Koszalin University of Technology is a public technical university located in Koszalin and other cities, i.e. Chojnice.The institution was established in 1968 as Higher School of Engineering. The university obtained its present name and status in 1996.The university consists of the following faculties and institutes: Faculty of Civil and Environmental engineering Faculty of Economics and Management Faculty of Electronics and Computer Science Faculty of Mechanical Engineering Institute of Mechatronics, Nanotechnology and Vacuum TechniqueThe University is taking part in international exchange programmes, including Erasmus Programme. Wikipedia.
Slowik A.,Koszalin University of Technology
IEEE Transactions on Industrial Electronics | Year: 2011
In this paper, an application of an adaptive differential evolution (DE) algorithm with multiple trial vectors for training artificial neural networks (ANNs) is presented. The proposed method is DE-ANNT+, which is a DE-ANN Training (DE-ANNT) modified by adding a multiple trial vectors technique. DE-ANNT+ allows one to train an ANN of arbitrary architectures, and it offers a nondifferentiable neuron activation function. In contrast to a basic DE algorithm, DE-ANNT+ possesses two modifications. In DE-ANNT+, adaptive selection of control parameters and a multiple trial vectors technique are introduced. Adaptive selection means that the number of required parameters of the algorithm is decreased. The multiple trial vectors technique increases the probability of generating a better solution because a greater number of temporary solutions is generated around the existing solutions. The DE-ANNT+ algorithm, with these two modifications, is used for ANN training to classify the parity-p problem. The results from the obtained algorithm have been compared with results from the following algorithms: an evolutionary algorithm, a DE algorithm without multiple trial vectors, gradient training methods, such as error back-propagation, and the Levenberg-Marquardt method. © 2009 IEEE.
Maciejewski I.,Koszalin University of Technology
Journal of Sound and Vibration | Year: 2012
This paper presents an approach to the control system design of seat suspension systems for the active vibration attenuation. The paper presents the studies of the active vibration control strategy based on the reverse dynamics of force actuator and the primary controller. The multi-criteria optimization procedure is utilized in order to calculate the primary controller settings which subsequently define the vibro-isolation characteristics of active suspensions. As an example of the proposed control system design, the seat with a pneumatic suspension is investigated and its vibro-isolation properties are shaped by an appropriate selection of the controller settings. © 2011 Elsevier Ltd All rights reserved.
Kuczynski W.,Koszalin University of Technology
International Journal of Heat and Mass Transfer | Year: 2012
Experimental research results are presented concerning the condensation of the R404A refrigerant in a five-channel multiport, which is fed in parallel and consists of mini-channels with internal diameter d = 0.90 and 3.30 mm. The research was performed in the presence of periodic instabilities generated in a frequency range from 5 to 0.2 Hz. During condensation in the multiport, the impact of instabilities is considerably stronger that in the case of single mini-channels. It was found that the temperature profiles and pressure profiles became deformed in each of the mini-channels of the multiport during the condensation process with the generated instabilities. These deformations decreased the value of heat transfer coefficient h, whose value depends on the diameter d of the multiport mini-channels, vapour quality x and the frequency f of the disturbances generated. © 2012 Elsevier Ltd. All rights reserved.
Dutkowski K.,Koszalin University of Technology
International Journal of Heat and Mass Transfer | Year: 2010
The results of experimental investigations of heat transfer during the flow of R134a in a minichannel are presented here. The experimental investigations were conducted using a minichannel with a total length of 500 mm and 1.68 mm internal diameter. The heated length of the minichannel was 200 mm, the total mass flow rate of the refrigerant (wρ) = 200-450 kg/m2 s, the inlet subcooling ΔTs = 5-15 K, and the heat flux density q = 1.7-60.3 kW/m2. The results of experimental investigations are presented as a boiling curve. The phenomenon known as the zero boiling crisis and the influence of the flashing phenomenon on the boiling curve show the importance of these elements on heat transfer in single- and two-phase systems. © 2009 Elsevier Ltd. All rights reserved.
Michalkiewicz J.,Koszalin University of Technology
IEEE Transactions on Neural Networks and Learning Systems | Year: 2012
This brief deals with the possibilities of using the modified Kolmogorov's neural network for the identification of non-linear dynamic systems, among them the Wiener and Hammerstein systems. The algorithm of training the network is simple, well convergent and with a small error of approximation. The modified neural network is characterized by a simple computer algorithm; it also omits complicated techniques of back propagation. The simulation results are shown to illustrate the modified Kolmogorov theorem. © 2012 IEEE.