Short communication: Part contour error prediction based on LSTM neural network

Machine tools are subject to multiple sources of error duringmachining, resulting in deviations in the dimensions of the part and areduction in contour accuracy. This paper proposes a contour errorprediction model based on a long short-term memory (LSTM) neural network,taking hexagonal recess machining as an example and considering the power,vibration, and temperature signals that affect the contour error. Theexperimental data show that the model can accurately predict the contourerror of the machined part. A more accurate and robust contour errorprediction model can provide data support for online compensation of contourerrors.