Use of LIBS technique for identification of type of pollutant and ESDD level on epoxy-alumina nanocomposites using ANN

Abstract

Epoxy-alumina nanocomposites have been coated with different types of pollutants at various concentrations in order to analyze their pollution performance using laser induced breakdown spectroscopy (LIBS) study. Elemental analysis of spectral peaks has been successful in determining the elemental composition of the pollutant present on the surface of the specimens. The conductivity and equivalent salt deposition density (ESDD) values have been determined for all the pollutants at different concentrations. A direct correlation between ESDD and the normalized intensity ratio of LIBS spectral data is noticed. Regression coefficient (R 2 ) has been used as a performance parameter in correlating the ESDD and normalized intensity ratio. Artificial neural network (ANN) technique has been adopted to LIBS spectral data for the classification of the pure epoxy and 3 wt% epoxy-alumina nanocomposite specimen based on conductivity and type of pollutant. ANN developed with conjugate gradient backpropagation with Polak-Ribiere updates training algorithm has reflected higher classification accuracy and required lesser epochs to converge, compared to other training algorithms in classifying the contaminated specimens.

Classification of Polluted Silicone Rubber Insulators by Using LIBS Assisted Machine Learning Techniques

“…Artificial pollutant slurries prepared with seven distinct types of pollutant mixtures (shown in Table 1) have been applied uniformly on the surface of the SR insulator. The kaolin clay is the composition of 30-40% of Al 2 O 3 , 0-3.2% of Fe 2 O 3 , 40-50% of SiO 2 and 7-14% of H 2 O [32], which is mixed along with pollutants and deionized water in order to form an artificial pollutant slurry. The weight of NaCl and CuSO 4 are selected such that the mass fraction of Na and Cu will be 14.28 % and 3.65 % respectively [32].…”

“…The kaolin clay is the composition of 30-40% of Al 2 O 3 , 0-3.2% of Fe 2 O 3 , 40-50% of SiO 2 and 7-14% of H 2 O [32], which is mixed along with pollutants and deionized water in order to form an artificial pollutant slurry. The weight of NaCl and CuSO 4 are selected such that the mass fraction of Na and Cu will be 14.28 % and 3.65 % respectively [32]. These mass fractions of Na and Cu represent ''very high'' level of pollutants, as per IEC/TR2 61245:1993 [13].…”

“…The optical resolution of the spectrometer was 0.3 nm full width half maximum. The further details of the instrument specifications employed in the experimental setup are provided in our previous study [32].…”

“…It is well-established that the normalized intensity ratio can substantially identify the variations in the quantity of an element present in the material [18], [32]. Hence, the normalized intensity ratios of the spectral peaks shown in the Fig 3 and 4 are calculated by taking neutral sodium (Na I) peak (588.9 nm) as reference in all the cases.…”

Investigation on Electrical, Thermal, and Mechanical Properties of Silicone Rubber ATH Nanocomposites

“…It was recently reported that using statistical tools in conjunction with LIBS data can be used to identify and classify the aging behavior of insulating materials [33]. The typical LIBS spectra of silicone rubber and nano-ATH composites with different filler loadings are shown in Fig.…”