军事知识服务平台
基于激光诱导击穿光谱与主导因素模型的煤炭灰分智能定量分析方法
Intelligent quantitative analysis of coal ash content based on laser-induced breakdown spectroscopy and dominant factor model
摘要 煤炭作为我国重要的基础能源,其清洁高效利用对实现"双碳"目标具有重要意义.煤质参数的快速、准确获取是实现煤炭高效利用的前提.然而,传统灰分测定方法流程复杂、耗时较长,难以满足实时监测需求.激光诱导击穿光谱(LIBS)技术具有快速、原位、多元素同步分析等优势,为煤灰分产率快速检测提供了新的技术路径.然而,在实际应用中,LIBS技术易受基体效应和光谱信号稳定性影响,导致定量分析精度不足.因此,提出了一种基于主导因素-残差修正的自注意力神经网络(DRAN)模型.该模型采用双分支并行架构,将物理驱动的特征谱线分析与数据驱动的全局特征学习相结合:一方面,主导因素分支基于目标元素的特征谱线构建子模型,以增强模型预测结果的物理可解释性;另一方面,残差修正分支引入自注意力机制,对全谱信息进行动态加权与特征融合,以提升模型对复杂样本的适应能力和泛化性能.为验证模型性能,采用 2组不同来源的煤样灰分 LIBS数据集,对所提出的 DRAN模型与常用基线方法进行对比分析.试验结果表明,DRAN在2组数据集的测试集上均表现出最优性能,其预测均方根误差(RMSEP)分别为 0.996%和 2.448%,相较于表现最优的基线模型,误差分别降低了 9.2%和 13.3%.结果表明,即使在测试样本分布超出训练范围的情况下,模型仍保持稳定预测性能,表现出较好的外推能力.此外,通过消融试验与贡献度分析发现,主导因素分支与自注意力机制的协同作用是提升模型性能与外推能力的关键因素,且模型的预测结果与灰分主量元素的特征谱线高度相关,说明所提出的模型具有明确的物理意义.相比传统方法,DRAN模型通过融合物理机理与深度学习方法,有效提升了 LIBS技术在复杂基体条件下智能定量分析的能力,为煤灰分产率的快速、精准检测提供了新的解决方案.
Abstract:
As an important basic energy in China,the clean and efficient utilization of coal is of great significance to achieve the goal of"double carbon".The rapid and accurate acquisition of coal quality parameters is the premise to realize the efficient utilization of coal.However,the traditional coal ash content determination method is complex and time-consuming,and it is difficult to meet the needs of real-time monitoring.Laser-induced breakdown spectroscopy(LIBS)technology provides a new idea for rapid detection of coal ash content due to its advantages of rapid,in-situ and multi-element simultaneous analysis.However,LIBS technology is affected by matrix effect and signal stability in practical applications,resulting in insufficient quantitative analysis accuracy.Therefore,this paper proposes a self-atten-tion neural network(DRAN)model based on dominant factor-residual correction.The model combines physical-driven feature line analys-is with data-driven global feature learning by using a dual-branch parallel architecture.On the one hand,the dominant factor branch con-structs a sub-model based on the feature line of the target element to ensure the physical interpretability of the model prediction.On the other hand,the residual correction branch introduces a self-attention mechanism to dynamically weight and fuse the full-spectrum informa-tion,thereby improving the adaptability and generalization performance of the model to complex samples.In order to verify the perform-ance of the model,two sets of LIBS data sets of coal ash from different sources were used to compare the proposed model with the com-monly used baseline methods.The results show that DRAN shows the best performance on the test sets of the two sets of data sets,and its root mean square error of prediction(RMSEP)is 0.996%and 2.448%,respectively.Compared with the baseline model with the best per-formance,the errors are reduced by 9.2%and 13.3%,respectively.The results confirm that the model still maintains stable prediction per-formance and shows good extrapolation ability when the distribution of test samples exceeds the training range.In addition,through abla-tion experiments and contribution analysis,it is found that the synergy between the dominant factor branch and the self-attention mechan-ism plays a key role in improving the performance and extrapolation ability of the model,and the prediction results of the model are highly correlated with the ash-related characteristic lines,which has clear physical significance.Compared with the traditional method,the pro-posed DRAN model effectively improves the intelligent quantitative analysis ability of LIBS technology under complex matrix conditions by integrating physical mechanism and deep learning method,and provides a new solution for the accurate detection of coal quality.
刊 名 煤炭科学技术 ISTICEIPKU
年,卷(期): 2026, 54(9)
分类号: TD20
机标分类号: F832.5 F224.0 TP391
在线出版日期: 2026年10月22日
基金项目: 2023YFE0204600:碳中和与能源智联国际大科学计划资助项目SZQZ2025-3-003:煤炭无人化开采数智技术全国重点实验室开放基金资助项目23-54:中国中煤重点科技资助项目,