Reinforcement learning-based HVAC control achieves 17.4 % energy savings, while ML-driven power management in manycore systems reduces energy use by 30 % and lowers peak chip temperatures by 17 °C. Neural network-based thermal forecasting achieves <1 % error, improving prediction accuracy. Additionally, LSTM models for thermal prognosis achieve a 3.45 % relative prediction error, outperforming traditional regression methods. These results highlight the potential of AI in optimizing thermal behavior across data centers, smart buildings, and manycore chip architectures. Key limitations were also identified, including limited data availability, challenges in model interpretability, and integration with legacy systems. The study provides a roadmap for scalable AI-driven thermal management. Emerging trends such as physics-informed ML models and the integration of cooling technologies promise innovation. Compared to conventional methods, these advancements deliver clear benefits in sustainability and adaptability.
- Open Access
- 19 March 2021
- Published by European Scientific Platform (Publications)
ENERGY PARAMETERS OF INTERPHASE INTERACTION IN Si-SiO2 STRUCTURES
- 19 March 2021
- Published by European Scientific Platform (Publications)
Open AccessENERGY PARAMETERS OF INTERPHASE INTERACTION IN Si-SiO2 STRUCTURES
- Open Access
- 19 November 2019
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 6 (5 (102)) , 23-29
Improvement of the toolset for diagnosing underground pipelines of oil and gas enterprises considering changes in internal working pressure
Improvement of the toolset for diagnosing underground pipelines of oil and gas enterprises considering changes in internal working pressure
- 19 November 2019
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 6 (5 (102)) , 23-29
Open AccessImprovement of the toolset for diagnosing underground pipelines of oil and gas enterprises considering changes in internal working pressure
Improvement of the toolset for diagnosing underground pipelines of oil and gas enterprises considering changes in internal working pressure
- 1 August 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 134-138
Intelligent Analysis of Data Systems for Defects in Underground Gas Pipeline
A method of functioning of intelligent software and hardware complex for monitoring system of an underground gas pipeline and cathodic protection devices using data and knowledge bases is proposed.
- 1 August 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 134-138
Intelligent Analysis of Data Systems for Defects in Underground Gas Pipeline
A method of functioning of intelligent software and hardware complex for monitoring system of an underground gas pipeline and cathodic protection devices using data and knowledge bases is proposed.
- 3 August 2017
- Published by Taylor & Francis in Radiation Effects and Defects in Solids
- Vol. 172 (7-8) , 600-609
Effect of combined radiation processing on parameters of Si-based MOS transistors
The variation of parameters of Si-based MOS-transistors affected by combined infrared and X- ray photons processing were presented. It was found that X-ray irradiated transistor under incoherent infrared radiation is characterized by lowering of radiation sensitivity. As positive charge and its radiation-induced rate of generation in undergate SiO2 insulator decreases, we observe a reduction of both ΔUNo and voltage threshold Uth transistor components. Under pulsed laser processing (λ = 1.06 µm, τ = 10−3s) of the X-rays irradiated transistor the energy density of laser beam corresponding to the minimum threshold voltage was established. It was shown that the combined treatment can be effectively used to control the transistor parameters. The model describing the radiation changes of parameters in Si-SiO2 structure was proposed. The effect of Na+, K+ and H+ ions in undergate insulator on variation of charge state and interface reconstruction under laser irradiation were predicted by proposed model.
- 3 August 2017
- Published by Taylor & Francis in Radiation Effects and Defects in Solids
- Vol. 172 (7-8) , 600-609
Effect of combined radiation processing on parameters of Si-based MOS transistors
The variation of parameters of Si-based MOS-transistors affected by combined infrared and X- ray photons processing were presented. It was found that X-ray irradiated transistor under incoherent infrared radiation is characterized by lowering of radiation sensitivity. As positive charge and its radiation-induced rate of generation in undergate SiO2 insulator decreases, we observe a reduction of both ΔUNo and voltage threshold Uth transistor components. Under pulsed laser processing (λ = 1.06 µm, τ = 10−3s) of the X-rays irradiated transistor the energy density of laser beam corresponding to the minimum threshold voltage was established. It was shown that the combined treatment can be effectively used to control the transistor parameters. The model describing the radiation changes of parameters in Si-SiO2 structure was proposed. The effect of Na+, K+ and H+ ions in undergate insulator on variation of charge state and interface reconstruction under laser irradiation were predicted by proposed model.
- Open Access
- 31 July 2017
- Published by OU Scientific Route in EUREKA: Physics and Engineering
- Vol. 4 (4) , 49-60
DEVELOPMENT OF INFORMATION SUPPORT OF QUALITY MANAGEMENT OF UNDERGROUND PIPELINES
Recommendations are worked out in relation to the evaluation of longevity and quality of underground metallic pipelines in the conditions of corrosion fatigue. The features of early exposure of crisis (before accident) situations are set. A complex qualimetric criterion is offered for determination of level of quality of pipeline by the account of his technological specific. The elements of investment project and methodology of estimation of resource are worked out. and also influences of factors of different nature on risks and possibility of accident of gas pipelines. The model of corrosion fatigue of metal is based on power criterion of destruction mechanics according to which there is an act of destruction in an arbitrary elemental volume of a material if the total irreversibly scattered energy of plastic deformation for all load cycles will reach a critical value equal to the energy of destruction. In order to control the corrosion process taking the polarization potential into account, a criterion relation is used to determine the rate of residual corrosion of a metal in the defect of the insulation coating, in particular, at the top of the crack, which is an anode region. The adhesive strength criteria of biocorrosive aggressive soil, mechanical criteria for the stress intensity factor, the criterion of corrosion resistance defect, criterion correlation for estimating the speed of residual corrosion in defect of insulation coating with imposed diagnostic weight characteristics and diagnostic value of tests, that complement, clarify and improve the corrosion monitoring system of pipelines, helpful for controlling and optimizing of the corrosion process, and Development of recommendations for anti-corrosion protection of metal are used in areas with non-stationary plastic deformation.
- 31 July 2017
- Published by OU Scientific Route in EUREKA: Physics and Engineering
- Vol. 4 (4) , 49-60
Open AccessDEVELOPMENT OF INFORMATION SUPPORT OF QUALITY MANAGEMENT OF UNDERGROUND PIPELINES
Recommendations are worked out in relation to the evaluation of longevity and quality of underground metallic pipelines in the conditions of corrosion fatigue. The features of early exposure of crisis (before accident) situations are set. A complex qualimetric criterion is offered for determination of level of quality of pipeline by the account of his technological specific. The elements of investment project and methodology of estimation of resource are worked out. and also influences of factors of different nature on risks and possibility of accident of gas pipelines. The model of corrosion fatigue of metal is based on power criterion of destruction mechanics according to which there is an act of destruction in an arbitrary elemental volume of a material if the total irreversibly scattered energy of plastic deformation for all load cycles will reach a critical value equal to the energy of destruction. In order to control the corrosion process taking the polarization potential into account, a criterion relation is used to determine the rate of residual corrosion of a metal in the defect of the insulation coating, in particular, at the top of the crack, which is an anode region. The adhesive strength criteria of biocorrosive aggressive soil, mechanical criteria for the stress intensity factor, the criterion of corrosion resistance defect, criterion correlation for estimating the speed of residual corrosion in defect of insulation coating with imposed diagnostic weight characteristics and diagnostic value of tests, that complement, clarify and improve the corrosion monitoring system of pipelines, helpful for controlling and optimizing of the corrosion process, and Development of recommendations for anti-corrosion protection of metal are used in areas with non-stationary plastic deformation.
- 1 February 2017
- Published by National Academy of Sciences of Ukraine (Co. LTD Ukrinformnauka) (Publications) in Ukrainian Journal of Physics
- Vol. 62 (2) , 166-171
Electrical Properties of Silicon-Oxide Heterostructures on the Basis of Porous Silicon
The processes of charge-carrier transport and relaxation in silicon-oxide heterostructures based on porous silicon have been studied, by using voltammetric measurements and thermoactivation spectroscopy. The temperature dependences of the conductivity in experimental structures are measured in an interval of 80–325 K, and the activation energy of the electrical conductivity is determined. On the basis of the temperature dependences obtained for the depolarization current, the energy distribution of localized electron states, which affect the charge transport processes, is calculated. The influence of coating the porous silicon layer with a thin SiOx film on the electrical properties of the layer is analyzed. The obtained results extend the application scope of silicon-oxide nanosystems.
- 1 February 2017
- Published by National Academy of Sciences of Ukraine (Co. LTD Ukrinformnauka) (Publications) in Ukrainian Journal of Physics
- Vol. 62 (2) , 166-171
Electrical Properties of Silicon-Oxide Heterostructures on the Basis of Porous Silicon
The processes of charge-carrier transport and relaxation in silicon-oxide heterostructures based on porous silicon have been studied, by using voltammetric measurements and thermoactivation spectroscopy. The temperature dependences of the conductivity in experimental structures are measured in an interval of 80–325 K, and the activation energy of the electrical conductivity is determined. On the basis of the temperature dependences obtained for the depolarization current, the energy distribution of localized electron states, which affect the charge transport processes, is calculated. The influence of coating the porous silicon layer with a thin SiOx film on the electrical properties of the layer is analyzed. The obtained results extend the application scope of silicon-oxide nanosystems.
- 11 December 2016
- Published by National Academy of Sciences of Ukraine (Co. LTD Ukrinformnauka) in Metallofizika i Noveishie Tekhnologii
- Vol. 38 (9) , 1167-1177
Influence of Sublayers of Germanium on Charge Transfer in Films of Chromium of Nanometre Thickness
- 11 December 2016
- Published by National Academy of Sciences of Ukraine (Co. LTD Ukrinformnauka) in Metallofizika i Noveishie Tekhnologii
- Vol. 38 (9) , 1167-1177
Influence of Sublayers of Germanium on Charge Transfer in Films of Chromium of Nanometre Thickness