Artificial Neural Networks: What Can They Learn about Color Laser Marking?
- Resource Type
- Conference
- Authors
- Cacivkins, Pavels; Lazov, Lyubomir; Teirumnieks, Edmunds; Sperga, Martins; Dilevka, Ingus; Vitins, Artis
- Source
- 2018 IX National Conference with International Participation (ELECTRONICA) Participation (ELECTRONICA), 2018 IX National Conference with International. :1-4 May, 2018
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Power, Energy and Industry Applications
Signal Processing and Analysis
Image color analysis
Training
Power lasers
Laser theory
Regression analysis
artificial neural networks
color laser marking
laser materials processing
machine learning
- Language
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.