General models for predicting the liquid thermal conductivity of fatty acid esters based on smart methods
This study aimed to develop reliable models for calculating the thermal conductivity of fatty acid esters, a class of biodiesels. To reach this target, an extensive database, including 1,641 experimental measurements, was extracted from the published sources. The foregoing database cover the thermal...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-04-01
|
| Series: | Energy Conversion and Management: X |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590174525001552 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study aimed to develop reliable models for calculating the thermal conductivity of fatty acid esters, a class of biodiesels. To reach this target, an extensive database, including 1,641 experimental measurements, was extracted from the published sources. The foregoing database cover the thermal conductivities of 22 different fatty acid esters over a wide spectrum of conditions. The advanced modeling techniques of Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were utilized to find the relationships between thermal conductivity and influential factors. A general and straightforward thermal conductivity correlation was also constructed employing the Gene Expression Programming (GEP) method. Evaluations based on statistical indices and visual techniques demonstrated that all of the developed models are capable of predicting thermal conductivity with a high degree of accuracy, because the majority of their predictions fell within a ± 2 % error band. However, the ANFIS model exhibited the highest agreement with experimental observations, achieving a Mean Absolute Percentage Error (MAPE) of 0.47 % and an R2 value of 99.66 % for the testing dataset. The intelligent models favorably simulated the impact of pressure, temperature, and the physical characteristics of the fuels on thermal conductivity. A comparison with literature correlations showed that the novel models offer significant improvements in the thermal conductivity prediction. Finally, a sensitivity analysis was performed to identify the relative importance of various factors in controlling the thermal conductivity of fatty acid esters. Overall, this study highlighted the capability of smart modeling tools for simulating the thermal conductivity of fatty acid esters. |
|---|---|
| ISSN: | 2590-1745 |