Blade polishing-grinding machining method based on neural network

Abstract

The invention relates to a blade polishing-grinding machining method based on a neural network. A blank part of a blade is scanned and measured by a measuring device, information is transferred to computer software so as to obtain a reconstructed three-dimensional model, the reconstructed three-dimensional model is compared with feature points on a theoretical model, adjustment is conducted, coordinate systems of the reconstructed three-dimensional model and the theoretical model coincide, and thus the theoretical machining allowance of the blade is calculated. A neural network model is trained with historical data, thereby being capable of recognizing machining technological parameter configurations under different theoretical machining allowances. The theoretical machining allowance of the blade is input to the neural network model, and machining technological parameters of blade machining are calculated by the neural network model and are used for polishing-grinding machining. The machined blade is scanned and measured, information is transferred to the computer software to obtain an update model, the update model is compared with the three-dimensional model before machining, and the material removal quantity of the blade is calculated. If the size of the machined blade meets the tolerance requirement, machining is completed.

Description

technical field [0001] The invention belongs to the field of mechanical processing, and in particular relates to a neural network-based blade polishing processing method. Background technique [0002] The level of machinery manufacturing is the embodiment of a country's comprehensive national strength. Although the total output value of my country's manufacturing industry ranks first in the world, its key core technologies and cutting-edge products are still far behind developed countries. As an important part of the national defense industry, the research and development and manufacture of aero-engines is related to the national defense security and comprehensive national strength of a country. Blades are key components of aero-engines. At present, the processing method for the blade mainly adopts the conventional process route of die forging blank-rough milling-finish milling-polishing. The purpose of milling is to improve the accuracy of the blade profile, and the purp...

AI Technical Summary

Problems solved by technology

However, in this method, the quality of blade processing depends on the accuracy of the data in the feature library, and the level of craftsmen affects the accuracy of the data, so it is difficult to guarantee the processing quality

Images