A quantitative investigation on pyrolysis behaviors of metal ion-exchanged coal macerals by interpretable machine learning algorithms

Created by W.Langdon from gp-bibliography.bib Revision:1.8414

@Article{Yao:2024:energy,

• author = "Qiuxiang Yao and Linyang Wang and Mingming Ma and Li Ma and Lei He and Duo Ma and Ming Sun",
• title = "A quantitative investigation on pyrolysis behaviors of metal ion-exchanged coal macerals by interpretable machine learning algorithms",
• journal = "Energy",
• year = "2024",
• volume = "300",
• pages = "131614",
• keywords = "genetic algorithms, genetic programming, Coal pyrolysis, Maceral, Ion-exchange, Machine learning, Symbolic regression",
• ISSN = "0360-5442",
• URL = "https://www.sciencedirect.com/science/article/pii/S0360544224013872",
• DOI = "doi:10.1016/j.energy.2024.131614",
• abstract = "Generalizing the rules from complex processes such as catalytic pyrolysis to guide their process control is always a difficult but attractive task. The influences of ion-exchange of metal ions (Na+, K+, Ca2+, Mg2+, Co2+ and Ni2+) on the pyrolysis behaviour of vitrinite and inertinite from Shendong coal were investigated by thermogravimetric analyser-Fourier transform infrared spectrometer (TG-FTIR), fixed-bed reactor (FBR), gas chromatograph-mass spectrometer (GC-MS) and X-ray diffractometer (XRD). A set of machine learning models was successfully constructed based on random forest, support vector machine, and Gaussian process regression, to quantify the relationships between pyrolysis behaviours and the properties of metals and macerals. The leave-one-out-cross validation showed that there are considerable determination coefficients (R2 > 0.9) between predicted and experimental values for most responses (17 out of 29). By combining genetic programming-based symbolic regression with the black-box algorithm, 23 symbolic regression expressions with high confidence were successfully constructed. This work is a pioneering attempt of optimisation in small-scale experiments. By using the highly interpretable models, a demand-orientated (multi-)optimisation coal pyrolysis can be achieved. The bi-objective optimisation was conducted on the yield of tar and the content of light aromatics in tar, and the results show that Co is the optimal loading metal",

}

Genetic Programming entries for Qiuxiang Yao Linyang Wang Mingming Ma Li Ma Lei He Duo Ma Ming Sun

Citations