Modeling method of thermal error of CNC machine tool spindle based on fs+wp__svm

Abstract

The invention discloses a FS+WP__SVM-based thermal error modeling method for the spindle of a numerical control machine tool. It includes data preprocessing, artificial fish swarm algorithm initialization, artificial fish swarm algorithm early optimization, artificial fish swarm algorithm optimization threshold judgment, wolf swarm algorithm initialization, wolf swarm algorithm late optimization, wolf swarm algorithm optimization threshold judgment and construction of CNC machine tools Spindle thermal error model. The present invention respectively uses the artificial fish swarm algorithm and the wolf swarm algorithm to optimize the core parameters of the support vector machine in the early stage and the later stage, and has the characteristics of strong global optimization ability of the fish swarm algorithm and fast local convergence speed of the wolf swarm algorithm, so that it can guarantee prediction Under the premise of precision, the execution efficiency is greatly improved, and it has high practical value in the actual engineering application of thermal error modeling of CNC machine tool spindle.

Description

technical field [0001] The invention belongs to the field of numerical control machine tools, and in particular relates to a method of optimizing parameters of a support vector machine by combining fish swarm and wolf pack algorithm to determine a thermal error model generated during machining of a main shaft of a numerical control machine tool. Background technique [0002] CNC machine tools have the characteristics of large strokes, heavy loads, and long processing cycles during the processing process, which causes serious temperature rises in the various parts of the machine tool during the processing process. Due to the uneven distribution of the heat source of the machine tool, the temperature rise of the various parts of the machine tool will be large. Under the action of these uneven temperatures, the machine tool will have serious thermal deformation. The deformation of the machine tool will affect the machining accuracy of the workpiece. Studies have shown that the...

AI Technical Summary

Problems solved by technology

Among them, the wandering and summoning behaviors belong to the process of local optimization, and the siege behavior belongs to the process of global optimization. From the programming of the algorithm, it can be seen that the algorithm focuses on local optimization during the execution process, so the later stages of the algorithm In the process of local optimization, the convergence speed is very fast, but in the early stage of global optimization, the convergence is unstable and the convergence speed is slow, and the results are very random. The existence of this randomness is very important for heavy machines. High-precision machinery is not allowed, so the wolf pack algorithm cannot be directly applied to the thermal error prediction of heavy machinery

Images