Long short-term memory networks-based gear hobbing quality online evaluation method

Abstract

The invention relates to the technical field of numerical control gear hobbing machine tool machining, and discloses a long short-term memory networks-based gear hobbing quality online evaluation method aiming at the defects that the gear quality is required to be inspected manually and the efficiency is low in a conventional gear hobbing process. The long short-term memory networks-based gear hobbing quality online evaluation method comprises the following steps: acquiring a gear hobbing effective vibration sequence data set and a gear hobbing precision index data set in a gear hobbing machining process; establishing a characteristic matrix set through sample segmentation and characteristic extraction, and respectively establishing a precision matrix set corresponding to the characteristic matrix set aiming at each precision index; establishing an evaluation model of each precision index in each vibration direction based on the long short-term memory networks, and obtaining the evaluation model in the optimal vibration direction corresponding to each precision index; and intercepting the effective vibration sequence to be evaluated for a gear hobbing process to be evaluated, acquiring the characteristic matrix to be evaluated through the sample segmentation and the characteristic extraction, and obtaining a gear hobbing quality online evaluation result by combining the evaluation model in the optimal vibration direction corresponding to each precision index. Compared with the prior art, the long short-term memory networks-based gear hobbing quality online evaluation methodhas the beneficial effect of high efficiency.

Description

technical field [0001] The invention relates to the technical field of numerically controlled gear hobbing machine tools, in particular to a method for online evaluation of gear hobbing quality during the gear hobbing process. Background technique [0002] Hobbing is a commonly used gear machining method. The traditional hobbing process generally includes two processes of processing and inspection. The first step is to carry out the gear hobbing operation on the CNC gear hobbing machine, and then remove the gear workpiece for accuracy inspection. The precision inspection process of gears requires manual operation, which is inefficient and seriously affects the efficiency of the entire production process. [0003] The error of gears in gear hobbing is mainly caused by cutting force, which will cause impact and thermal deformation, and then affect the tooth surface morphology of gears. The vibration signal of the hob during the gear hobbing process is a comprehensive reflec...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the shortcomings of manual inspection of gear quality and low efficiency in the traditional gear hobbing process, the present invention discloses an online evaluation method for gear hobbing quality based on long-term and short-term memory networks, and learns the vibration sequence of the hob under different hobbing qualities through the long-term and short-term memory network. Features, realize online evaluation of gear hobbing quality based on vibration sequence, and improve efficiency

Images