A transformer is an important part of power transmission and transformation equipment. Once a fault occurs, it may cause a large-scale power outage. The safety of the transformer is related to the safe and stable operation of the power system. Aiming at the problem that the diagnosis result of transformer fault diagnosis method is not ideal and the model is unstable, a transformer fault diagnosis model based on improved particle swarm optimization online sequence extreme learning machine (IPSO-OS-ELM) algorithm is proposed. The improved particle swarmoptimization algorithm is applied to the transformer fault diagnosis model based on the OS-ELM, and the problems of randomly selecting parameters in the hidden layer of the OS-ELM and its network output not stable enough, are solved by optimization. Finally, the effectiveness of the improved fault diagnosis model in improving the accuracy is verified by simulation experiments.
This paper presents the resolution of the optimal reactive power dispatch (ORPD) problem and the control of voltages in an electrical energy system by using a hybrid algorithm based on the particle swarmoptimization (PSO) method and interior point method (IPM). The IPM is based on the logarithmic barrier (LB-IPM) technique while respecting the non-linear equality and inequality constraints. The particle swarmoptimization-logarithmic barrier-interior point method (PSO-LB-IPM) is used to adjust the control variables, namely the reactive powers, the generator voltages and the load controllers of the transformers, in order to ensure convergence towards a better solution with the probability of reaching the global optimum. The proposed method was first tested and validated on a two-variable mathematical function using MATLAB as a calculation and execution tool, and then it is applied to the ORPD problem to minimize the total active losses in an electrical energy network. To validate the method a testwas carried out on the IEEE electrical energy network of 57 buses.
Five models and methodology are discussed in this paper for constructing classifiers capable of recognizing in real time the type of fuel injected into a diesel engine cylinder to accuracy acceptable in practical technical applications. Experimental research was carried out on the dynamic engine test facility. The signal of in-cylinder and in-injection line pressure in an internal combustion engine powered by mineral fuel, biodiesel or blends of these two fuel types was evaluated using the vibro-acoustic method. Computational intelligence methods such as classification trees, particle swarm optimization and random forest were applied.
The near net shaped manufacturing ability of squeeze casting process requiresto set the process variable combinations at their optimal levels to obtain both aesthetic appearance and internal soundness of the cast parts. The aesthetic and internal soundness of cast parts deal with surface roughness and tensile strength those can readily put the part in service without the requirement of costly secondary manufacturing processes (like polishing, shot blasting, plating, hear treatment etc.). It is difficult to determine the levels of the process variable (that is, pressure duration, squeeze pressure, pouring temperature and die temperature) combinations for extreme values of the responses (that is, surface roughness, yield strength and ultimate tensile strength) due to conflicting requirements. In the present manuscript, three population based search and optimization methods, namely genetic algorithm (GA), particle swarm optimization (PSO) and multi-objective particle swarm optimization based on crowding distance (MOPSO-CD) methods have been used to optimize multiple outputs simultaneously. Further, validation test has been conducted for the optimal casting conditions suggested by GA, PSO and MOPSO-CD. The results showed that PSO outperformed GA with regard to computation time.
The Bulletin of the Polish Academy of Sciences: Technical Sciences (Bull.Pol. Ac.: Tech.) is published bimonthly by the Division IV Engineering Sciences of the Polish Academy of Sciences, since the beginning of the existence of the PAS in 1952. The journal is peer‐reviewed and is published both in printed and electronic form. It is established for the publication of original high quality papers from multidisciplinary Engineering sciences with the following topics preferred: Artificial and Computational Intelligence, Biomedical Engineering and Biotechnology, Civil Engineering, Control, Informatics and Robotics, Electronics, Telecommunication and Optoelectronics, Mechanical and Aeronautical Engineering, Thermodynamics, Material Science and Nanotechnology, Power Systems and Power Electronics. Journal Metrics: JCR Impact Factor 2018: 1.361, 5 Year Impact Factor: 1.323, SCImago Journal Rank (SJR) 2017: 0.319, Source Normalized Impact per Paper (SNIP) 2017: 1.005, CiteScore 2017: 1.27, The Polish Ministry of Science and Higher Education 2017: 25 points. Abbreviations/Acronym: Journal citation: Bull. Pol. Ac.: Tech., ISO: Bull. Pol. Acad. Sci.-Tech. Sci., JCR Abbrev: B POL ACAD SCI-TECH Acronym in the Editorial System: BPASTS.
The paper presents optimization of power line geometrical parameters aimed to reduce the intensity of the electric field and magnetic field intensity under an overhead power line with the use of a genetic algorithm (AG) and particle swarm optimization (PSO). The variation of charge distribution along the conductors as well as the sag of the overhead line and induced currents in earth wires were taken into account. The conductor sag was approximated by a chain curve. The charge simulation method (CSM) and the method of images were used in the simulations of an electric field, while a magnetic field were calculated using the Biot–Savart law. Sample calculations in a three-dimensional system were made for a 220 kV single – circuit power line. A comparison of the used optimization algorithms was made.