跨仪器和煤炭类型的煤炭质量光谱分析中的校准转移方法研究
Jiaxuan Li1, Jiaxin Yin1, Rui Gao1
1State Key Laboratory of Quantum Optics and Quantum Optics Devices, Institute of Laser Spectroscopy, Shanxi University, Taiyuan, 030006, China; Collaborative Innovation Center of Extreme Optics, Shanxi University, Taiyuan, 030006, China.
Analytica chimica acta
|September 3, 2025
概括
域对抗神经网络 (DANN) 通过在不同仪器和煤类型之间实现强大的光谱校准转移,显著改善了煤炭质量分析. 这种机器学习方法的性能优于传统方法, 需要更少的校准样本才能达到高精度.
科学领域:
- 分析化学
- 光谱学
- 机器学习
背景情况:
- 像NIRS和XRF这样的光谱技术对于快速,非破坏性的煤质分析至关重要.
- 仪器和煤炭类型的变化挑战了已有的校准模型的可靠性.
- 传统的校准转移方法 (Slope/Bias,PDS) 面临复杂的煤矩阵的局限性.
研究的目的:
- 系统地评估和比较传统 (S/B,PDS) 和机器学习 (DANN) 方法用于煤炭分析中的光谱校准转移.
- 评估这些方法在不同仪器和煤炭类型的性能.
- 根据所需的校准样本来确定DANN的效率.
主要方法:
- 使用了两个自主开发的NIRS-XRF煤质量分析仪和264个煤样 (气体和脂肪煤).
- 对比斜率/偏差 (S/B),分片直接标准化 (PDS) 和域对抗神经网络 (DANN) 进行校准转移.
- 使用指标评估性能:确定系数 (Rp2),预测的平方平均误差 (RMSEp) 和平均绝对相对偏差 (MARDp).
主要成果:
- DANN实现了卓越的跨仪器传输 (Rp2=0.92,RMSEp=0.68%,MARDp=6.19%),表现优于S/B和PDS.
- 对于跨煤类型的转移,DANN显示出显著的能力 (Rp2=0.75,RMSEp=0.64%,MARDp=7.89%),而传统方法则失败了.
- 为了获得最佳的性能,DANN要求采用最小的校准样本 (18个用于交叉仪器,14个用于交叉煤类型).
结论:
- 在仪器和煤炭类型之间进行光谱校准转移时,DANN表现出卓越的适应性和准确性.
- 这种机器学习方法为光谱煤分析的实用工业应用提供了创新解决方案.
- 这些发现突显了DANN克服传统方法的局限性,提高效率和可靠性.
相关概念视频
Instrument Calibration
265
Instrument calibration is essential for ensuring that instruments produce accurate and consistent results. It is vital in manufacturing, healthcare, testing laboratories, and scientific research. Calibration processes are specific to each instrument and help enhance data accuracy. Each instrument has a unique calibration process tailored to its design and function to improve data accuracy.
Analytical Balance Calibration
An analytical balance measures mass and requires regular calibration to...
Analytical Balance Calibration
An analytical balance measures mass and requires regular calibration to...
265
Calibration Curves: Linear Least Squares
2.1K
A calibration curve is a plot of the instrument's response against a series of known concentrations of a substance. This curve is used to set the instrument response levels, using the substance and its concentrations as standards. Alternatively, or additionally, an equation is fitted to the calibration curve plot and subsequently used to calculate the unknown concentrations of other samples reliably.
For data that follow a straight line, the standard method for fitting is the linear...
For data that follow a straight line, the standard method for fitting is the linear...
2.1K
Calibration Curves: Correlation Coefficient
2.3K
In a linear calibration curve, there is a value called the calibration coefficient, denoted by 'r,' which measures the strength and the direction of association between two variables. The correlation coefficient value ranges from −1 to +1. A value of +1 indicates a perfect positive linear correlation, −1 denotes a perfect negative correlation, and 0 implies no correlation between the two variables. A positive correlation value establishes that as one variable increases, the...
2.3K
Atomic Absorption Spectroscopy: Lab
556
For AAS measurements, samples must be introduced as clear solutions, often requiring extensive preliminary treatment to dissolve materials like soils, animal tissues, and minerals. Common methods for sample preparation include treatment with hot mineral acids, wet ashing, combustion in closed containers, high-temperature ashing, or fusion with reagents.
Solutions containing organic solvents, such as low-molecular-mass alcohols, esters, or ketones, enhance absorbances by increasing...
Solutions containing organic solvents, such as low-molecular-mass alcohols, esters, or ketones, enhance absorbances by increasing...
556
Quantitative Analysis
600
Quantitative analysis is a technique for measuring the amount of specific constituents in a sample. When the sample's composition is unknown, qualitative analysis is performed first to identify its components, which ensures that the correct substances are measured during the quantitative phase.
In quantitative analysis, two key measurements are made: the sample quantity and a property proportional to the amount of the analyte (the substance being analyzed). This forms the basis of the...
In quantitative analysis, two key measurements are made: the sample quantity and a property proportional to the amount of the analyte (the substance being analyzed). This forms the basis of the...
600
Atomic Emission Spectroscopy: Lab
242
AES is a powerful analytical technique, especially effective when used with plasma sources, producing abundant spectra in characteristic emission lines. The Inductively Coupled Plasma (ICP), in particular, yields superior quantitative analytical data due to its high stability, low noise, low background, and minimal interferences under optimal experimental conditions. However, newer air-operated microwave sources are emerging as promising alternatives that could be more cost-effective than...
242


