Intelligent Precise Goniometric System of Analysis of Spectral Distribution Intensities for Definition of Chemical Composition of Metal-Containing Substances

An artificial neural network (ANN) is proposed, which allows to make express-analysis of the chemical composition of production objects metalcontaining materials in automatic mode with high accuracy and real-time performance. The proposed ANN for automatic recognition of chemicals (ANN ARoC) is an alternative to traditional high-cost and time-consuming physical and chemical methods and labelling analysis, which are significantly complicate and slow down technological processes, as well as environmentally hazardous to human health and environment. The mean square error of proposed ANN ARoC does not exceed 5%, the time of determining the chemical composition of production objects metal-containing materials is not more than 2.5 s. ANN ARoC is built on the principle of a multilayer perceptron

show abstract

Software of high-precision goniometric complex with artificial intelligence

Cherepanska¹,

Melnychuk²,

Sazonov³

2021

Visnyk TNTU

View full text Add to dashboard Cite

Software of high-precision goniometric complex with artificial intelligence developed by the authors, particularly with artificial neural networks, with advanced functionality, designed for non-contact high-precision measurements at the previous settings of navigation sensing elements, flat angles, pyramidal prisms, other production objects, refraction index of optical glass, etc. is presented in this paper. The proposed software product has advanced capabilities, particularly, allows high-precision analysis of the intensities of the spectral distribution of chemical elements in metal-containing materials. The structure of the software reproduces the paradigm of modular construction, which determines the flexibility, extensibility and variability of software components. As a result, neural network processing of measuring information, automatic filtering by the method of moving average output signal noisy by errors of different nature is implemented.

show abstract

Intelligent Precise Goniometric System of Analysis of Spectral Distribution Intensities for Definition of Chemical Composition of Metal-Containing Substances

Cited by 3 publications

References 8 publications

Ring Laser for Angle Measurement Devices

Ring Laser for Angle Measurement Devices

Artificial Neural Network as a Part of Intelligent Precise Goniometric System for Analysis of Spectral Distribution Intensity and Definition of Chemical Composition of Metal-Containing Substances

Software of high-precision goniometric complex with artificial intelligence

Contact Info

Product

Resources

About