Fuzzy control system of multioperational machine status

Introduction. The paper presents the key aspects of constructing a management system for the state of multi-operation computer-controlled machines based on the information-control module of e-Mind Machine and the apparatus of fuzzy sets and fuzzy logic. It is shown that the input effects of the control system are formed due to the sets of inheriting and operating components of the status parameters. The work objective is to develop a system for monitoring the condition, detecting dimensional wear, and determining the period of tool life on the basis of the fuzzy logic methods. Materials and Methods. A new algorithm for constructing an expert system based on the fuzzy logic methods is proposed. The applicability of fuzzy neuron methods for solving the problems on determining the service life of the instrument through comparing the calculated values to the data of the manufacturing firms is demonstrated. The study is based on the application of the concept of electronic services using expert systems. Research Results. The basic principles of the construction and application of the status monitoring system are substantiated. They provide the possibility, under managing, to adapt to the emerging situation and to predict state changes when processing the parts. The monitoring functions include not only the processing of data obtained from the test units of the mechatronic system and external equipment, but both the forecasting of the residual dimensional tool life and the durability for the period of normal wear and tear. The decision-making process on managing the tool status is presented in the form of an algorithm for the expert system activity based on the use of a fuzzy neuron controller. Discussion and Conclusions. The results obtained can be applied in the parts production where accuracy is one of the key parameters. Automated control systems for the machine condition allow reducing costs due to equipment downtime, and monitoring the tool status can reduce the rejection rate. The characteristic examples of decision-making in the fuzzy neuron system are given.