Machine Learning for Chemical Looping: Recent Advances and Prospects

Energy & Fuels, Journal Year: 2024, Volume and Issue: 38(13), P. 11541 - 11561

Published: June 20, 2024

Chemical looping is a revolutionary energy conversion method aimed at the low-carbon transformation of fossil fuels. The development this technology primarily involves screening oxygen carriers, design reactors, and optimization process flows, typically requiring extensive experimental trials time consumption. Machine learning, with its high-precision predictive capabilities, can optimize chemical technology. This review comprehensively summarizes methods recent advances in application machine learning outlined typical involving database construction, model analysis, interpretable algorithms. Then, carrier screening, reactor design, flow through are explored. To address challenges found these research developments, potential solutions future perspectives proposed. We hope that offer inspiration for researchers field promote advancement

Language: Английский

---

A hybrid machine learning model for NOx emission concentration prediction from sludge incineration

Process Safety and Environmental Protection, Journal Year: 2025, Volume and Issue: unknown, P. 106854 - 106854

Published: Feb. 1, 2025

Language: Английский

---

High-throughput screening of high-activity oxygen carriers for chemical looping argon purification via a machine learning – density functional theory method

Sustainable Energy & Fuels, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

A new method based on machine learning and DFT calculations for screening oxygen carriers during chemical looping argon purification is proposed in this study.

Language: Английский

---

Prediction of Biomass Chemical Looping Gasification Performance Using the Extra Tree Ensemble Model

Energy & Fuels, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 19, 2025

Language: Английский

---

Prediction of Enthalpy of Mixing of Binary Alloys Based on Machine Learning and CALPHAD Assessments

Metals, Journal Year: 2025, Volume and Issue: 15(5), P. 480 - 480

Published: April 24, 2025

The enthalpy of mixing, a critical thermodynamic property in the liquid phase reflecting element interaction strength and pivotal for studying equilibria, can now be predicted efficiently using machine learning. This study proposes model combining learning with Calculation Phase Diagram (CALPHAD) to predict mixing. We obtained data 583 binary alloy systems from SGTE database, ensuring experimental constraints accuracy. Using pure properties Miedema’s parameters as descriptors, we trained evaluated four algorithms, finding LightGBM perform best (R2 = 92.2%, MAE 3.5 kJ/mol). performance was further optimized through Recursive Feature Elimination (REF) Maximal Information Coefficient (MIC) feature selection methods. Shapley Additive Explanations reveals that primary factors affecting mixing enthalpy, such atomic radius electronegativity, align key Miedema model, thereby confirming physical interpretability our data-driven approach. work offers an accelerated method predicting complex multi-component system thermodynamics. Future research will focus on collecting more high-quality enhance accuracy generalization.

Language: Английский

---

Screening structure and predicting toxicity of pesticide adjuvants using MD simulation and machine learning for minimizing environmental impacts

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 942, P. 173697 - 173697

Published: June 6, 2024

Language: Английский

---

Artificial intelligence driven evolution of perovskite-based solar thermochemical systems for hydrogen production: a narrative review

Emergent Materials, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 16, 2024

Language: Английский

---