Self-adapting anti-surge intelligence control and numerical simulation of centrifugal compressors based on RBF neural network
Anti-surge control of centrifugal compressors is an essential issue for the operation of long-distance natural gas pipeline systems. A suitable controller can make a centrifugal compressor runs smoothly and stably and improve the economy. This work presents a new intelligence control strategy with s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484722001354 |
| _version_ | 1797902119531970560 |
|---|---|
| author | San He Mengyu Xie Patioon Tontiwachwuthikul Christine Chan Jianfeng Li |
| author_facet | San He Mengyu Xie Patioon Tontiwachwuthikul Christine Chan Jianfeng Li |
| author_sort | San He |
| collection | DOAJ |
| description | Anti-surge control of centrifugal compressors is an essential issue for the operation of long-distance natural gas pipeline systems. A suitable controller can make a centrifugal compressor runs smoothly and stably and improve the economy. This work presents a new intelligence control strategy with self-adapting ability. The strategy includes the proportional integral (PI) control self-tuned by radial basis function neural network (RBF-NN), recycle trip control, special derivative control, surge line correction, and asymmetric output of the controller. A hybrid numerical simulation platform is built to validate the anti-surge strategy, and a real centrifugal compressor is simulated. The results show that the strategy makes the anti-surge valve respond quickly, decreases the surge control line’s margin and backflow rate, and improves the economy. In the controller, the special derivative control can make the anti-surge valve open earlier and effectively reduce the fluctuating of inlet flow rate. Aiming at the problem that the gradient descent method is more sensitive to the initial value when solving RBF-NN, a hybrid algorithm of k-means, recursive least square, and gradient descent (KRG algorithm) is proposed. It is successfully applied in the anti-surge controller. Even if the given RBF-NN initial parameters are not good enough, the KRG algorithm illustrates good learning stability and increases the adaptive ability of RBF-NN. |
| first_indexed | 2024-04-10T09:12:45Z |
| format | Article |
| id | doaj.art-ffcee07032254d87bc92c1f28e2a331e |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-04-10T09:12:45Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-ffcee07032254d87bc92c1f28e2a331e2023-02-21T05:10:16ZengElsevierEnergy Reports2352-48472022-11-01824342447Self-adapting anti-surge intelligence control and numerical simulation of centrifugal compressors based on RBF neural networkSan He0Mengyu Xie1Patioon Tontiwachwuthikul2Christine Chan3Jianfeng Li4Petroleum Engineering School, Southwest Petroleum University, China; University of Regina, Canada; Corresponding author at: Petroleum Engineering School, Southwest Petroleum University, China.Petroleum Engineering School, Southwest Petroleum University, ChinaUniversity of Regina, CanadaUniversity of Regina, CanadaPetroleum Engineering School, Southwest Petroleum University, China; Gas Transmission Division, Southwest Oil & Gas Field Company, CNPC, ChinaAnti-surge control of centrifugal compressors is an essential issue for the operation of long-distance natural gas pipeline systems. A suitable controller can make a centrifugal compressor runs smoothly and stably and improve the economy. This work presents a new intelligence control strategy with self-adapting ability. The strategy includes the proportional integral (PI) control self-tuned by radial basis function neural network (RBF-NN), recycle trip control, special derivative control, surge line correction, and asymmetric output of the controller. A hybrid numerical simulation platform is built to validate the anti-surge strategy, and a real centrifugal compressor is simulated. The results show that the strategy makes the anti-surge valve respond quickly, decreases the surge control line’s margin and backflow rate, and improves the economy. In the controller, the special derivative control can make the anti-surge valve open earlier and effectively reduce the fluctuating of inlet flow rate. Aiming at the problem that the gradient descent method is more sensitive to the initial value when solving RBF-NN, a hybrid algorithm of k-means, recursive least square, and gradient descent (KRG algorithm) is proposed. It is successfully applied in the anti-surge controller. Even if the given RBF-NN initial parameters are not good enough, the KRG algorithm illustrates good learning stability and increases the adaptive ability of RBF-NN.http://www.sciencedirect.com/science/article/pii/S2352484722001354Centrifugal compressorAnti-surge controlRBF neural networkSelf-adapting |
| spellingShingle | San He Mengyu Xie Patioon Tontiwachwuthikul Christine Chan Jianfeng Li Self-adapting anti-surge intelligence control and numerical simulation of centrifugal compressors based on RBF neural network Energy Reports Centrifugal compressor Anti-surge control RBF neural network Self-adapting |
| title | Self-adapting anti-surge intelligence control and numerical simulation of centrifugal compressors based on RBF neural network |
| title_full | Self-adapting anti-surge intelligence control and numerical simulation of centrifugal compressors based on RBF neural network |
| title_fullStr | Self-adapting anti-surge intelligence control and numerical simulation of centrifugal compressors based on RBF neural network |
| title_full_unstemmed | Self-adapting anti-surge intelligence control and numerical simulation of centrifugal compressors based on RBF neural network |
| title_short | Self-adapting anti-surge intelligence control and numerical simulation of centrifugal compressors based on RBF neural network |
| title_sort | self adapting anti surge intelligence control and numerical simulation of centrifugal compressors based on rbf neural network |
| topic | Centrifugal compressor Anti-surge control RBF neural network Self-adapting |
| url | http://www.sciencedirect.com/science/article/pii/S2352484722001354 |
| work_keys_str_mv | AT sanhe selfadaptingantisurgeintelligencecontrolandnumericalsimulationofcentrifugalcompressorsbasedonrbfneuralnetwork AT mengyuxie selfadaptingantisurgeintelligencecontrolandnumericalsimulationofcentrifugalcompressorsbasedonrbfneuralnetwork AT patioontontiwachwuthikul selfadaptingantisurgeintelligencecontrolandnumericalsimulationofcentrifugalcompressorsbasedonrbfneuralnetwork AT christinechan selfadaptingantisurgeintelligencecontrolandnumericalsimulationofcentrifugalcompressorsbasedonrbfneuralnetwork AT jianfengli selfadaptingantisurgeintelligencecontrolandnumericalsimulationofcentrifugalcompressorsbasedonrbfneuralnetwork |