Rapid detection of coal ash based on machine learning and X-ray fluorescence

Real-time testing of coal ash plays a vital role in the chemical, power generation, metallurgical, and separation sectors. The rapid online using radiation measurement as mainstream technology has problems such strict sample requirements, poor safety, low accuracy, complicated equipment replacement. In this study, an intelligent detection technique based on feed-forward neural networks improved particle swarm optimization (IPSO-FNN) is proposed to predict quality content fast, accurate, safe，and convenient manner. data set was obtained by elemental 198 samples with X-ray fluorescence (XRF). types input elements for machine learning (Si, Al, Fe, K, Ca, Mg, Ti, Zn, Na, P) were determined combining photoelectron spectroscopy (XPS) change physical phase each element during combustion. mean squared error coefficient determination chosen performance measures model. results show that IPSO algorithm useful adjusting optimal number nodes hidden layer. IPSO-FNN model strong prediction ability good accuracy prediction. effect investigated, it found potassium most significant factor affecting content. This study essential real-time online, fast ash.