The selection of key temperature measurement points for thermal error modeling of heavy-duty computer numerical control machine tools with density peaks clustering

Abstract

Having great impacts on machining precision, thermal error is one of the main error sources for heavy-duty computer numerical control machine tools. Thermal error compensation using prediction models with temperature field is an effective way to improve machining precision of computer numerical control machine tools. The accuracy and robustness of thermal error prediction models depend considerably on the selection of temperature measurement points. Too many temperature measurement points will increase the complexity of thermal error prediction models and incur overfitting problems. To improve the complexity and performances of prediction models, a selection method of key temperature measurement points based on density peaks clustering is presented in this article. This method is able to cluster massive temperature measurement points quickly and select the key temperature measurement point which characterizes the common feature of each cluster automatically. It is verified on the ZK5540A heavy-duty computer numerical control gantry drilling machine tool. Six key temperature measurement points are selected from the total 222 temperature measurement points with this method. Then, the back propagation neural network optimized by genetic algorithm thermal error model with the six key temperature measurement points is built and the accuracy and robustness of the model are analyzed. The results show that the model has high prediction accuracy and strong robustness.

Application of Machine Learning in the Precise and Cost-Effective Self-Compensation of the Thermal Errors of CNC Machine Tools – A Review

“…Therefore an industrial computer is used to implement them [23]. The ANNs most often used in thermal error modelling are: a multilayer perceptron (MLP) [4,6,7,9,14,15,17,21,24,26,29,33,35,[40][41][42][43][44] and a radial basis function (RBF) network [8,9,16,19,20,27,28,34,36,38]. Linear models have usually shown an accuracy of a few/10-20 micrometres, while artificial neural networks have usually shown an accuracy of few micrometres.…”

“…Since the overall precision of thermal error compensation depends on the modelling accuracy and the thermal error measurement precision, it is important that the measurement of the thermal error be very precise. The thermal error has been measured by means of: an inductive sensor [13,16,17,21,23,25,26,30,[33][34][35][36][37][38]42], a capacitive sensor [14], a laser interferometer [9,19,31] and a laser reflective sensor [7,24,43,44]. The thermal error measurement procedures used in 5-axis machine tools have been: the R-test [46] and ETVE [25].…”

“…A group of machine tool structure points in which temperature measurements are similar is called a cluster. The following clustering methods are used: fuzzy c-means clustering [2,6,7,16,22,27,40], hierarchical clustering [26,33,35,36], k-means clustering [45], Kohonen network clustering [39] and density peaks clustering [44]. After clustering is performed representatives of each cluster are selected by assessing the effect of temperatures on the thermal error [2,6,26,27,33,35,36,39,40].…”

Spindle Thermal Error Prediction Based on LSTM Deep Learning for a CNC Machine Tool

“…Multiple linear regression (MLR) is a common algorithm for creating mathematical prediction models of thermal displacement [17][18][19][20][21][22][23]. Some neural network modeling techniques have also been proposed to obtain more robust and accurate predictions [24][25][26][27][28][29][30][31][32]. In addition, how to select and decide the representative temperature-sensitive points among numerous Initial Temperature Points (ITPs) is crucial.…”

“…Yin et al also adopted a genetic algorithm to optimize a BackPropagation neural network (BPNN) to reduce the instability of the thermal displacement estimation models. Zhou et al [30] established a total of 222 ITPs from different structural positions of a machine tool; among the ITPs, KTPs were selected using density-based clustering. Subsequently, a steepest descent algorithm was replaced by the genetic algorithm in a BPNN to establish a thermal displacement model.…”