Prediction of the Control Effect of Fractured Leakage in Unconventional Reservoirs Using Machine Learning Method
Bridging plugging is the most used method of plugging in unconventional oil reservoirs, and many factors affect the effect of bridging and plugging. Since the laboratory cannot simulate the actual leakage size of the lost formation and the corresponding leakage plugging process at the drilling site,...
| Huvudupphovsmän: | , , , , , |
|---|---|
| Materialtyp: | Artikel |
| Språk: | English |
| Publicerad: |
Hindawi-Wiley
2022-01-01
|
| Serie: | Geofluids |
| Länkar: | http://dx.doi.org/10.1155/2022/4145219 |
| _version_ | 1827080037613961216 |
|---|---|
| author | Lei Pu Jianjian Song Mingbiao Xu Jun Zhou Peng Xu Shanshan Zhou |
| author_facet | Lei Pu Jianjian Song Mingbiao Xu Jun Zhou Peng Xu Shanshan Zhou |
| author_sort | Lei Pu |
| collection | DOAJ |
| description | Bridging plugging is the most used method of plugging in unconventional oil reservoirs, and many factors affect the effect of bridging and plugging. Since the laboratory cannot simulate the actual leakage size of the lost formation and the corresponding leakage plugging process at the drilling site, the laboratory experiment results cannot reflect the actual leakage plugging construction effect. Aiming at the problem of frequent fracture leakage during drilling in Chepaizi block, Xinjiang, China, this paper proposes a set of machine learning methods based on a neural network. Three types of factors and 14 parameters with a strong correlation with the leakage control effect were screened out. Three categories of factors include construction parameters, choice of plugging material, and fluid properties of the carrier fluid. The training was carried out based on the collected field data, the appropriate activation function was set, and the deep well network structure was optimized. By improving the field plugging measures in the later period, the model was verified by these actual cases, and the results showed that the established model produced the highest R2 of 0.974, has a good fit, and predicts well. |
| first_indexed | 2024-04-13T14:04:00Z |
| format | Article |
| id | doaj.art-0748d8d3f3cf4c7a99e07716e8996c4c |
| institution | Directory Open Access Journal |
| issn | 1468-8123 |
| language | English |
| last_indexed | 2025-03-20T02:55:05Z |
| publishDate | 2022-01-01 |
| publisher | Hindawi-Wiley |
| record_format | Article |
| series | Geofluids |
| spelling | doaj.art-0748d8d3f3cf4c7a99e07716e8996c4c2024-10-03T07:25:19ZengHindawi-WileyGeofluids1468-81232022-01-01202210.1155/2022/4145219Prediction of the Control Effect of Fractured Leakage in Unconventional Reservoirs Using Machine Learning MethodLei Pu0Jianjian Song1Mingbiao Xu2Jun Zhou3Peng Xu4Shanshan Zhou5School of Petroleum EngineeringSchool of Petroleum EngineeringSchool of Petroleum EngineeringPetroChina Xinjiang Oilfield Development CompanySchool of Petroleum EngineeringSchool of Petroleum EngineeringBridging plugging is the most used method of plugging in unconventional oil reservoirs, and many factors affect the effect of bridging and plugging. Since the laboratory cannot simulate the actual leakage size of the lost formation and the corresponding leakage plugging process at the drilling site, the laboratory experiment results cannot reflect the actual leakage plugging construction effect. Aiming at the problem of frequent fracture leakage during drilling in Chepaizi block, Xinjiang, China, this paper proposes a set of machine learning methods based on a neural network. Three types of factors and 14 parameters with a strong correlation with the leakage control effect were screened out. Three categories of factors include construction parameters, choice of plugging material, and fluid properties of the carrier fluid. The training was carried out based on the collected field data, the appropriate activation function was set, and the deep well network structure was optimized. By improving the field plugging measures in the later period, the model was verified by these actual cases, and the results showed that the established model produced the highest R2 of 0.974, has a good fit, and predicts well.http://dx.doi.org/10.1155/2022/4145219 |
| spellingShingle | Lei Pu Jianjian Song Mingbiao Xu Jun Zhou Peng Xu Shanshan Zhou Prediction of the Control Effect of Fractured Leakage in Unconventional Reservoirs Using Machine Learning Method Geofluids |
| title | Prediction of the Control Effect of Fractured Leakage in Unconventional Reservoirs Using Machine Learning Method |
| title_full | Prediction of the Control Effect of Fractured Leakage in Unconventional Reservoirs Using Machine Learning Method |
| title_fullStr | Prediction of the Control Effect of Fractured Leakage in Unconventional Reservoirs Using Machine Learning Method |
| title_full_unstemmed | Prediction of the Control Effect of Fractured Leakage in Unconventional Reservoirs Using Machine Learning Method |
| title_short | Prediction of the Control Effect of Fractured Leakage in Unconventional Reservoirs Using Machine Learning Method |
| title_sort | prediction of the control effect of fractured leakage in unconventional reservoirs using machine learning method |
| url | http://dx.doi.org/10.1155/2022/4145219 |
| work_keys_str_mv | AT leipu predictionofthecontroleffectoffracturedleakageinunconventionalreservoirsusingmachinelearningmethod AT jianjiansong predictionofthecontroleffectoffracturedleakageinunconventionalreservoirsusingmachinelearningmethod AT mingbiaoxu predictionofthecontroleffectoffracturedleakageinunconventionalreservoirsusingmachinelearningmethod AT junzhou predictionofthecontroleffectoffracturedleakageinunconventionalreservoirsusingmachinelearningmethod AT pengxu predictionofthecontroleffectoffracturedleakageinunconventionalreservoirsusingmachinelearningmethod AT shanshanzhou predictionofthecontroleffectoffracturedleakageinunconventionalreservoirsusingmachinelearningmethod |