Development and industrial application of LIBS-XRF coal quality analyzer by combining PCA and PLS regression methods

Abstract

Rapid and stable analysis of coal quality for fine management of coal is essential for the clean and efficient utilization of coal in thermal power plants. In this work, a...

NIRS-XRF fusion spectroscopy for coal calorific value prediction using data deficient learning

“…And PLS achieves state-of-the-art (SOTA) performance among traditional machine learning methods on coal calorific value detection. 32–34 Especially, PLS could be applied to cases with a few training samples. In order to inherit the characteristics of PLS, we reuse the parameters of PLS to initialize the neural network.…”

“…In the past, conventional machine learning methods such as partial least squares (PLS) regression 15,21,32–36 and random forest (RF) 37–40 are mostly used to establish the relationship between spectral signals and ground-truth calorific labels in this field. Due to the existence of complex non-linear system biases and other non-linear issues in real-world applications, such as the complex environment issue, coal particle size and so on, these traditional machine learning methods could not accurately predict the calorific value of coal.…”

Atomic spectrometry update – a review of advances in environmental analysis

“…The authors claimed to be the first to combine Rayleigh/reflected light, LIBS and Raman spectra to acquire simultaneously geometrical topography and information on elemental composition and molecular structure. A LIBS-XRF analyser that combined PCA and PLS regression methods was developed 211 for rapid assessment of coal quality. The experimental results for calorific value, ash content, volatile matter and S content demonstrated good accuracy and stability, with the measurement repeatabilities meeting national standards.…”

Developing a compact coal quality rapid detection integrated machine based on laser‐induced breakdown spectroscopy

“…Through model optimization, they have achieved high-precision measurements of industrial analysis indexes and calorific values of coal quality. [3][4][5][6] However, they have chosen coal pellets as their sample preparation method, which adds complexity to the process and limits the advantages of quick LIBS measurements. In addition, few teams have investigated the application of this technique to carbon accounting in emission control enterprises.…”