ARTIFICIAL NEURAL PSEUDO-NETWORK FOR PRODUCTION CONTROL PURPOSES

Background: Experience from the implementation of the industry 4.0 concept has proved that the key success factor is the use of techniques and methods of artificial intelligence. One of these techniques is artificial neural networks. The development of artificial neural networks has been taking placefor a long time and has led to a number of important applications of this technique in industrial practice. Along with the development of practical applications, a wide theoretical base has also been created regarding the concepts, tools and principles of using this technique.

Methods: This paper contains an attempt to use the theoretical basis of artificial neural networks to build a specialized tool. This tool is called a pseudo-network. It is based not on the whole of the theory of artificial neural networks but only on the targeted elements selected for it. The selection criterion is the use of an artificial neural pseudo-network to control production.

Results: The paper presents the assumptions of an artificial neural pseudo - network, the architecture of the developed solution and initial experience of using it.

Conclusions: These initial results proved the assumptions made by an author. The architecture of the pseudo-network has been developed. Work to build a system demonstrator representing the artificial neural pseudo - network have been initiated and is still in progress.

A part of this study was presented as oral presentation at the „8th International Logistics Scientific Conference  WSL FORUM 2019” in  Poznan (Poland), 18th-19th of November 2019.