Combined flow prediction model for natural gas pipeline network based on EMD-Attention-GRU
In order to overcome the deficiency of the traditional time series prediction method in flow prediction of natural gas pipeline networks, a combined prediction model based on Empirical Mode Decomposition (EMD), Attention and Gated Recurrent Unit (GRU) was proposed. Specifically, the model is to subs...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Oil & Gas Storage and Transportation
2023-10-01
|
| Series: | You-qi chuyun |
| Subjects: | |
| Online Access: | https://yqcy.pipechina.com.cn/cn/article/doi/10.6047/j.issn.1000-8241.2023.10.013 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841525871239757824 |
|---|---|
| author | Jiacheng MEN Yuguang FAN Lin GAO Hongxian LIN Ke ZHANG |
| author_facet | Jiacheng MEN Yuguang FAN Lin GAO Hongxian LIN Ke ZHANG |
| author_sort | Jiacheng MEN |
| collection | DOAJ |
| description | In order to overcome the deficiency of the traditional time series prediction method in flow prediction of natural gas pipeline networks, a combined prediction model based on Empirical Mode Decomposition (EMD), Attention and Gated Recurrent Unit (GRU) was proposed. Specifically, the model is to substitute the raw flow data of the natural gas pipeline network with its time series component obtained through Empirical Mode Decomposition (EMD), input the intrinsic mode function component obtained into the GRU neural network, calculate the attention probability weight at different times with the attention integrated into the network, and finally learn in the network and predict the time series of flow in the natural gas pipeline network. The verification results in a natural gas pipeline network show that: the EMD-Attention-GRU combined model demonstrates remarkable performance in flow prediction of natural gas pipeline network, capable of capturing the complex non-linear relationships. Besides, the average absolute percentage error of prediction by the combined model outperforms the single GRU and Attention-GRU models by 6.29% and 5.17%, respectively. Thus, it is indicated that the EMD-Attention-GRU combined model could better address the complexities and dynamic features of flow in natural gas pipeline networks than the conventional time-series prediction methods, with values for promotion and application. |
| format | Article |
| id | doaj-art-a9ed71f2f4f541239fae55b93b812fff |
| institution | Kabale University |
| issn | 1000-8241 |
| language | zho |
| publishDate | 2023-10-01 |
| publisher | Editorial Office of Oil & Gas Storage and Transportation |
| record_format | Article |
| series | You-qi chuyun |
| spelling | doaj-art-a9ed71f2f4f541239fae55b93b812fff2025-01-17T06:49:20ZzhoEditorial Office of Oil & Gas Storage and TransportationYou-qi chuyun1000-82412023-10-0142101193120010.6047/j.issn.1000-8241.2023.10.013yqcy-42-10-1193Combined flow prediction model for natural gas pipeline network based on EMD-Attention-GRUJiacheng MEN0Yuguang FAN1Lin GAO2Hongxian LIN3Ke ZHANG4Mechanical Engineering College, Xi'an Shiyou UniversityMechanical Engineering College, Xi'an Shiyou UniversityMechanical Engineering College, Xi'an Shiyou UniversitySchool of Materials Science and Engineering, Xi'an Shiyou UniversityShaanxi Provincial Natural Gas Co. Ltd.In order to overcome the deficiency of the traditional time series prediction method in flow prediction of natural gas pipeline networks, a combined prediction model based on Empirical Mode Decomposition (EMD), Attention and Gated Recurrent Unit (GRU) was proposed. Specifically, the model is to substitute the raw flow data of the natural gas pipeline network with its time series component obtained through Empirical Mode Decomposition (EMD), input the intrinsic mode function component obtained into the GRU neural network, calculate the attention probability weight at different times with the attention integrated into the network, and finally learn in the network and predict the time series of flow in the natural gas pipeline network. The verification results in a natural gas pipeline network show that: the EMD-Attention-GRU combined model demonstrates remarkable performance in flow prediction of natural gas pipeline network, capable of capturing the complex non-linear relationships. Besides, the average absolute percentage error of prediction by the combined model outperforms the single GRU and Attention-GRU models by 6.29% and 5.17%, respectively. Thus, it is indicated that the EMD-Attention-GRU combined model could better address the complexities and dynamic features of flow in natural gas pipeline networks than the conventional time-series prediction methods, with values for promotion and application.https://yqcy.pipechina.com.cn/cn/article/doi/10.6047/j.issn.1000-8241.2023.10.013natural gas pipeline networkflow predictionempirical mode decomposition (emd)attentiongated recurrent unit (gru) |
| spellingShingle | Jiacheng MEN Yuguang FAN Lin GAO Hongxian LIN Ke ZHANG Combined flow prediction model for natural gas pipeline network based on EMD-Attention-GRU You-qi chuyun natural gas pipeline network flow prediction empirical mode decomposition (emd) attention gated recurrent unit (gru) |
| title | Combined flow prediction model for natural gas pipeline network based on EMD-Attention-GRU |
| title_full | Combined flow prediction model for natural gas pipeline network based on EMD-Attention-GRU |
| title_fullStr | Combined flow prediction model for natural gas pipeline network based on EMD-Attention-GRU |
| title_full_unstemmed | Combined flow prediction model for natural gas pipeline network based on EMD-Attention-GRU |
| title_short | Combined flow prediction model for natural gas pipeline network based on EMD-Attention-GRU |
| title_sort | combined flow prediction model for natural gas pipeline network based on emd attention gru |
| topic | natural gas pipeline network flow prediction empirical mode decomposition (emd) attention gated recurrent unit (gru) |
| url | https://yqcy.pipechina.com.cn/cn/article/doi/10.6047/j.issn.1000-8241.2023.10.013 |
| work_keys_str_mv | AT jiachengmen combinedflowpredictionmodelfornaturalgaspipelinenetworkbasedonemdattentiongru AT yuguangfan combinedflowpredictionmodelfornaturalgaspipelinenetworkbasedonemdattentiongru AT lingao combinedflowpredictionmodelfornaturalgaspipelinenetworkbasedonemdattentiongru AT hongxianlin combinedflowpredictionmodelfornaturalgaspipelinenetworkbasedonemdattentiongru AT kezhang combinedflowpredictionmodelfornaturalgaspipelinenetworkbasedonemdattentiongru |