A production prediction method of single well in water flooding oilfield based on integrated temporal convolutional network model
Since the oil production of single well in water flooding reservoir varies greatly and is hard to predict, an oil production prediction method of single well based on temporal convolutional network (TCN) is proposed and verified. This method is started from data processing, the correspondence betwee...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2022-10-01
|
| Series: | Petroleum Exploration and Development |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1876380422603392 |
| _version_ | 1811251874915942400 |
|---|---|
| author | Lei ZHANG Hongen DOU Tianzhi WANG Hongliang WANG Yi PENG Jifeng ZHANG Zongshang LIU Lan MI Liwei JIANG |
| author_facet | Lei ZHANG Hongen DOU Tianzhi WANG Hongliang WANG Yi PENG Jifeng ZHANG Zongshang LIU Lan MI Liwei JIANG |
| author_sort | Lei ZHANG |
| collection | DOAJ |
| description | Since the oil production of single well in water flooding reservoir varies greatly and is hard to predict, an oil production prediction method of single well based on temporal convolutional network (TCN) is proposed and verified. This method is started from data processing, the correspondence between water injectors and oil producers is determined according to the influence radius of the water injectors, the influence degree of a water injector on an oil producer in the month concerned is added as a model feature, and a Random Forest (RF) model is built to fill the dynamic data of water flooding. The single well history is divided into 4 stages according to its water cut, that is, low water cut, middle water cut, high water cut and extra-high water cut stages. In each stage, a TCN based prediction model is established, hyperparameters of the model are optimized by the Sparrow Search Algorithm (SSA). Finally, the models of the 4 stages are integrated into one whole-life model of the well for production prediction. The application of this method in Daqing Oilfield, NE China shows that: (1) Compared with conventional data processing methods, the data obtained by this processing method are more close to the actual production, and the data set obtained is more authentic and complete. (2) The TCN model has higher prediction accuracy than other 11 models such as Long Short Term Memory (LSTM). (3) Compared with the conventional full-life-cycle models, the model of integrated stages can significantly reduce the error of production prediction. |
| first_indexed | 2024-04-12T16:26:43Z |
| format | Article |
| id | doaj.art-962f3126c69443a398e2fd6c9738fccc |
| institution | Directory Open Access Journal |
| issn | 1876-3804 |
| language | English |
| last_indexed | 2024-04-12T16:26:43Z |
| publishDate | 2022-10-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Petroleum Exploration and Development |
| spelling | doaj.art-962f3126c69443a398e2fd6c9738fccc2022-12-22T03:25:22ZengKeAi Communications Co., Ltd.Petroleum Exploration and Development1876-38042022-10-0149511501160A production prediction method of single well in water flooding oilfield based on integrated temporal convolutional network modelLei ZHANG0Hongen DOU1Tianzhi WANG2Hongliang WANG3Yi PENG4Jifeng ZHANG5Zongshang LIU6Lan MI7Liwei JIANG8PetroChina Research Institute of Petroleum Exploration & Development, Beijing 100083, ChinaPetroChina Research Institute of Petroleum Exploration & Development, Beijing 100083, China; Corresponding authorResearch Institute of Petroleum Exploration and Development, Daqing Oilfield Company, Daqing 163000, ChinaPetroChina Research Institute of Petroleum Exploration & Development, Beijing 100083, ChinaPetroChina Research Institute of Petroleum Exploration & Development, Beijing 100083, ChinaResearch Institute of Petroleum Exploration and Development, Daqing Oilfield Company, Daqing 163000, ChinaPetroChina Research Institute of Petroleum Exploration & Development, Beijing 100083, ChinaPetroChina Research Institute of Petroleum Exploration & Development, Beijing 100083, ChinaPetroChina Research Institute of Petroleum Exploration & Development, Beijing 100083, ChinaSince the oil production of single well in water flooding reservoir varies greatly and is hard to predict, an oil production prediction method of single well based on temporal convolutional network (TCN) is proposed and verified. This method is started from data processing, the correspondence between water injectors and oil producers is determined according to the influence radius of the water injectors, the influence degree of a water injector on an oil producer in the month concerned is added as a model feature, and a Random Forest (RF) model is built to fill the dynamic data of water flooding. The single well history is divided into 4 stages according to its water cut, that is, low water cut, middle water cut, high water cut and extra-high water cut stages. In each stage, a TCN based prediction model is established, hyperparameters of the model are optimized by the Sparrow Search Algorithm (SSA). Finally, the models of the 4 stages are integrated into one whole-life model of the well for production prediction. The application of this method in Daqing Oilfield, NE China shows that: (1) Compared with conventional data processing methods, the data obtained by this processing method are more close to the actual production, and the data set obtained is more authentic and complete. (2) The TCN model has higher prediction accuracy than other 11 models such as Long Short Term Memory (LSTM). (3) Compared with the conventional full-life-cycle models, the model of integrated stages can significantly reduce the error of production prediction.http://www.sciencedirect.com/science/article/pii/S1876380422603392single well production predictiontemporal convolutional networktime series predictionwater flooding reservoir |
| spellingShingle | Lei ZHANG Hongen DOU Tianzhi WANG Hongliang WANG Yi PENG Jifeng ZHANG Zongshang LIU Lan MI Liwei JIANG A production prediction method of single well in water flooding oilfield based on integrated temporal convolutional network model Petroleum Exploration and Development single well production prediction temporal convolutional network time series prediction water flooding reservoir |
| title | A production prediction method of single well in water flooding oilfield based on integrated temporal convolutional network model |
| title_full | A production prediction method of single well in water flooding oilfield based on integrated temporal convolutional network model |
| title_fullStr | A production prediction method of single well in water flooding oilfield based on integrated temporal convolutional network model |
| title_full_unstemmed | A production prediction method of single well in water flooding oilfield based on integrated temporal convolutional network model |
| title_short | A production prediction method of single well in water flooding oilfield based on integrated temporal convolutional network model |
| title_sort | production prediction method of single well in water flooding oilfield based on integrated temporal convolutional network model |
| topic | single well production prediction temporal convolutional network time series prediction water flooding reservoir |
| url | http://www.sciencedirect.com/science/article/pii/S1876380422603392 |
| work_keys_str_mv | AT leizhang aproductionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT hongendou aproductionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT tianzhiwang aproductionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT hongliangwang aproductionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT yipeng aproductionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT jifengzhang aproductionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT zongshangliu aproductionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT lanmi aproductionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT liweijiang aproductionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT leizhang productionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT hongendou productionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT tianzhiwang productionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT hongliangwang productionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT yipeng productionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT jifengzhang productionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT zongshangliu productionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT lanmi productionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel AT liweijiang productionpredictionmethodofsinglewellinwaterfloodingoilfieldbasedonintegratedtemporalconvolutionalnetworkmodel |