Now showing 1 - 3 of 3
No Thumbnail Available
Publication

Mathematical Model of the Distribution of Laser Pulse Energy

2016, Pavels Narica, Teilāns, Artis, Lazov, Lyubomir, Pavels Cacivkins, Teirumnieks, Edmunds

Method allows for modelling of the complex process of laser pulse energy distribution over flat work surface. The process of calculating the correct result does not use common lasing formulas but instead employs the mathematical model of matrix multiplication of three input matrices representing a pulse model, a line model, and a plane model. The pulse model represents the distribution of planar energy densities within the laser pulse. The line model represents the distribution of pulses within the line. The plane model represents the distribution of lines within the plane. Because mathematical model is implemented within a spreadsheet processor, its size can be adjusted as needed and it can be instantiated multiple times for simultaneous modelling of different input parameters.

No Thumbnail Available
Publication

Mathematical Model of Forecasting Laser Marking Experiment Results

2016, Pavels Narica, Teilāns, Artis, Lazov, Lyubomir, Pavels Cacivkins, Teirumnieks, Edmunds

Method allows for modelling of the anticipatory results of colour laser marking experiments. The process of calculating expected results takes into consideration the construction specifics of laser system being used and displays the results in compact form of a set of parameter matrices that have their values conditionally formatted as colour maps for easy identification of complex patterns. The complete set of all the related parameter matrices, both technical and derived, as well as the specific relations between them form the mathematical model of forecasting laser marking experiment results. Because the mathematical model is implemented within spreadsheet processor, it can be instantiated multiple times for any number of experiments.

No Thumbnail Available
Publication

Artificial Neural Networks: What Can They Learn about Color Laser Marking?

2018, Pavels Cacivkins, Lazov, Lyubomir, Teirumnieks, Edmunds, Martins Sperga, Ingus Dilevka, Artis Vitins

Color laser marking paves the way for many useful applications in modern industry - traceability, anticounterfeiting, etc. Laser marking of materials is an inherently difficult problem with no clear functional relationship between many technological parameters on the input and the results of processing on the output. Some processes cannot be well defined without the use of examples. In this paper we discuss the novel method of training artificial neural networks using real experimental color laser marking data for prediction of results. We conclude the paper by discussing the other potential applications of proposed solution in the field of laser materials processing.