ABOUT ONE ALGORITHM OF ADAPTIVE CONTROL OF THE TURNING PROCESS USING ARTIFICIAL INTELLIGENCE METHODS

Abstract

Increasing the efficiency of turning processes on CNC machines requires the development of special mathematical and information support for the implementation of adaptive control. It is proposed to use neural network approximators as models of the cutting process, constructed on the basis of experimental data obtained on a specific CNC machine during the processing of a specific material using a fixed tool. The purpose of the study: to study the issues of applying artificial intelligence methods for adaptive control of the turning process based on the obtained data on tool vibration. Materials and methods. An algorithm for solving the problem of optimal adaptive control is proposed, which ensures maximum productivity of a CNC machine in automatic mode. To organize feedback in adaptive control of the cutting process, sensor data on vibration acceleration of the cutting tool are continuously taken and processed. An estimate of the specific energy of the signal is calculated for a given time interval and a connection is established between it and the roughness of the workpiece surface. For this, a trained neural network is used, predicting the roughness value for given cutting modes based on the signal energy value about vibration. Results. The problem statement of adaptive control of the turning cutting process taking into account tool wear is proposed. An algorithm for intelligent processing of data on tool vibration acceleration during cutting is developed and a neural network is built that establishes a connection between the vibration level and surface roughness. An effective algorithm for solving the problem of optimal adaptive control is proposed. It allows real-time selection of cutting modes that ensure maximum cutting process productivity while meeting surface roughness constraints. Conclusion. The studied algorithms and models were tested on real data, which confirms the possibility of their use in the development of an intelligent information system for adaptive control of the turning process.