Acoustic signal is more and more frequently used to diagnose machines operated in industrial conditions where installation of sensors is hindered. Impact of background noise seems to be the major problem as part of analysis of such signal. In most cases of industrial environments, background level is high; thus, it prevents against concluding as per standard methods that have been used in diagnostic testing. This study specifies the problem related to diagnosing machines operated under variable loads. Synchronous methods are used for diagnosing these types of machines, those include synchronisation of diagnostic signal with revolutions of the diagnosed machine. For the purpose of this study an acoustic signal was used as the diagnostic signal. Application of the synchronous method (order analysis) enables eliminating an impact of background noise derived from other sources. This study specifies application of acoustic signal to diagnose planetary gear in laboratory testing rig in order to discover damages at early stage of degradation. This method was compared with the method basing on measurement of vibrations.
In this paper deep neural networks are proposed to diagnose inter-turn short-circuits of induction motor stator windings operating under the Direct Field Oriented Control method. A convolutional neural network (CNN), trained with a Stochastic Gradient Descent with Momentum method is used. This kind of deep-trained neural network allows to significantly accelerate the diagnostic process compared to the traditional methods based on the Fast Fourier Transform as well as it does not require stationary operating conditions. To assess the effectiveness of the applied CNN-based detectors, the tests were carried out for variable load conditions and different values of the supply voltage frequency. Experimental results of the proposed induction motor fault detection system are presented and discussed.
The subject of the paper is the analysis of factors determining the value of multi-entity organizations in the energy sector and their ranking according to the degree of impact on this value. For this purpose, statistical methods were used, which are best suited to determine the order of diagnostic features according to a specific criterion. The survey covered companies from the Polish energy sector, while the process itself is based on aggregated data, which represents the financial data of capital groups currently operating in the Polish energy sector.
The first part of the article presents a short description of the Polish energy sector, paying particular attention to the organizational structure of the sector, i.e. companies operating on the domestic energy market. The nature of a multi-entity enterprise as a typical economic unit in the sector is described. The second part of the article describes the assumptions of multidimensional comparative analysis (MCA) as a tool for comparing multifunctional units. The MCA makes it possible to find the most important parameters or indicators having the greatest impact on the value of a multi-entity organization, i.e. a capital group. The survey covered four companies from the Polish energy sector: TAURON Polska Energia SA, ENEA SA, ENERGA SA and PGE Polska Grupa Energetyczna SA.
The study with the use of MCA was conducted in three stages:
- in the first stage, on the basis of information contained in the financial statements, a matrix of diagnostic features was created, describing the financial condition of the examined entity,
- in the second stage, the values of diagnostic variables were normalized/unified; two methods of normalization were applied: the method of standardization and zero unitization,
- in the third stage, the diagnostic variables were grouped using two methods: the model measure of Hellwig’s development and the non-standard measure of development.
The results of the analysis are illustrated by tables and figures.
This paper presents an analysis of use of ultrasonic standing wave in cell separation from bodily fluids based on the example of erythrocyte separation from plasma. It describes movement of red blood cells in plasma under the influence of the acoustic field (whose forces result from interaction of red blood cells with plasma as the vibrating medium) and under the influence of resistance forces in Stokes’ and Oseen’s approximation. The general properties of solutions of the motion equation are given. The solutions for the parameters of the ultrasonic wave and blood cells which are interesting in terms of practical applications in medical diagnostics are discussed. Time constants of the cell transportation to the regions of stable equilibrium in the field of ultrasonic standing wave are estimated. The formulas which determine the time needed to obtain the assumed concentration increase in plasma in nodes and/or anti-nodes of the standing wave are derived.
The reliable and rapid diagnosis of infectious animal diseases presents an exceptionally im- portant aspect when considering their control and prevention. The paper describes the compara- tive evaluation of two rapid isothermal amplification methods for diagnosis of African swine fever (ASF). The robustness of loop-mediated isothermal amplification (LAMP) and the cross-priming amplification (CPA) were compared using samples obtained from ASF confirmed animals. Both assays were evaluated in order to define their diagnostic capabilities in terms of ASF diagnosis and reproducibility of the results. Investigations showed no cross-reactivity for other pig patho- gens and no significant differences in the specificity of both assays. The sensitivity of LAMP reached 90%, while that of CPA was 70%. In conclusion, both methods are suitable for imple- mentation in preliminary ASF diagnosis but further improvements are required to enhance their diagnostic sensitivity.
The article presents the assumptions, characteristics and description of the implementation of a pilot system for on-line monitoring of partial discharges in heads of the high-voltage cable lines. The main purpose of the implementation was to increase the reliability of cable line heads by equipping them with a system of continuous assessment of technical condition with direct transmission of measurement data and alarms to the SCADA system. In order to achieve the assumed goal, unconventional methods for measuring partial discharges were used, the application of which does not require disconnecting the line from the voltage. The implementation was carried out on an active 110 kV high voltage cable line in the area of activity of one of the Distribution System Operators.