Bowei Zou

Power allocation in wind-powered multi-stack proton exchange membrane (PEM) electrolysis depends on both load-dependent efficiency and thermal response. This study evaluates coordinated allocation, stack rotation and temperature control for four parallel 200 kW stacks. A control-oriented model couples electrochemical and thermal dynamics with rectifier losses and hydrogen compression power. Particle swarm optimisation determines the allocation, an equivalent health index guides stack rotation, and model predictive control (MPC) tracks temperature references from an offline stack-efficiency map. Predicted polarisation voltages differ from experimental data by no more than 1.4% at 313 and 333 K. In annual simulations, rotation reduces the cross-stack index standard deviation from 725.10 to 2.92 h. MPC achieves a simulated temperature-tracking root mean square error of 0.019 K, 91.12% below that of fuzzy proportional–integral–derivative control. Across three representative wind power scenarios, the probability-weighted daily hydrogen production is 199.85 kg, 0.59% above optimal allocation at 333 K. The corresponding increases over equal and sequential allocation are 1.26% and 2.43%, respectively. These results quantify the additional hydrogen yield from load-dependent temperature control and the operating-load balance obtained through stack rotation under the evaluated conditions.

Laser powder bed fusion (L-PBF) has emerged as a core metal additive manufacturing technology for high-end sectors, including aerospace and medical device manufacturing. However, melting anomalies that occur during fabrication accumulate layer by layer, leading to degraded surface quality and impaired mechanical performance of as-built components—a critical bottleneck limiting their large-scale industrial adoption. Accurate and robust layer-wise melting quality recognition remains a challenge due to the complex surface morphologies induced by such melting anomalies. This study presents a machine learning-enabled in situ monitoring approach for layer-wise melting quality identification in L-PBF. By systematically varying laser power and scanning speed, 24 parameter combinations were designed to fabricate specimens with three distinct melting states: over-melting (OM), lack of fusion (LOF), and normal melting. A high-resolution complementary meta–oxide–semiconductor (CMOS) camera was used to capture layer-wise surface images of the specimens, and following abnormal layer filtering and manual validation, a high-quality dataset comprising 5110 layer-wise images was constructed. Two mainstream machine learning approaches were systematically evaluated and optimized for melting quality classification: a support vector machine (SVM) model leveraging handcrafted gray-level co-occurrence matrix (GLCM) texture features achieved a classification accuracy of 96.77%, while a convolutional neural network (CNN) model with end-to-end feature learning directly from raw images attained a superior accuracy of 98.14%. In terms of computational efficiency, the CNN model exhibited a faster inference speed with a per-layer inference time of just 0.036 s, nearly half that of the SVM model (0.068 s per layer). Most critically, the CNN model completely eliminated fatal cross-class misclassification between OM and LOF—an error mode common in the SVM model that would trigger erroneous process corrective actions in practical industrial applications. The findings demonstrate that image-based machine learning provides a reliable technical foundation for intelligent in situ monitoring of the L-PBF process. With its high accuracy, strong robustness, and superior computational efficiency, the CNN model can effectively support on-site operational decision-making, reduce material and time losses, and enhance process stability in industrial settings, thus exhibiting significant potential for practical engineering deployment.