Geometric-thermal error control system for gear profile grinding machine

• GTECS is designed for gear profile grinding machine. • Transfer learning model of STO-BTCN model is established. • Long-term memorizing behavior is demonstrated. • Geometric error models of linear axes are constructed. • Thermal error models of linear axes are established based on deformation principle. Geometric and thermal errors, which are the main error factors for reducing the machining accuracy, should be controlled. But the control effect is poor, which is a stumbling block to limit the wide application of the error control. In this study, a geometric-thermal error control system (GTECS) is designed for gear profile grinding machines. For the mist layer of GTECS, the wireless sensor network is designed to realize the data collection and transfer. For the edge layer of GTECS, the edge controller is designed to conduct the sensitive error analysis. For the fog layer, the control module is designed to conduct the geometric and thermal error prediction. In this layer, the analytical model of the rolling guide/slider system is proposed to calculate geometric errors of X- and Z- axes, and the thermal boundary conditions are calculated, and the thermal error models of the spindle and C-axis are proposed based on transfer learning model (TLM) of the sooty tern optimization (STO)-bilinear temporal convolutional network (BTCN). For the cloud layer, the data computation and management are realized by Hadoop and Yet Another Resource Negotiator (YARN), respectively. The geometric and thermal error models of X- and Z-axes, thermal errors models of the spindle and C-axis, and multi-source error model are embedded into it. With the execution of GTECS, the geometric precision for the total tooth profile deviation and tooth profile deviation are increased from ISO level 8 to ISO level 5 and from ISO level 5 to ISO level 3, respectively.