Volume 17, number 1, 2023. Published papers:
Regular papers:
Copy citation: A. E. Okolo, E. Twumasi, E. A. Frimpong, Optimal PID Controller Based on an Improved Sparrow Search Algorithm for Multi-Area Frequency Control, Carpathian Journal of Electrical Engineering, vol. 17, no. 1, pp. 7-20, 2023.
Amobi Edward OKOLO, Elvis TWUMASI, Emmanuel Asuming FRIMPONG, Department of Electrical and Electronic Engineering, Kwame Nkrumah University of Science and Technology Kumasi, Ghana, Okoloedward19@gmail.com, etwumasi.coe@knust.edu.gh, eafrimpong.soe@knust.edu.gh
Keywords: Area control error, automatic generation control, load frequency control, sparrow search algorithm, PID controller
Abstract: To boost power system reliability there must be a good scheme for the automatic generation control to maintain the generation-load balance. The development of this scheme started with the enhancement of the sparrow search algorithm, where the initial population and producer selection was targeted to improve the search quality. The enhancement made was used to optimize the gain parameters of the PID controller increasing the overall system performance. The proposed scheme was tested on the two-area power system in the MATLAB/Simulink environment and comparisons were made with recent publications. Integral time absolute error (ITAE) was used as the performance index. The proposed method shows improved performance with minimum settling time. This work presents the enhancement of the sparrow search algorithm for the automatic generation control of a two-area non-reheat thermal power system.
EXTENDED APPLIED DATA CLEANING METHODS IN OUTLIER DETECTION FOR RESIDENTIAL CONSUMER
Copy citation: D. I. Jurj, D. D. Micu, A. G. Berciu, M. Lancrajan, L. Czumbil, A. Bende, B. A. Mitrache, A. Mureșan, Extended Applied Data Cleaning Methods in Outlier Detection for Residential Consumer, Carpathian Journal of Electrical Engineering, vol. 17, no. 1, pp. 21-31, 2023.
Dacian I. JURJ, Dan D. MICU, Alexandru G. BERCIU, Mircea LANCRAJAN, Levente CZUMBIL, Andrei BENDE, Bogdan A. MITRACHE, Alexandru MUREȘAN, Technical University of Cluj-Napoca, dacian.jurj@ethm.utcluj.ro, Dan.Micu@ethm.utcluj.ro, Alexandru.Berciu@campus.utcluj.ro, lancranjanmircea98@gmail.com, Levente.CZUMBIL@ethm.utcluj.ro, andrei.bende28@gmail.com, bogdan.mitrache99@gmail.com, Alexandru.Muresan@ethm.utcluj.ro
Keywords: Energy measurement, Artificial intelligence, Statistics, Probabilistic computing, Data science, Data aggregation, Algorithms, Energy efficiency
Abstract: This paper delves into the subject of outlier detection techniques tailored for unique datasets related to residential energy consumption. Building upon the current state of research we introduce the Grubbs and Z-score methods and investigate a range of outlier detection strategies encompassing statistical, probabilistic, and machine learning algorithms. The findings underscore the importance of outlier detection in the Romanian residential energy sector.
Copy citation: A. Ramakić, Z. Bundalo, D. Bundalo, Analysis of Different Deep Learning Approaches Based on Deep Neural Networks for Person Re-Identification, Carpathian Journal of Electrical Engineering, vol. 17, no. 1, pp. 32-41, 2023.
Adnan Ramakić1, Zlatko BUNDALO2, Dušanka BUNDALO3, 1Technical Faculty, University of Bihać, Bihać, Bosnia and Herzegovina, 2Faculty of Electrical Engineering, University of Banja Luka, Banja Luka, Bosnia and Herzegovina, 3Faculty of Philosophy, University of Banja Luka, Banja Luka, Bosnia and Herzegovina, adnan.ramakic@unbi.ba, zlatbun2007@gmail.com, dusbun@gmail.com
Keywords: Deep Neural Network (DNN), Person Identification, Person Re-Identification, Convolutional Neural Network (CNN)
Abstract: In this work, different deep learning approaches based on deep neural networks for person re-identification were analyzed. Both identification and re-identification of people are frequently required in various fields of human life. Some of the most common applications are in various security systems where it is necessary to identify and track a particular person. In the case of person identification, the identity of a particular person needs to be established. In the case of re-identification, the main task is to match the identity of a particular person across different, non-overlapping cameras or even with the same camera at different times. In this work, three different deep neural networks were used for the purpose of person re-identification. Two of them were user-defined, while one of them is a pre-trained neural network adapted to work with a specific dataset. Two neural networks used were Convolutional Neural Networks (CNN). For the defined experiment, it was used own dataset with 13 subjects in gait.
THE ELECTRICAL RESISTANCE OF THE LUBRICANT FILM IN THE CASE OF THE HYDRODYNAMIC SLIDING BEARING SUBJECTED TO SHOCKS
Copy citation: I. M. Alexandrescu, R. Cotetiu, A. Cotetiu, D. Daraba, I. L. Alexandrescu, The Electrical Resistance of the Lubricant Film in the Case of the Hydrodynamic Sliding Bearing Subjected to Shocks, Carpathian Journal of Electrical Engineering, vol. 17, no. 1, pp. 42-48, 2023.
Ioan Marius ALEXANDRESCU, Radu COTETIU, Adriana COTETIU, Dinu DARABA, Ioana Laura ALEXANDRESCU,Technical University of Cluj-Napoca, Ioan.Alexandrescu@imtech.utcluj.ro
Keywords: minimal lubricating film, electrical resistance, radial sliding bearing
Abstract: This paper presents experimental research on electrical resistance of the lubricant film, shock absorption in the lubricating film, under different static and dynamic load conditions. We focus on determination of the minimal lubricating film which estimates the minimum lubricating thickness between spindle and bushing in the case of the hydrodynamic sliding bearing subjected to shocks.