Search Results (2)

This work outlines the commissioning and initial experiments from a new pilot plant at Arcelor Mittal Gas Lab (Asturias, Spain) designed to decarbonize up to 300 Nm³/h of blast furnace gas (BFG). This investigation intends to demonstrate for the first time at TRL7 the calcium-assisted steel-mill off-gas hydrogen (CASOH) process to decarbonize blast furnace gases. The CASOH process is carried out in packed-bed reactors operating through three main reaction stages: (1) H₂ production via the water–gas shift (WGS) of the CO present in the BFG assisted by the simultaneous carbonation of CaO; (2) oxidation of the Cu-based catalyst with air, and (3) reduction of CuO with a fuel gas to regenerate CaO and produce a concentrated CO₂ stream. The first experimental campaign used 200 kg of commercial Ca- and Cu-based solids mixed to create a 1 m reactive bed, which is sufficient to validate operations and confirm the process’s effectiveness. A product gas with 40% of H₂ is obtained with CO₂ capture efficiency above 95%. Demonstrating at TRL7 the ability to convert BFG into H2-enriched gas with minimal CO/CO₂ enables remarkable decarbonization in steel production while utilizing existing blast furnaces, eliminating the need for less commercially developed production processes. Full article

This paper introduces a novel hyperparameter optimization framework for regression tasks called the Combined-Sampling Algorithm to Search the Optimized Hyperparameters (CASOH). Our approach enables hyperparameter tuning for deep learning models with two hidden layers and multiple types of hyperparameters, enhancing the model’s capacity to work with complex optimization problems. The primary goal is to improve hyperparameter tuning performance in deep learning models compared to conventional methods such as Bayesian Optimization and Random Search. Furthermore, CASOH is evaluated alongside the state-of-the-art hyperparameter reinforcement learning (Hyp-RL) framework to ensure a comprehensive assessment. The CASOH framework integrates the Metropolis-Hastings algorithm with a uniform random sampling approach, increasing the likelihood of identifying promising hyperparameter configurations. Specifically, we developed a correlation between the objective function and samples, allowing subsequent samples to be strongly correlated with the current sample by applying an acceptance probability in our sampling algorithm. The effectiveness of our proposed method was examined using regression datasets such as Boston Housing, Critical heat flux (CHF), Concrete compressive strength, Combined Cycle Power Plant, Gas Turbine CO, and NOx Emission, as well as an ‘in-house’ dataset of lattice-physics parameters generated from a Monte Carlo code for nuclear fuel assembly simulation. One of the primary goals of this study is to construct an optimized deep-learning model capable of accurately predicting lattice-physics parameters for future applications of machine learning in nuclear reactor analysis. Our results indicate that this framework achieves competitive accuracy compared to conventional random search and Bayesian optimization methods. The most significant enhancement was observed in the lattice-physics dataset, achieving a 56.6% improvement in prediction accuracy, compared to improvements of 53.2% by Hyp-RL, 44.9% by Bayesian optimization, and 38.8% by random search relative to the nominal prediction. While the results are promising, further empirical validation across a broader range of datasets would be helpful to better assess the framework’s suitability for optimizing hyperparameters in complex problems involving high-dimensional parameters, highly non-linear systems, and multi-objective optimization tasks. Full article