A Data-Based Model of the Thermo-Elastic TCP Error Using the Encoder Difference and Neural Networks

Abstract The thermo-elastic tool center point (TCP) error has been an ongoing research focus, due to its large effect on the workpiece quality. Existing models compute TCP already perform quite well regarding accuracy and speed of computation. However, are often time consuming in their parameterization, expensive apply or error-prone used model inputs. work presented this paper addresses these issues by introducing encoder difference as input. Since easy inexpensive measure, it yields a high potential for industrial use. Therefore, paper, correlation between is investigated. physical relationship complex, necessary use artificial neural network resulting error. Due variety (ANN) types, with different capabilities, range networks tested capability To conclude method parametrize such derived from gathered results.