2024 - Repozytorium publikacji - Politechnika Gdańska

Pokaż publikacje z roku

Publikacje z roku 2024

Pokaż wszystkie

Fault detection in the marine engine using a support vector data description method
- Klaudia Wrzask
- Jerzy Kowalski
- Van Vang Le
- Van Bac Nguyen
- Dao Nam Cao
2024 Journal of Marine Engineering and Technology
Fast detection and correct diagnosis of any engine condition changes are essential elements of safety andenvironmental protection. Many diagnostic algorithms significantly improve the detection of malfunctions.Studies on diagnostic methods are rarely reported and even less implemented in the marine engine industry.To fill this gap, this paper presents the Support Vector Data Description (SVDD) method as applied to thefault detection of the fuel delivery system of a two-stroke marine engine. The selected diagnostic data is theexhaust gas composition, with four components considered: oxygen, carbon oxide, nitric oxide, and carbondioxide. With these diagnostics, the method distinguishes eight different engine faults from the efficient state.The manuscript presents in detail the methodology for applying the SVDD method in a marine engine. Themethod of obtaining diagnostic data and its scaling is described. The method of training and validating thealgorithm is also presented, along with ready-made algorithms for use. The 100% accuracy of the proposedfault detection method. Based on the obtained results, the proposed fault detection method is promising fora simple application. Moreover, generalised algorithms that may be adapted to different technical solutionsare also presented.
Feasibility Study of Three-Phase Modular Converter for Dual-Purpose Application in DC and AC Microgrids
- Carlos Roncero-Clemente
- Oleksandr Husev
- Oleksandr Matiushkin
- J. Gutierrez-Escalona
- Fermin Barrero-Gonzalez
- D. Vinnikov
- Ryszard Strzelecki
2024 IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS
The modern concept of a universal converter is intended as a power converter suitable for application in both dc or ac grids using the same external connectors. This novel family was recently proposed to allow an easier integration of renewable energy sources and energy storage systems, interfacing with dc/ac grids and/or loads with a minimum redundancy of power switches and passive elements. This kind of solution and applications are expected to be a reality in the nearest decade, as ac and dc low voltage distribution networks will coexist. Nevertheless, the initial solutions proposed as universal converter were focused on ac single-phase power conversion systems. In this sense, this article proposes and describes a new member of the universal converter family suitable for dc to dc and dc to ac power conversion (both in three-phase three-wire and in three-phase four-wire). The proposed power topology is derived as a modular extension from the single buck-boost bidirectional cell. Its main operation modes (buck and boost) are discussed, and a pulse-width-modulation technique is developed to generate the corresponding switching patterns. The proposed solution is successfully validated in open-loop mode both in simulation and experimentally with a laboratory prototype. The measured efficiency of the power converter was above 97% in the dc to ac mode and around 99% in the dc to dc mode
Feasibility Study of Three-Phase Modular Converter for Dual-Purpose Application in DC and AC Microgrids
- Carlos Roncero-Clemente
- Oleksandr Husev
- Oleksandr Matiushkin
- Javier Gutiérrez-Escalona
- Fermin Barrero-Gonzalez
- Dmitri Vinnikov
- Ryszard Strzelecki
2024 IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS
The modern concept of a universal converter is intended as a power converter (PC) suitable for application in both dc or ac grids using the same external connectors. This novel family was recently proposed to allow easier integration of renewable energy sources and energy storage systems (ESSs), interfacing with dc/ac grids and/or loads with a minimum redundancy of power switches and passive elements. This kind of solution and applications are expected to be a reality in the nearest decade, as ac and dc low voltage distribution networks will coexist. Nevertheless, the initial solutions proposed as universal converters were focused on ac single-phase power conversion systems. In this sense, this article proposes and describes a new member of the universal converter family suitable for dc–dc and dc–ac power conversion (both in three-phase three-wire and in three-phase four-wire). The proposed power topology is derived as a modular extension from the single buck-boost bidirectional cell. Its main operation modes (buck and boost) are discussed, and a pulsewidth-modulation technique is developed to generate the corresponding switching patterns. The proposed solution is successfully validated in open-loop mode both in simulation and experimentally with a laboratory prototype. The measured efficiency of the PC was above 97% in the dc–ac mode and around 99% in the dc–dc mode.
Feedback Control of Doubly-Fed Generator Connected to Current Source Converter
- Marcin Morawiec
- Pawel Kroplewski
- Filip Wilczyński
2024 IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
Doubly-fed induction generator (DFIG) system supplied by current source converter (CSC) is considered in this article. The DFIG can work in two independent modes: AC grid connection and stand-alone mode. The DFIG is connected to the ac grid directly through its stator and the CSC links the rotor side. In this mode, the active and reactive powers of the DFIG must be controlled. This article proposes two control system structures for the DFIG working in the generator mode. Both control structures are based on nonlinear transformations but on different state-feedback control variables. The selection of the variables is similar to the input–output linearization but more complicated due to the CSC and “voltage control” involved. Both proposed control structures ensure independent control of the active and reactive powers with different accuracies; as evidenced in the simulation and experimental results. The proposed approach can be named by voltage control of the DFIG because the control variables are the voltage in the dc-link and the angular speed of the output current vector from the inverter. For both proposed control structures, the current in the dc-link is not a constant value, but depends on the dynamic states and values of the controlled powers; thus, it varies accordingly. The proposed control strategy can be applied to low- and high-power DFIG systems. Simulation and experimental results from a 2-kW generator validate theoretical propositions.
FEM simulations applied to the failure analysis of RC structure under the influence of municipal sewage pressure
- Łukasz Skarżyński
- Ireneusz Marzec
2024 ENGINEERING FAILURE ANALYSIS
The paper discusses a failure mechanism of reinforced concrete (RC) structure with steel cover that failed under the influence of municipal sewage pressure. To explain the reasons of failure, in-situ measurements, laboratory experiments and comprehensive Finite Element Method (FEM) computations were performed. Non-destructive in-situ scanning tests were carried out to determine quantity and cover thickness of embedded reinforcement bars, simultaneously, laboratory tests regarding concrete and shotcrete thickness, density and compressive strength were performed on samples prepared from core drills taken from the RC structure. FEM computations were carried out with the constitutive continuum model for concrete and steel with material parameters designated on the basis of stress-strain curves in uniaxial compression and uniaxial tension, respectively. An isotropic coupled elasto-plastic-damage formulation based on the strain equivalence hypothesis was used. In order to describe strain localization in concrete, model was enhanced in a softening regime by a characteristic length of micro-structure by means of a non-local theory. FEM analyses were carried out for different values of sewage pressure. The main attention was paid to the evolution of steel cover deformation and strain localization of the RC ceiling slab. FEM results revealed strong dependence between a bond-slip between anchors and steel cover deformation as well as between sewage pressure value and strain localization pattern of RC structure. Mechanism of the structure failure under complex loading conditions was realistically captured and its reasons were discussed in detail.
Femtosecond laser ablated trench array for improving performance of commercial solid oxide cell
- Mohamed A. Baba
- Bartłomiej Lemieszek
- Mantas Sriubas
- Brigita Abakevičiene
- Sigitas Tamulevičius
- Sebastian Molin
- Tomas Tamulevičius
2024 JOURNAL OF POWER SOURCES
The performance of electrode-supported solid oxide cells (SOCs) is limited adversely by gas diffusion impedance in thick and porous support. This work focuses on the improvement of gas transport properties of commercial Ni-YSZ anode-supported SOFC by femtosecond laser-based micromachining where micro-holes of identical depth but different hole separations pitches with minimal heated affected zones were imposed. The polarization resistance calculations and DRT analysis revealed that the presence of the micro-holes improves fuel transport in the anode active zone of commercial SOFC. The presence of the micro-holes resulted in up to 20.8 % and up to 17.2 % reduction in polarization resistance for dry H2 and wet H2 gas-fueled SOFC samples, respectively. Moreover, the decrease in intensity of peaks responsible for fuel diffusion with increasing micro-holed density was observed. Therefore, dense and sparse cells exhibited a performance augmentation of 25 % and 11 % in dry H2 and enhancement of 16 % and 15.6 % in wet H2, respectively. Fs-laser ablation appeared as a unique capability for the post-processing of SOFC elements via imposing different gas channel geometries.
Few-Layer Black Phosphorus/Chitosan Nanocomposite Electrodes via Controlled Electrodeposition for Enhanced Electrochemical Kinetic Performance
- Paweł Jakóbczyk
- Iwona Kaczmarzyk
- Robert Bogdanowicz
2024 Journal of Physical Chemistry C
This study presents the preparation and characterization of few-layer black phosphorus (FLBP) chitosan electrodes by controlled electrochemical deposition of chitosan nanoparticles on FLBP-modified glassy carbon electrodes. FLBP was prepared by solvent-assisted exfoliation of bulk BP and was further modified with chitosan forming together a nanocomposite, including easy cross-linking with nanomaterials and film-forming properties. Cyclic voltammetry was employed to analyze the kinetic properties of electrodes fabricated at different electrochemical deposition durations of chitosan, revealing distinct reduction and oxidation peaks using 10 V. The electrochemical impedance spectroscopy technique was employed to further characterize the investigated FLBP-chitosan nanocomposites, which provides valuable insights into the electrode material properties. The controlled electrochemical deposition of chitosan nanoparticles on FLBP-modified glassy carbon electrodes opens up possibilities for developing a wide range of electrochemical sensors and devices for energy storage applications.
Field Calibration of Low-Cost Particulate Matter Sensors Using Artificial Neural Networks and Affine Response Correction
- Sławomir Kozieł
- Anna Pietrenko-Dąbrowska
- Marek Wójcikowski
- Bogdan Pankiewicz
2024 Pełny tekst MEASUREMENT
Due to detrimental effects of atmospheric particulate matter (PM), its accurate monitoring is of paramount importance, especially in densely populated urban areas. However, precise measurement of PM levels requires expensive and sophisticated equipment. Although low-cost alternatives are gaining popularity, their reliability is questionable, attributed to sensitivity to environmental conditions, inherent instability, and manufacturing imperfections. The objectives of this paper include (i) introduction of an innovative approach to field calibration for low-cost PM sensors using artificial intelligence methods, (ii) implementation of the calibration procedure involving optimized artificial neural network (ANN) and combined multiplicative and additive correction of the low-cost sensor readings, (iii) demonstrating the efficacy of the presented technique using a custom-designed portable PM monitoring platform and reference data acquired from public measurement stations. The results obtained through comprehensive experiments conducted using the aforementioned low-cost sensor and reference data demonstrate remarkable accuracy for the calibrated sensor, with correlation coefficients of 0.86 for PM1 and PM2.5, and 0.76 PM10 (particles categorized as having diameter equal to or less than 1m, 2.5m, and 10m, respectively), along with low RMSE values of only 3.1, 4.1, and 4.9 µg/m³.
Fine-Tuning the Photocatalytic Activity of the Anatase {1 0 1} Facet through Dopant-Controlled Reduction of the Spontaneously Present Donor State Density
- Szymon Dudziak
- Jakub Karczewski
- Adam Ostrowski
- Grzegorz Trykowski
- Kostiantyn Nikiforow
- Anna Zielińska-Jurek
2024 Pełny tekst ACS Materials Au
The present study highlights the importance of the net density of charge carriers at the ground state on photocatalytic activity of the faceted particles, which can be seen as a highly underexplored problem. To investigate it in detail, we have systematically doped {1 0 1} enclosed anatase nanoparticles with Gd3+ ions to manipulate the charge carrier concentration. Furthermore, control experiments using an analogical Nb5+ doped sample were performed to discuss photocatalytic activity in the increased range of free electrons. Overall results showed significant enhancement of phenol degradation rate and coumarin hydroxylation, together with an increase of the designed Gd/Ti ratio up to 0.5 at. %. Simultaneously, the mineralization efficiency, measured as a TOC reduction, was controlled between the samples. The observed activity enhancement is connected with the controlled decrease of the donor state density within the materials, being the net effect of the spontaneously present defects and introduced dopants, witch reduce hydroxylation and the hole trapping ability of the {1 0 1} facets. This allows to fine-tune multi-/single-electron processes occurring over the prepared samples, leading to clear activity maxima for 4-nitrophenol reduction, H2O2 generation, and ·OH formation observed for different donor densities. The optimized material exceeds the activity of the TiO2 P25 for phenol degradation by 52% (377% after surface normalization), showing its suitable design for water treatment. These results present a promising approach to boost photocatalyst activity as the combined result of the exposed crystal facet and dopant-optimized density of ground-state charge carriers.
Finger Vein Presentation Attack Detection Method Using a Hybridized Gray-Level Co-Occurrence Matrix Feature with Light-Gradient Boosting Machine Model
- Kashif Shaheed
- Piotr Szczuko
- Inam Ullah
- Hammed Mojeed
- Abdullateef O. Balogun
- Luiz Fernando Capretz
2024
Presentation Attack Detection (PAD) is crucial in biometric finger vein recognition. The susceptibility of these systems to forged finger vein images is a significant challenge. Existing approaches to mitigate presentation attacks have computational complexity limitations and limited data availability. This study proposed a novel method for identifying presentation attacks in finger vein biometric systems. We have used optimal Gray-Level Co-occurrence Matrix (GLCM) features with the Light-Gradient Boosting Machine (LGBM) classification model. We use statistical texture attributes namely, energy, correlation, and contrast to extract optimal features from counterfeit and authentic finger-vein images. The study investigates cluster-pixel connectivity in finger vein images. Our approach is tested using K-fold cross-validation and compared to existing methods. Results demonstrate that Light-GBM outperforms other classifiers. The proposed classifier achieved low APCER values of 2.73% and 8.80% compared to other classifiers. The use of Light-GBM in addressing presentation attacks in finger vein biometric systems is highly significant.
Fire evacuations of public places - theory and practise
- Beata Świeczko-Żurek
- Marcin Żurek
2024
Publikacja dotyczy ewakuacji pożarowych miejsc publicznych.
Fire-Retardant Flexible Foamed Polyurethane (PU)-Based Composites: Armed and Charmed Ground Tire Rubber (GTR) Particles
- Paulina Kosmela
- Kamila Sałasińska
- Daria Kowalkowska-Zedler
- Mateusz Barczewski
- Adam Piasecki
- Mohammad Saeb
- Aleksander Hejna
2024 Pełny tekst Polymers
Inadequate fire resistance of polymers raises questions about their advanced applications. Flexible polyurethane (PU) foams have myriad applications but inherently suffer from very high flammability. Because of the dependency of the ultimate properties (mechanical and damping performance) of PU foams on their cellular structure, reinforcement of PU with additives brings about further concerns. Though they are highly flammable and known for their environmental consequences, rubber wastes are desired from a circularity standpoint, which can also improve the mechanical properties of PU foams. In this work, melamine cyanurate (MC), melamine polyphosphate (MPP), and ammonium polyphosphate (APP) are used as well-known flame retardants (FRs) to develop highly fire-retardant ground tire rubber (GTR) particles for flexible PU foams. Analysis of the burning behavior of the resulting PU/GTR composites revealed that the armed GTR particles endowed PU with reduced flammability expressed by over 30% increase in limiting oxygen index, 50% drop in peak heat release rate, as well as reduced smoke generation. The Flame Retardancy Index (FRI) was used to classify and label PU/GTR composites such that the amount of GTR was found to be more important than that of FR type. The wide range of FRI (0.94–7.56), taking Poor to Good performance labels, was indicative of the sensitivity of flame retardancy to the hybridization of FR with GTR components, a feature of practicality. The results are promising for fire protection requirements in buildings; however, the flammability reduction was achieved at the expense of mechanical and thermal insulation performance.
First highly effective non-catalytic nitrobenzene reduction in UV/dithionite system with aniline production – Advanced reduction process (ARP) approach
- Łukasz Cichocki
- Lingshuai Kong
- Chongqing Wang
- Andrzej Przyjazny
- Grzegorz Boczkaj
2024 Pełny tekst CHEMICAL ENGINEERING JOURNAL
Advanced reduction processes (ARPs) are currently intensively investigated as an alternative to Advanced Oxidation Processes (AOPs). The study presents efficient reduction of nitrobenzene under non-catalytic conditions through reaction with free radicals having reductive potential. Effective conversion of nitrobenzene in a model wastewater solution, was obtained for sodium dithionite (SDT)/ dithionite (DTN). The developed process provide a nitrobenzene reduction efficiency of > 99.9 % within 10 min under neutral conditions, ambient temperature, with a molar ratio of reductant to pollutant (rred) of 3. Additional UV radiation lowered by 10 % the dose of DTN. Interestingly, addition of titanium dioxide (TiO2) as a photocatalyst did not show a positive effect. An extremely significant conclusion of this study is the observed excellent resistance of the reaction system to the negative influence of inorganic anions, with a reduction in efficiency in the following order: and dissolved organic matter (DOM) . The study showed that the process works effectively across the pH range from 3 to 12. Studies on the reaction mechanism revealed that sulfur dioxide anion radical ) was responsible for the main reduction effect. The main product of nitrobenzene reduction was aniline (>99.9 %). The total cost of purification process was USD 0.77/m3. The high efficiency, short process time, low cost, and lack of need for complicated equipment make this developed process potentially widely applicable in the industry. The developed method for the reduction of nitrobenzene to aniline is the first non-catalytic method with such high efficiency and without the formation of intermediate reaction products.
Flap Monitoring Techniques: A Review
- Ignacy Rogoń
- Agnieszka Rogoń
- Adam Kaczmarek
- Adam Bujnowski
- Jerzy Wtorek
- Filip Lachowski
- Jerzy Jankau
2024 Journal of Clinical Medicine
Postoperative tissue flap vitality monitoring enables early detection of clinical complications, allowing for intervention. Timely re-operation can prevent the need for extensive correction procedures, thus reducing healthcare costs and hospitalisation time. Statistics show that monitoring can increase the success rate of flap survival to 95\% or higher. However, despite the significant progress in monitoring techniques, major and minor complications, leading to the loss of the flap, still occur. This clinical application review aims to provide a comprehensive overview of the recent advancements and findings in flap surgery reconstructions, transplants, and systems for their postoperative assessment. Literature from the years 1925 to 2024 has been reviewed to capture previous and current solutions for monitoring flap vitality. Clinically acclaimed methods and experimental techniques were classified and reviewed from a technical and clinical standpoint. Physical examination, metabolism change, ultrasound method, and electromagnetic (EM) radiation-based measurement methods were carefully evaluated from the perspective of their considered applications. Guidelines aiding engineers in the future design and development process of monitoring systems were proposed. This paper provides a comprehensive overview of the monitoring techniques used in postoperative flap vitality monitoring. It also gives an overview of each approach and potential ways for future development.
Flicker Noise in Resistive Gas Sensors—Measurement Setups and Applications for Enhanced Gas Sensing
- Janusz Smulko
- Graziella Scandurra
- Katarzyna Drozdowska
- Andrzej Kwiatkowski
- Carmine Ciofi
- He Wen
2024 Pełny tekst SENSORS
We discuss the implementation challenges of gas sensing systems based on low-frequency noise measurements on chemoresistive sensors. Resistance fluctuations in various gas sensing materials, in a frequency range typically up to a few kHz, can enhance gas sensing by considering its intensity and the slope of power spectral density. The issues of low-frequency noise measurements in resistive gas sensors, specifically in two-dimensional materials exhibiting gas-sensing properties, are considered. We present measurement setups and noise-processing methods for gas detection. The chemoresistive sensors show various DC resistances requiring different flicker noise measurement approaches. Separate noise measurement setups are used for resistances up to a few hundred kΩ and for resistances with much higher values. Noise measurements in highly resistive materials (e.g., MoS2, WS2, and ZrS3) are prone to external interferences but can be modulated using temperature or light irradiation for enhanced sensing. Therefore, such materials are of considerable interest for gas sensing.
Floodsar: Automatic mapping of river flooding extent from multitemporal SAR imagery
- Tomasz Berezowski
- Szymon Niemiec
- Andrzej Chybicki
2024 Pełny tekst SoftwareX
Floodsar is an open-source tool for automatic mapping of the flood extent from a time series of synthetic aperture radar (SAR) imagery. Floodsar is unsupervised, however, it requires defining the parameters search space, geographical area of interest, and some river gauge observations (e.g. water levels or discharges) time series that overlap temporarily with the SAR imagery. Applications of Floodsar are mainly in real-time monitoring and elaborating long-time series of historical data. Floodsar features two algorithms for flood extent mapping. The 1D algorithm identifies a flood/no-flood threshold in one SAR polarization. The 2D algorithm performs clustering on two SAR polarizations at the same time. Floodsar chooses the optimal threshold or the composition of clusters by maximizing the correlation between the resulting flood area and the river gauge observations. Floodsar was tested on three case studies with different land uses to illustrate its performance. The 2D algorithm performed on average the best with the average kappa=0.78, yet the less complex 1D/VV algorithm obtained similar results.
Fluctuation-Enhanced Sensing of Organic Vapors by Ink-Printed MoS2 Devices under UV Irradiation
- Katarzyna Drozdowska
- Janusz Smulko
- Sergey Rumyantsev
- Andrzej Kwiatkowski
2024
This work presents the results of fluctuationenhanced sensing (FES) of selected organic gases by MoS2 sensor fabricated via a simple ink printing method. We demonstrate that low-frequency noise measured under UV irradiation (275 nm) is more sensitive to different gases than measured in the dark. The noise at 1 Hz under UV light increased 3.3, 3.5, 1.6, and 2.9 times for chloroform, tetrahydrofuran, acetonitrile, and acetone ambiances, respectively. By comparing the noise spectra collected in the dark and under UV light, we report that irradiation has a visible effect on the noise in the lowest frequency range (0.125–10 Hz), changing mainly the slope of the spectra. Thus, each organic gas produces a distinct signature by affecting the noise amplitude and the shape of the spectrum. The differences in the characteristic noise features among organic vapors are ascribed to differences in their molecular configuration and polar properties.
Fluorescence of p-hydroxyazobenzocrowns – Tautomeric equilibrium effect
- Paulina Szulc
- Elżbieta Luboch
- Andrzej Okuniewski
- Ewa Wagner-Wysiecka
2024 SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
The spectroscopic properties of a series of para-hydroxyazobenzocrowns, including three novel compounds, were investigated using UV–Vis absorption and emission spectroscopy. This study presents, for the first time, determined quantum yield (QY) values for macrocycles of this category, ranging between 0.122 and 0.195. The highest values were obtained for crowns bearing two phenyl substituents in benzene rings. The impact of aromatic ring substituents and macroring size on the spectral characterization (1H NMR and FTIR) of p-hydroxyazobenzocrowns was examined in consideration of the azophenol ⇄ quinone-hydrazone tautomeric equilibrium. Dipole moments of p-hydroxyazobenzocrowns in the ground and excited states have been determined. The alignment between experimental findings and theoretical studies was established.
Fluvial ecology disasters: the impact of the Gliwice Canal on the ecological crisis in the Oder River basin, Poland (2022)
- Marek Ruman
- Natalia Janczewska
- Klaudia Kosek
- Wojciech Artichowicz
- Magdalena Nasiek
- Magdalena Matysik
2024 Acta Geophysica
In August 2022, the Oder River experienced an ecological disaster, resulting in the extinction of hundreds of aquatic organ- isms. Mass fsh deaths also occurred during that time in the Gliwice Canal, located in southern Poland, which connects to the upper section of the Oder River. The aim of the article was to assess the impact of the waters from the Gliwice Canal on the water quality changes in the Oder River, as expressed by chloride, sulphate, nitrate, phosphate content, as well as its parameters such as conductivity, temperature, and pH. Statistical analyses were conducted based on our own research and a series of data collected by the Chief Inspectorate for Environmental Protection. Below the confuence of the Oder River with the waters of the canal, an increase in sulphates levels and a decrease in sodium content were observed. The other parameters remained unchanged. It was also noted that the magnitude of each parameter was signifcantly higher in the waters of the Gliwice Canal compared to the Oder River. The research conclusion is that there is no infuence of the canals’ waters on the quality of the Oder River waters, both during the ecological disaster and afterwards. The presented research clearly indicates the need for separate analyses of fowing waters (with signifcantly higher salt and other pollutant dissolution capacity) and stagnant waters in water infrastructure (without water exchange).
Forecasting energy consumption and carbon dioxide emission of Vietnam by prognostic models based on explainable machine learning and time series
- Thanh Tuan Le
- Prabhakar Sharma
- Sameh M. Osman
- Marek Dzida
- Phuoc Quy Phong Nguyen
- Minh Ho Tran
- Dao Nam Cao
- Viet Dung Tran
2024 Clean Technologies and Environmental Policy
This study assessed the usefulness of algorithms in estimating energy consumption and carbon dioxide emissions in Viet- nam, in which the training dataset was used to train the models linear regression, random forest, XGBoost, and AdaBoost, allowing them to comprehend the patterns and relationships between population, GDP, and carbon dioxide emissions, energy consumption. The results revealed that random forest, XGBoost, and AdaBoost outperformed linear regression. Furthermore, for random forest, XGBoost, and AdaBoost, the coefficients of determination were higher, indicating a better fit to the data. Moreover, time series forecasting models such as autoregressive integrated moving average, seasonal autore- gressive integrated moving average, and exponential smoothing were used to predict future energy consumption and carbon dioxide emissions in Vietnam. The models were trained and verified using historical data. The time series model findings showed that energy consumption rose steadily during the predicted timeframe. The autoregressive integrated moving aver- age model predicted 162258.77 ktoe of energy use by 2050, whereas the seasonal autoregressive integrated moving average and exponential smoothing modes predicted 160673.8 ktoe and 153206.44 ktoe of energy use, respectively. By 2050, the autoregressive integrated moving average model anticipated 6.51 metric tons of carbon dioxide emissions per capita, the SARIMA model 7.769 metric tons, and the exponential smoothing model 6.22 metric tons. The findings show how machine learning techniques and time series models may be used to estimate energy usage and carbon dioxide emissions in Vietnam. These insights could assist Vietnam government in making informed judgments concerning energy planning and policy development