Screening of Natural Oxygen Carriers for Chemical Looping Combustion Based on a Machine Learning Method

Abstract

The screening of high-quality oxygen carriers is a key focus in the field of chemical looping combustion. However, the existing screening methods have the problems of being high cost and having long material design cycles. Here, a machine learning model has been established which successfully predicted the effect of composition, porosity, specific surface area, and other physicochemical properties on the redox performance. A database consisting of 190 samples was used to train the BP-ANN algorithm and the SVM algorithm. The SVM algorithm triumphs over the BP-ANN algorithm in that the best model by the SVM algorithm makes predictions with a high coefficient of determination (R 2 = 0.961) and a low root mean square error (RMSE = 0.014).According to the obtained model, the copper ore was estimated to exhibit high reaction performance in terms of 68% CH 4 conversion and 96% CO conversion at 950 °C. We anticipate the machine learning method can be extended to predict the performance of oxygen carriers for other chemical looping applications.

A machine learning approach for predicting the performance of oxygen carriers in chemical looping oxidative coupling of methane

“…These algorithms were chosen because they are widely used in material prediction and are considered the most commonly used ML regression algorithms. [25][26][27][28][29][30] However, each algorithm has its own unique characteristics, so we trained six different models and selected the best one for our application.…”

Machine Learning for Chemical Looping: Recent Advances and Prospects

“…As shown in Figure 12, we predicted 8 new input oxygen carriers using the optimized ML model and performed experimental validation, which showed that the prediction results were generally consistent with the experimental results. 116 In addition to this, Yan et al 73 collected 19 natural manganese ore oxygen carriers from the literature, analyzed their input sensitivities using the ANN model, and finally predicted the effect of the Fe/Mn ratio on the performance of the oxygen carriers. In CLOCM, various oxygen carriers significantly influence the selectivity of C 2 products.…”

“…Prediction of the performance of new oxygen carriers using ML methods. This figure was reproduced with permission from ref . Copyright 2023 American Chemical Society.…”

Nanoscaled Oxygen Carrier-Driven Chemical Looping for Carbon Neutrality: Opportunities and Challenges

“…67 The use of these machine learning techniques has been proven to be effective and efficient for screening natural oxygen carriers for chemical looping combustion, thereby reducing experimental demands. 68 Different from DFT, which primarily focuses on calculating the electronic structure and static properties of a system, molecular dynamics (MD) simulations can be used for modeling the interactions of molecules within the nanoparticle system over time. For relatively small nanoparticles, such as those with sizes on the order of a few nanometers or smaller, MD simulations can provide detailed insights into their behavior like nanoparticle diffusion, surface interactions, and structural changes.…”

“…Neural network-based functionals and potentials are being explored for DFT calculations, which could expedite the screening and designing process for suitable oxygen carriers . The use of these machine learning techniques has been proven to be effective and efficient for screening natural oxygen carriers for chemical looping combustion, thereby reducing experimental demands . Different from DFT, which primarily focuses on calculating the electronic structure and static properties of a system, molecular dynamics (MD) simulations can be used for modeling the interactions of molecules within the nanoparticle system over time.…”