Continuous carbon anode roasting in industrial parks requires a stable high-temperature heat supply and remains highly dependent on grid electricity and natural gas. However, existing energy-system studies rarely coordinate hydrogen production and storage, volumetric hydrogen blending, and temperature-graded waste-heat recovery under continuous production constraints. To address this gap, this study proposes an electricity–heat–gas–hydrogen integrated energy system for carbon anode industrial parks and develops a 24 h multi-objective scheduling model. The model coordinates heat demands at different temperature levels with hourly electricity and hydrogen flows, using surplus photovoltaic power to produce hydrogen for later high-load periods. The selected scheme achieves a daily volumetric hydrogen-blending ratio of 10.79%, with an operating cost of 82,985.75 CNY and carbon emissions of 54,371.53 kg. Relative to an otherwise equivalent non-hydrogen configuration, hydrogen coupling provides additional reductions of 7.2% in operating cost and 2.3% in carbon emissions. Compared with a basic conventional configuration, operating cost and carbon emissions decrease by 27.9% and 26.0%, respectively. Cascade recovery also increases the daily waste-heat utilization rate by approximately 30 percentage points. These results show that the proposed scheduling framework can coordinate hydrogen utilization and graded waste-heat recovery while maintaining continuous carbon anode production.

The post-combustion carbon capture process with monoethanolamine/piperazine (MEA/PZ) blends encounters notable modeling and optimization challenges. These arise from strong thermodynamic–kinetic nonlinear coupling, as well as limited availability of high-quality experimental data. To address this, we propose a machine learning and multi-objective optimization strategy driven by physicochemical features. By extracting explicit physical features and embedding physicochemical constraints into data-driven models, this study evaluated the predictive performance of three distinct algorithms based on wet-wall column experimental data. These algorithms included natural gradient boosting (NGBoost), sure independence screening and sparsifying operator (SISSO), and gaussian process regression (GPR). Subsequently, an optimization problem aimed at minimizing $P_{{\mathrm{CO}}_2}^{*}$ and maximizing $k_{\mathrm{g}}^{\prime }$ was formulated. The multi-objective beluga whale optimization (MOBWO) algorithm was then employed for global optimization and benchmarked against the traditional non-dominated sorting genetic algorithm II (NSGA-II). Results indicate that the Gaussian process regression (GPR) model performed best when it was enhanced by physicochemical features and optimized via Bayesian hyperparameter tuning. It achieved R² values of 0.989 and 0.953 for $P_{{\mathrm{CO}}_2}^{*}$ and $k_{\mathrm{g}}^{\prime }$, with average absolute relative deviations (AARDs) kept below 15.7% and 12.2% respectively. Feature importance analysis validated the underlying physical laws. Specifically, temperature dictates thermodynamic equilibrium, while CO₂ loading limits mass transfer kinetics. In the optimization phase, MOBWO outperformed NSGA-II by generating a more uniformly distributed Pareto front. Decision-making analysis further identified three typical operating regimes encompassing kinetics-dominant, thermodynamics-dominant, and comprehensive equilibrium conditions. This framework provides a robust paradigm for small-sample modeling and optimization in complex chemical processes.