This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
The reliable operation of gas-pumping units (GPU) is due to their current technical state, which needs to be monitored in real-time, requires the use of effective methods for diagnosing GPU. A particularly relevant problem is the assessment of the current technical condition of the GPU GTC- 25I of Nuovo Pignone company, which is installed at the Urengoy-Pomari-Uzhgorod main gas pipeline. The results of long-term development of methods for diagnosing the technical state of GTC-25I, installed at the Bogorodchansky compressor station LPAMP MPA "Prykarpatransgas", are considered. For many years, experiments were conducted in which vibration and acoustic vibration parameters were recorded with the help of specially developed technical means, as well as with the use of a standard SCADA system. The results of the method development of parametric diagnostics of GTC- 25I are based on the use of discriminant analysis of its technological parameters. The choice of 8 of 16 technological parameters of GPU operation is justified, which were subsequently subject to discriminant analysis. The results of the development of the method of diagnosing GTC- 25l and the use of artificial neural networks (ANN), in particular, a two-layer hierarchical ANN of direct distribution, which trains under the algorithm of back propagation of error, are presented. It is shown that the method of diagnostics of GPU GTC- 25I of “Nuovo-Pignone” company on the basis of artificial neural networks allows to increase the reliability of control of its technical state and can be used to control the technical condition of other types of GPU.
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.
