The required machining accuracy can be realized by compensating the thermal error of the machine tool. The paper presents a method of constructing a system of compensation for the thermal error of the machine tool. The method is based on the part measurement system installed on the machine. A review of studies in the field of precision machining was conducted. The review showed that the methods of correction of machining errors caused by dynamic and static factors using OMM-technology (On Machine Measurement) is presented in the literature. At the same time, the methods of compensation of the thermal error of machine tool built on the use of OMM-technology are poorly represented. Therefore, the practical implementation of control algorithms of the working bodies of the machine allowing one to compensate for its thermal error using OMM-technology is in demand. The methodology contains seven main stages, methodologically covering four areas of research. In addition to the experimental, mathematical and measurement areas of research, they also distinguish the area of software development (preparation of NC programs for CNC machines). It is proved that the presented methodology allows one to develop own automated system of compensation of a thermal error for any machine tool. It is shown that the most important directions of the framework for the improvement of the effectiveness of such system are to ensure the completeness of the experimental base and the accuracy of the adjustment of the thermal error compensation algorithms of the machine tool.
The article evaluates the effectiveness of an artificial neural network use for mathematical processing of the machine tool experimental thermal characteristics. To improve the quality of approximation and the accuracy of forecasting, two types of neural networks were used, namely a network of radially basis functions and a generalized regression neural network. The results of a full-scale thermal experiment of the idling 400V machine tool are presented. Computational experiments of the thermal testing results of a metal cutting machine were carried out to build and test the models under study. The results showed that neural networks perform better than the classical power polynomial model in terms of accuracy and approximation quality. Thus, neural networks can be used to approximate the experimental thermal characteristics of the machine tool in real time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.