Proposing an intelligent approach for measuring the thickness of metal sheets independent of alloy type

Application of frequency characteristic extraction in increasing the accuracy of X-ray based thickness gauges used for aluminum alloys employing GMDH neural network

Radiation-based gauges have been widely utilized in the industry as a dependable, non-destructive method of measuring metal layer thickness. It is only possible to trust the conventional radiation thickness meter when the material's composition is known in advance. Thickness measurement errors are to be anticipated in contexts like rolled metal factories, where the real component of the material could diverge greatly from the stated composition. An X-ray-based device was suggested in this study to measure aluminum sheet thickness and identify the type of its alloys. Transmission and backscattered X-ray energy were recorded using two sodium iodide detectors while a 150 kV X-ray tube in the described detection system was operated. Aluminum layers of varying thicknesses (2-45 mm) and alloys (1050, 3105, 5052, and 6061) were simulated to be placed between the X-ray source and the transmission detector. The development of radiation-based systems used the MCNP code as a very powerful framework to imitate the detecting architecture and the spectra acquired by the detectors. The recorded signals were transferred to the frequency domain using the Fourier transform, and the frequency characteristics were extracted from them. Two GMDH neural networks were trained using these characteristics: one to identify the alloy type and another to determine the aluminum layer's thickness. The classifier network had a 92.2% success rate in identifying the alloy type, while the predictive network had a 1.9% error rate in determining the thickness of the aluminum layer. By extracting important characteristics and using powerful neural networks, this study was able to improve the precision with which aluminum layer thickness was measured and correctly identify the alloy type. The suggested method is used to determine the thickness of aluminum and its alloy sheets and may also be applied to other metals.

An artificial neural network based approach for estimating the density of liquid applied in gamma transmission and gamma scattering techniques

The study presents a new ANN-based approach to determine the density of a liquid applied in the gamma transmission and gamma scattering techniques. This approach used the Monte Carlo simulation combined with an artificial intelligence technique and experimental data to estimate the density of liquids. Two advantages of the proposed approach: (1) it is able to determine the density of a liquid by only measuring the gamma spectrum (transmission spectrum or scattering spectrum) without knowing the composition of the liquid, and (2) it is able to determine the density of a liquid when it is contained in a tube of various diameters. The artificial neural network model was trained by data obtained from simulation and then was used to predict the density of seven liquids with density in the range of 0.6 g cm^-3 to 2.0 g cm^-3 for the purpose of validating the proposed approach. For the gamma transmission technique, there are 25/28 samples with relative deviations between reference and predicted densities of less than 5%. The remaining three samples have deviations in the range from 5.2% to 6.3%. For the gamma scattering technique, there are 17/21 samples with a relative deviation of less than 5%. The remaining four samples have a deviation in the range from 5.2% to 6.9%. The results proved that the artificial intelligence technique combined with Monte Carlo based on gamma transmission and gamma scattering techniques is an effective approach for estimating the density of a liquid.