Mikołaj Skowron

Dr. Mikołaj Skowron

Department of Electrical and Power Engineering, AGH University of Science and Technology, A. Mickiewicza 30, 30-059, Krakow, Poland
orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 June 2021 in Energies
Verified
Journal Article
Open access
PDF file
GXGu Xiong
Gu Xiong
Krzysztof PrzystupaKrzysztof Przystupa
Krzysztof Przystupa
YTYao Teng
Yao Teng
WXWang Xue
Wang Xue
WHWang Huan
Wang Huan
MBMykola Beshley
Mykola Beshley
With the development of smart power grids, electronic transformers have been widely used to monitor the online status of power grids. However, electronic transformers have the drawback of poor long-term stability, leading to a requirement for frequent measurement. Aiming to monitor the online status frequently and conveniently, we proposed an attention mechanism-optimized Seq2Seq network to predict the error state of transformers, which combines an attention mechanism, Seq2Seq network, and bidirectional long short-term memory networks to mine the sequential information from online monitoring data of electronic transformers. We implemented the proposed method on the monitoring data of electronic transformers in a certain electric field. Experiments showed that our proposed attention mechanism-optimized Seq2Seq network has high accuracy in the aspect of error prediction.

10 May 2022 in Energies
Verified
Journal Article
Open access
PDF file
LSLichao Sun
Lichao Sun
HQHang Qin
Hang Qin
Krzysztof PrzystupaKrzysztof Przystupa
Krzysztof Przystupa
YCYanrong Cui
Yanrong Cui
OKOrest Kochan
Orest Kochan
JSJun Su
Jun Su
Feature selection is the procedure of extracting the optimal subset of features from an elementary feature set, to reduce the dimensionality of the data. It is an important part of improving the classification accuracy of classification algorithms for big data. Hybrid metaheuristics is one of the most popular methods for dealing with optimization issues. This article proposes a novel feature selection technique called MetaSCA, derived from the standard sine cosine algorithm (SCA). Founded on the SCA, the golden sine section coefficient is added, to diminish the search area for feature selection. In addition, a multi-level adjustment factor strategy is adopted to obtain an equilibrium between exploration and exploitation. The performance of MetaSCA was assessed using the following evaluation indicators: average fitness, worst fitness, optimal fitness, classification accuracy, average proportion of optimal feature subsets, feature selection time, and standard deviation. The performance was measured on the UCI data set and then compared with three algorithms: the sine cosine algorithm (SCA), particle swarm optimization (PSO), and whale optimization algorithm (WOA). It was demonstrated by the simulation data results that the MetaSCA technique had the best accuracy and optimal feature subset in feature selection on the UCI data sets, in most of the cases.

13 April 2022 in Sensors
Verified
Journal Article
Open access
PDF file
DGDonatas Gurauskis
Donatas Gurauskis
Krzysztof PrzystupaKrzysztof Przystupa
Krzysztof Przystupa
AKArtūras Kilikevičius
Artūras Kilikevičius
MSMikołaj Skowron
Mikołaj Skowron
Jonas MatijošiusJonas Matijošius
Jonas Matijošius
KKKristina Kilikevičienė
Kristina Kilikevičienė
Optical linear encoders are widely used in manufacturing. They are accurate and have a relatively high resolution and good repeatability. However, there are a lot of side effects, which have an inevitable impact on the performance of an encoder. In general, the majority of these effects could be minimized by the appropriate design of an encoder’s reading head. This paper discusses the working principle of and commonly occurring errors in optical linear encoders. Three different mechanical designs are developed and implemented in the experimental reading head of the linear encoder in order to evaluate how mechanical construction influences the displacement measurement accuracy and total performance of the encoder.

25 May 2017 in IOP Conference Series: Materials Science and Engineering
Verified
Conference Paper
Open access
PDF file
PSPrzemyslaw Syrek
Przemyslaw Syrek
MSMikołaj Skowron
Mikołaj Skowron
The aim of article is to discuss interaction between stents implanted in the body of worker and harmonic magnetic field in the vicinity of electric wires. In last decades, a growing proportion of people has any devices implanted, to list: cardiac pacemakers, cardioverter – defibrillators. Recommendations of International Commision on Non-ionizing Radiation Protection (ICNIRP), and resctrictions imposed in different states, may exlude specific individuals from their duties. The autors focused on the situation, when the employee with stent, works in the immediate vicinity of overhead electric wires, cleaning with dry ice the electric insulators.

1 March 2016 in Gospodarka Surowcami Mineralnymi - Mineral Resources Management
Verified
Journal Article
Open access
PDF file
ACAntoni Cieśla
Antoni Cieśla
WKWojciech Kraszewski
Wojciech Kraszewski
MSMikołaj Skowron
Mikołaj Skowron
Agnieszka SurowiakAgnieszka Surowiak
Agnieszka Surowiak
PSPrzemyslaw Syrek
Przemyslaw Syrek
Static electric fields are used, among others, in technological processes such as electric separation. Electrodynamic separation is a process of separating two or more solid phases of various physical properties by electric field forces. The advantage of electrodynamic separation is possibility of obtaining separation of individual components in dry conditions. This eliminates many operations such as thickening, dewatering, hydrotransportation, additional drying which cause higher energy consumption and higher separation process costs. Efficiency of beneficiation depends on many factors such as: electric properties of feed components, feed particle size distribution, drum rotary speed, electric field intensity in working space of separator, configuration of electrodes or surrounding conditions.The paper presents the working of high-voltage drum separator. The analysis of electric field distribution in separator working space was done. Additionally, distribution of forces acting on particles of dielectric and conductive properties was examined, trajectories of charged particles movement were presented too. The laboratory investigations of electronic wastes were performed in two particle fractions: 0.25–0.5 mm and 0–0.25 mm. It was observed that as a result of selective charging of particles they separate according to surface ability to electrifying what allows to obtain selective separation of components being so-called electronic wastes. The application of electrodynamic drum separator allows to separate such elements as Ti, Cu, Fe, Pb, Sn from plastics occurring in electronic wastes.

1 May 2018
Verified
Conference Paper
Closed access
AZAnna Zielinska
Anna Zielinska
MSMikołaj Skowron
Mikołaj Skowron
Andrzej BienAndrzej Bien
Andrzej Bien
In engineering it is a common practice to apply a mathematical model of a given system in order to describe the behaviour of the system. The main aim of this study is to create a mathematical model of a photovoltaic installation as well as to verify whether such model enables one to assess the effectiveness, operating specification and voltage characteristics of the mentioned installation without the need for creating a real-world working installation. The mathematical models have been prepared for a single photovoltaic cell as well as a series circuit of a couple of cells connected using both a bypass diode. The study has been carried out using Matlab Simulink software in various levels of exposure to Sun rays, various temperatures as well as during a simulation of a partial eclipse of the photovoltaic installation. In order to depict the operation of the mathematical model, a graphic interpretation of the results has been created. The graphic presentation of the data has enabled one to show how temperature and sun-light intensity (changing atmospheric conditions) can influence the voltage characteristics of the photovoltaic modules. It also shows the dependence between power and voltage. The study shows that the mathematical model can be used for exploring anomalies as well as for diagnostics. It also enables one to interpret the results described through an implemented algorithm in a way that would mirror real operating conditions.