Effect of temperature on transport index of fish oil-based drilling mud in high pressure high temperature well: a hybrid model approach.
Saved in:
| Title: | Effect of temperature on transport index of fish oil-based drilling mud in high pressure high temperature well: a hybrid model approach. |
|---|---|
| Authors: | Utthirapathy, Ashadevi1 (AUTHOR) gopinathasha1979@gmail.com, Subbian, Sutha1 (AUTHOR), Jayaprakash, Jayapriya2 (AUTHOR), Arumugam, Ramaswamy3 (AUTHOR) |
| Source: | Journal of Dispersion Science & Technology. 2026, Vol. 47 Issue 6, p981-993. 13p. |
| Subject Terms: | *Drilling muds, *Temperature effect, *Nonlinear regression, *Oil wells, *Rheology, *Artificial neural networks |
| Abstract: | Diesel Oil-based drilling mud used in the oil and gas industry causes severe environmental and public health issues due to its high toxicity, especially in high-pressure, high-temperature (HPHT) wells. Therefore, easily biodegradable synthetic oil-based mud with high drilling performance is essential. Fish oil is a bio-oil known for its non-toxicity, high lubricity, thermal stability, and biodegradability. Effective hole cleaning is crucial for drilling performance and is ensured by the rheological properties of drilling mud. While rheological parameter prediction can be performed using an artificial neural network (ANN) based model, such models often fail to provide accurate predictions for unseen data. In contrast, empirical models are more robust and facilitate generalization. This study aims at assessment of the suitability of invert emulsion fish oil-based drilling mud (IEFOBDM) in HPHT wells through evaluation of hole cleaning performance (HCP) using a hybrid approach that combines an ANN with nonlinear regression (NLR) for temperatures ranging from 40 °C to 80 °C.Firstly, an ANN model was developed considering mud weight, temperature, and shear rate. Secondly, the NLR model was used in the prediction of rheological parameters, namely, Yield point (YP) and Plastic viscosity (PV), based on the predicted shear stress from the ANN model. Finally, the performance metrics of the ANN-NLR rheological model were evaluated using the root mean square error (RMSE) and correlation coefficient (R2) and comparison made with the Single ANN rheological model. The results showed the outperformance of ANN-NLR model over the ANN model for rheological parameter prediction, with R2 values of (0.99) for YP and (1) for PV. The predicted PV and YP values were then used for evaluation of transport index (TI) for HCP analysis. The effect of temperature on TI analysis showed this with increase in temperature, TI also increased, indicating the proposed mud providing good HCP under HPHT conditions. HIGHLIGHTS: Analyze the rheological characteristics of invert emulsion fish oil-based drilling mud(IEFOBDM) against different temperatures in high -pressure, high-temperature well condition. Prediction of shear stress using artificial neural network(ANN) model. Prediction of plastic viscosity(PV) and yield point(YP) based on shear-stress using non-linear regression (NLR)model. Development of a hybrid model by combining ANN and NLR model for limited experimental dataset to predict YP and PV accurately. Investigate the effect of temperature on hole cleaning performance of IEFOBDM by evaluating transport index(TI). [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Diesel Oil-based drilling mud used in the oil and gas industry causes severe environmental and public health issues due to its high toxicity, especially in high-pressure, high-temperature (HPHT) wells. Therefore, easily biodegradable synthetic oil-based mud with high drilling performance is essential. Fish oil is a bio-oil known for its non-toxicity, high lubricity, thermal stability, and biodegradability. Effective hole cleaning is crucial for drilling performance and is ensured by the rheological properties of drilling mud. While rheological parameter prediction can be performed using an artificial neural network (ANN) based model, such models often fail to provide accurate predictions for unseen data. In contrast, empirical models are more robust and facilitate generalization. This study aims at assessment of the suitability of invert emulsion fish oil-based drilling mud (IEFOBDM) in HPHT wells through evaluation of hole cleaning performance (HCP) using a hybrid approach that combines an ANN with nonlinear regression (NLR) for temperatures ranging from 40 °C to 80 °C.Firstly, an ANN model was developed considering mud weight, temperature, and shear rate. Secondly, the NLR model was used in the prediction of rheological parameters, namely, Yield point (YP) and Plastic viscosity (PV), based on the predicted shear stress from the ANN model. Finally, the performance metrics of the ANN-NLR rheological model were evaluated using the root mean square error (RMSE) and correlation coefficient (R2) and comparison made with the Single ANN rheological model. The results showed the outperformance of ANN-NLR model over the ANN model for rheological parameter prediction, with R2 values of (0.99) for YP and (1) for PV. The predicted PV and YP values were then used for evaluation of transport index (TI) for HCP analysis. The effect of temperature on TI analysis showed this with increase in temperature, TI also increased, indicating the proposed mud providing good HCP under HPHT conditions. HIGHLIGHTS: Analyze the rheological characteristics of invert emulsion fish oil-based drilling mud(IEFOBDM) against different temperatures in high -pressure, high-temperature well condition. Prediction of shear stress using artificial neural network(ANN) model. Prediction of plastic viscosity(PV) and yield point(YP) based on shear-stress using non-linear regression (NLR)model. Development of a hybrid model by combining ANN and NLR model for limited experimental dataset to predict YP and PV accurately. Investigate the effect of temperature on hole cleaning performance of IEFOBDM by evaluating transport index(TI). [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 01932691 |
| DOI: | 10.1080/01932691.2024.2428349 |
