Application of heuristic algorithms in analyzing data to solve the problem of detection of electric centrifugal pumping units
Ensuring effective control and preventing failures of electrical submersible pumps, because of their wide distribution is the relevant and demanded task. The use of automated control systems of electric centrifugal pumping units allows improving the quality and speed of decisions made about their te...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Tomsk Polytechnic University
2018-03-01
|
| Series: | Известия Томского политехнического университета: Инжиниринг георесурсов |
| Subjects: | |
| Online Access: | http://izvestiya.tpu.ru/archive/article/view/1994 |
| _version_ | 1797813135109783552 |
|---|---|
| author | Rustam Ildarovich Valiakhmetov Vil Uzbekovich Yamaliev Stanislav Sergeevich Shubin Aleksey Viktorovich Alferov |
| author_facet | Rustam Ildarovich Valiakhmetov Vil Uzbekovich Yamaliev Stanislav Sergeevich Shubin Aleksey Viktorovich Alferov |
| author_sort | Rustam Ildarovich Valiakhmetov |
| collection | DOAJ |
| description | Ensuring effective control and preventing failures of electrical submersible pumps, because of their wide distribution is the relevant and demanded task. The use of automated control systems of electric centrifugal pumping units allows improving the quality and speed of decisions made about their technical condition. All methods of diagnosing the installation of electrical submersible pumps are aimed at monitoring the state of the composite nodes, and are reduced to the analysis of time series, which are the time scans of the operation parameters. Traditionally applied linear methods of time series research in the last decades have been substantially expanded by nonlinear methods, among which heuristic algorithms were developed significantly. The main aim is to increase the efficiency of determining the technical state of installations of electric centrifugal pumps during operation. Methods. The approach proposed in this paper is based on solving the diagnostic problem by decomposition into the following subtasks: automatic segmentation, formalization and interpretation of the data obtained. Segmentation is considered as a clustering problem, the purpose of which is the establishment of autocorrelation links between the values of the time series with the formation of temporal clusters and adaptive approximation within the established areas while preserving the local features of the signals. For each allocated class of deviations in operation of electric centrifugal pumping units, the decisive rules are formed based on expert knowledge. The main differences from the classical approach to the problem of diagnosis are: the lack of the need for expert participation in solving the clustering problem; providing adaptive approximation within the allocated time intervals; the possibility of implementing interpretable approaches to fault recognition. Results. The authors have proposed the approach based on solving the diagnostic problem by its decomposition into the following subtasks: automatic segmentation, formalization and interpretation of the data obtained. The necessary list of controlled parameters of operation of the electric centrifugal pumping units is determined. The list allows technical diagnosis. |
| first_indexed | 2024-03-13T07:48:55Z |
| format | Article |
| id | doaj.art-52ac0d72f46d45f88771819c8ed32704 |
| institution | Directory Open Access Journal |
| issn | 2500-1019 2413-1830 |
| language | Russian |
| last_indexed | 2024-03-13T07:48:55Z |
| publishDate | 2018-03-01 |
| publisher | Tomsk Polytechnic University |
| record_format | Article |
| series | Известия Томского политехнического университета: Инжиниринг георесурсов |
| spelling | doaj.art-52ac0d72f46d45f88771819c8ed327042023-06-02T21:10:42ZrusTomsk Polytechnic UniversityИзвестия Томского политехнического университета: Инжиниринг георесурсов2500-10192413-18302018-03-013292Application of heuristic algorithms in analyzing data to solve the problem of detection of electric centrifugal pumping unitsRustam Ildarovich ValiakhmetovVil Uzbekovich YamalievStanislav Sergeevich ShubinAleksey Viktorovich AlferovEnsuring effective control and preventing failures of electrical submersible pumps, because of their wide distribution is the relevant and demanded task. The use of automated control systems of electric centrifugal pumping units allows improving the quality and speed of decisions made about their technical condition. All methods of diagnosing the installation of electrical submersible pumps are aimed at monitoring the state of the composite nodes, and are reduced to the analysis of time series, which are the time scans of the operation parameters. Traditionally applied linear methods of time series research in the last decades have been substantially expanded by nonlinear methods, among which heuristic algorithms were developed significantly. The main aim is to increase the efficiency of determining the technical state of installations of electric centrifugal pumps during operation. Methods. The approach proposed in this paper is based on solving the diagnostic problem by decomposition into the following subtasks: automatic segmentation, formalization and interpretation of the data obtained. Segmentation is considered as a clustering problem, the purpose of which is the establishment of autocorrelation links between the values of the time series with the formation of temporal clusters and adaptive approximation within the established areas while preserving the local features of the signals. For each allocated class of deviations in operation of electric centrifugal pumping units, the decisive rules are formed based on expert knowledge. The main differences from the classical approach to the problem of diagnosis are: the lack of the need for expert participation in solving the clustering problem; providing adaptive approximation within the allocated time intervals; the possibility of implementing interpretable approaches to fault recognition. Results. The authors have proposed the approach based on solving the diagnostic problem by its decomposition into the following subtasks: automatic segmentation, formalization and interpretation of the data obtained. The necessary list of controlled parameters of operation of the electric centrifugal pumping units is determined. The list allows technical diagnosis.http://izvestiya.tpu.ru/archive/article/view/1994pumpcentrifugaldiagnosticsanalysisstatusstatistics |
| spellingShingle | Rustam Ildarovich Valiakhmetov Vil Uzbekovich Yamaliev Stanislav Sergeevich Shubin Aleksey Viktorovich Alferov Application of heuristic algorithms in analyzing data to solve the problem of detection of electric centrifugal pumping units Известия Томского политехнического университета: Инжиниринг георесурсов pump centrifugal diagnostics analysis status statistics |
| title | Application of heuristic algorithms in analyzing data to solve the problem of detection of electric centrifugal pumping units |
| title_full | Application of heuristic algorithms in analyzing data to solve the problem of detection of electric centrifugal pumping units |
| title_fullStr | Application of heuristic algorithms in analyzing data to solve the problem of detection of electric centrifugal pumping units |
| title_full_unstemmed | Application of heuristic algorithms in analyzing data to solve the problem of detection of electric centrifugal pumping units |
| title_short | Application of heuristic algorithms in analyzing data to solve the problem of detection of electric centrifugal pumping units |
| title_sort | application of heuristic algorithms in analyzing data to solve the problem of detection of electric centrifugal pumping units |
| topic | pump centrifugal diagnostics analysis status statistics |
| url | http://izvestiya.tpu.ru/archive/article/view/1994 |
| work_keys_str_mv | AT rustamildarovichvaliakhmetov applicationofheuristicalgorithmsinanalyzingdatatosolvetheproblemofdetectionofelectriccentrifugalpumpingunits AT viluzbekovichyamaliev applicationofheuristicalgorithmsinanalyzingdatatosolvetheproblemofdetectionofelectriccentrifugalpumpingunits AT stanislavsergeevichshubin applicationofheuristicalgorithmsinanalyzingdatatosolvetheproblemofdetectionofelectriccentrifugalpumpingunits AT alekseyviktorovichalferov applicationofheuristicalgorithmsinanalyzingdatatosolvetheproblemofdetectionofelectriccentrifugalpumpingunits |