发表机构
Applied Artificial Intelligence and INtelligent Systems (AAIINS) Laboratory; University of Scholars; Murdoch University; Charles Darwin University（应用人工智能与智能系统（AAIINS）实验室; 学者大学; 莫道克大学; 查尔斯达尔文大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对电解槽材料分割难题，提出双分支深度学习框架HREM-Net，结合高光谱和RGB图像，通过创新模块、融合模块及损失函数，在相关数据集上取得良好效果，有望用于工业提升电解槽效率和制氢预测性维护。
AI 中文摘要
准确分割电解槽材料对氢能技术中的自动化拆解、可持续回收和循环制造至关重要。但由于材料间视觉相似度高、光谱重叠、形状不规则和类别严重不平衡，该任务具有挑战性。为此提出双分支框架Hyperspectral-RGB Electrolyzer Materials Network (HREM-Net)，结合高光谱成像(HSI)和RGB图像进行分割。实现了多个创新模块，通过自适应门控跨模态融合模块和复合损失函数，在Electrolyzers-HSI数据集上平均类别准确率达91.66%，平均交并比(mIoU)为0.82，优于基线模型。在PCB-Vision数据集上的跨数据集验证显示出良好泛化能力。该工作有潜力应用于工业，提高电解槽效率及制氢预测性维护。
英文摘要
Accurate segmentation of electrolyzer materials is essential for automated disassembly, sustainable recycling, and circular manufacturing in hydrogen technologies. However, this task is challenging due to strong visual similarity between materials, spectral overlap, irregular shapes, and severe class imbalance. To address these challenges, we propose an AI-driven dual-branch framework, Hyperspectral-RGB Electrolyzer Materials Network (HREM-Net), that combines hyperspectral imaging (HSI) and RGB images for electrolyzer material segmentation. We implemented several innovative modules, including Efficient Channel Attention, Coordinate Attention, Mobile Inverted Bottleneck blocks, and Atrous Spatial Pyramid Pooling to capture spectral and spatial features from HSI, and RGB images. With an adaptive gated cross-modal fusion module and composite loss function, HREM-Net achieves a mean class accuracy of 91.66% and a mean Intersection over Union (mIoU) of 0.82 on the Electrolyzers-HSI dataset, outperforming baseline segmentation models. Cross-dataset validation on the PCB-Vision dataset demonstrates strong generalization with 96.91% accuracy and 0.93 mIoU. This work poses its potential as an industrial application to improve electrolyzer efficiency, thereby improving the predictive maintenance of hydrogen production.
