Pressure Drop Prediction in Fluidized Dense Phase Pneumatic Conveying using Machine Learning Algorithms

Shijo, J. S.; Behera, N.

doi:10.47176/jafm.16.10.1869

Pressure Drop Prediction in Fluidized Dense Phase Pneumatic Conveying using Machine Learning Algorithms

Document Type : Regular Article

Authors

VIT Vellore, Vellore, Tamilnadu,632014, India

10.47176/jafm.16.10.1869

Abstract

Modeling of pressure drop in fluidized dense phase conveying (FDP) of powders is a tough work as the flow comprises of various interactions among solid, gas and pipe wall. It is difficult to incorporate these interactions into a model. The pressure drop depends on flow, material and geometrical parameters. The existing models show high error when applied to other pipeline configurations of varying pipeline lengths or diameters. The current study investigates the capability of machine learning (ML) techniques to estimate the drop in pressure in FDP conveying of powders. Pneumatic conveying experimental data were used for training the network and then for predicting the pressure drop. For estimating the pressure drop, four distinct ML algorithms light gradient boosting machine (LighGBM)), multilayer perception (MLP), K-nearerst neighbors (KNN), extreme gradient boosting (XGBoost), and were selected. XGBoost model performed better than other models chosen for the study with ±5% error margin while training and testing the data, and ±10% error margin in validating the data. MLP, XGBoost, KNN, and LightGBM models predicted the data of pressure drop with MAE of 5.05, 1.19, 5.72, and 2.85, respectively, for training as well as testing data. Among the four models considered, the model using XGBoost algorithm performed the best, whereas the model using KNN algorithm performed poorly in predicting the FDP conveying pressure drop.

Keywords

Main Subjects

Particle/fluid flow

References

Abbas, F., Yan, Y., & Wang, L. (2020). Mass flow measurement of pneumatically conveyed solids through multi-modal sensing and machine learning. 2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), IEEE, New York, NY, 1–6. https://ieeexplore.ieee.org/document/9128576##

Alkassar, Y., Agarwal, V. K., Pandey, R. K., & Behera, N. (2020). Experimental study and Shannon entropy analysis of pressure fluctuations and flow mode transition in fluidized dense phase pneumatic conveying of fly ash. Particuology, 49, 169-178. https://doi.org/10.1016/j.partic.2019.03.003##

Alkassar, Y., Agarwal, V. K., Pandey, R. K., & Behera, N. (2021a). Influence of particle attrition on erosive wear of bends in dilute phase pneumatic conveying. Wear, 476, 203594. https://doi.org/10.1016/j.wear.2020.203594##

Alkassar, Y., Agarwal, V. K., Pandey, R., & Behera, N. (2021b). Analysis of dense phase pneumatic conveying of fly ash using CFD including particle size distribution. Particulate Science Technology, 39(3), 322–337. https://doi.org/10.1080/02726351.2020.1727592##

Behera, N., Agarwal, V. K., Jones, M. G., & Williams, K. C. (2013a). CFD modeling and analysis of dense phase pneumatic conveying of fine particles including particle size distribution. Powder Technology, 244, 30-37. https://doi.org/10.1016/j.powtec.2013.04.005##

Behera, N., Agarwal, V. K., Jones, M., & Williams, K. C. (2015). Power spectral density analysis of pressure fluctuation in pneumatic conveying of powders. Powder Technology, 33 (5), 510-516. https://doi.org/10.1080/02726351.2015.1008079##

Behera, N., Agarwal, V., Jones, M., & Williams, K. (2013b). Modeling and analysis of solids friction factor for fluidized dense phase pneumatic conveying of powders. Particulate Science Technology, 31 (2), 136–146. https://doi.org/10.1080/02726351.2012.672544##

Chang, Y., Lin, J., Shieh, J., & Abbod, M. (2012). Optimization the initial weights of artificial neural networks via genetic algorithm applied to hip bone fracture prediction. Advances in Fuzzy Systems, 2012, Article ID 951247. https://doi.org/10.1155/2012/951247##

Chen, B. L., Yang, T. F., Sajjad, U., Ali, H. M., & Yan, W. M. (2023). Deep learning-based assessment of saturated flow boiling heat transfer and two-phase pressure drop for evaporating flow. Engineering Analysis with Boundary Elements, 151, 519-537. https://doi.org/10.1016/j.enganabound.2023.03.016##

Datta, V., & Ratnayake, C. (2003). A simple technique for scaling up pneumatic conveying systems. Particulate Science Technology, 21 (3), 227–236. https://doi.org/10.1080/02726350307480##

Davydzenka, T., & Tahmasebi, P. (2022). High-resolution fluid–particle interactions: a machine learning approach. Journal of Fluid Mechanics, 938, A20. https://doi.org/10.1017/jfm.2022.174##

Freund, Y., & Schapire, R. (1999). A short introduction to boosting. Journal of the Japanese Society for Artificial Intelligence, 14(5), 771-780. https://cseweb.ucsd.edu/~yfreund/papers/IntroToBoosting.pdf##

Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T. Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Proceedings of the advances in neural information processing systems, NeurIPS, 3146–3154. https://proceedings.neurips.cc/paper_files/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf##

Kidd, A. J., Zhang, J., & Cheng, R. (2020). A low-error calibration function for an electrostatic gas-solid flow meter obtained via machine learning techniques with experimental data. Energy and Built Environment, 1(2), 224-232. https://doi.org/10.1016/j.enbenv.2020.02.003##

Kim, J. Y., Kim, D., Li, Z. J., Dariva, C., Cao, Y., & Ellis, N. (2023). Predicting and optimizing syngas production from fluidized bed biomass gasifiers: A machine learning approach. Energy, 263:125900. https://doi.org/10.1016/j.energy.2022.125900##

Kim, Y., & Lee, K. (2020). Pressure loss optimization to reduce pipeline clogging in bulk transfer system of offshore drilling rig. Applied Sciences, 10(21), 7515. https://doi.org/10.3390/app10217515##

Kumar, N., Zhang, L., & Nayar, S. (2008). What is a good nearest neighbors algorithm for finding similar patches in images? Proceedings of the European Conference on Computer Vision, Springer, Switzerland AG, 364–378. https://link.springer.com/chapter/10.1007/978-3-540-88688-4_27##

Liu, Z., Yang, X., Ali, H. M., Liu, R., & Yan, J., (2023). Multi-objective optimizations and multi-criteria assessments for a nanofluid-aided geothermal PV hybrid system. Energy Reports, 9, 96-113. https://doi.org/10.1016/j.egyr.2022.11.170##

Loyola-Fuentes, J., Pietrasanta, L., Marengo, M., & Coletti, F. (2022). Machine learning algorithms for flow pattern classification in pulsating heat pipes. Energies, 15(6), 1970. https://doi.org/10.3390/en15061970##

Lu, J., Duan, C., & Zhao, Y. (2022). Machine learning approach to predict the surface charge density of monodispersed particles in gas–solid fluidized beds. ACS Omega, 7(11), 9879-9890. https://doi.org/10.1021/acsomega.2c00299##

Mallick, S. S. (2009). Modeling of fluidized dense phase pneumatic conveying of powders. [Doctoral Thesis, University of Wollongong]. Centre for bulk solid and particulate technologies, Wollongong NSW, Australia##.

Memon, N., Patel, S. B., & Patel, D. P. (2019). Comparative analysis of artificial neural network and XGBoost algorithm for PolSAR image classification. International Conference on Pattern Recognition and Machine Intelligence, Springer, Cham, Switzerland, 452-460. https://link.springer.com/chapter/10.1007/978-3-030-34869-4_49##

Nielsen, D. (2016). Tree boosting with XGBoost-Why does XGBoost win ‘“every”’ machine learning competition? [Master Thesis]. NTNU, Trondheim, Norway. http://hdl.handle.net/11250/2433761##

Rashmi, K. V., & Gilad-Bachrach, R. (2015). Dart: dropouts meet multiple additive regression trees. Proceedings of the Artificial Intelligence and Statistics, PMLR, Microtome Publishing, Brookline, MA, 489–497. https://doi.org/10.48550/arXiv.1505.01866##

Sanchez, L., Vasquez, N., Klinzing, G., & Dhodapkar, S. (2003). Characterization of bulk solids to assess dense phase pneumatic conveying. Powder Technology, 138, 93–117. https://doi.org/10.1016/j.powtec.2003.08.061##

Setia, G., Mallick, S. S., Pan, R., & Wypych, P. W. (2016). Modeling solids friction factor for fluidized dense-phase pneumatic transport of powders using two layer flow theory. Powder Technology, 294, 80–92. https://doi.org/10.1016/j.powtec.2016.02.006##

Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding machine learning: from theory to algorithms. Cambridge University Press, Cambridge, UK. https://doi.org/10.1017/CBO9781107298019##

Shijo, J. S. & Behera, N. (2021). Performance prediction of pneumatic conveying of powders using artificial neural network method. Powder Technology, 388, 149–157. https://doi.org/10.1016/j.powtec.2021.04.071##

Shijo, J. S., & Behera, N. (2017). Transient parameter analysis of pneumatic conveying of fine particles for predicting the change of mode of flow. Particuology, 32, 82–88. https://doi.org/10.1016/j.partic.2016.07.004##

Vapnik, V. (1992). Principles of risk minimization for learning theory. Advances in Neural Information Processing Systems, 831–838.##

Zawawi, N. N. M., Azmi, W. H., Redhwan, A. A. M., Ramadhan, A. I., & Ali, H. M. (2022). Optimization of air conditioning performance with Al2O3-SiO2/PAG composite nanolubricants using the response surface method. Lubricants, 10(10), 243. https://doi.org/10.3390/lubricants10100243##

Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2018). Mixup: beyond empirical risk minimization. ICLR, 2018. https://doi.org/10.48550/arXiv.1710.09412##

Zhang, P., Yang, Y., Huang, Z., Sun, J., Liao, Z., Wang, J., & Yang, Y. (2021). Machine learning assisted measurement of solid mass flow rate in horizontal pneumatic conveying by acoustic emission detection. Chemical Engineering Science, 229, 116083. https://doi.org/10.1016/j.ces.2020.116083##

Zhang, X., & Lei, J. (2019). Study on the optimum design of pneumatic conveying system based on DNN. Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence, 621-625. https://doi.org/10.1145/3366194.3366305##

Zhu, L. T., Tang, J. X., & Luo, Z. H. (2020). Machine learning to assist filtered two‐fluid model development for dense gas–particle flows. AIChE Journal, 66(6), 16973. https://doi.org/10.1002/aic.16973##