Intelligent cutter handle auxiliary milling cutter life prediction method based on GRU neural network

Abstract

The invention discloses an intelligent cutter handle auxiliary milling cutter life prediction method based on a GRU neural network, and the method comprises the following steps: 1), obtaining a state monitoring signal of a cutter, carrying out the data preprocessing of the state monitoring signal, and obtaining a data sample set of the cutter; 2) performing feature selection on effective data in the data sample set, and obtaining a sample data set for GRU neural network training consisting of feature values and tool wear loss; and 3) building a GRU neural network model based on the sample data set to obtain the time sequence analysis prediction data of the state monitoring signal and the wear value of the cutter. The special structure of the GRU model can fully consider the change of the working condition scene and the wear feature in the time sequence and the cumulative effect of the change, meanwhile, the fuzziness of the GRU can model the complex correlation between the working condition scene and the machining wear feature in space, meanwhile, the required data volume is smaller, and the training speed is higher.

Description

technical field [0001] The invention belongs to the technical field of tool life prediction, and in particular relates to a GRU neural network-based intelligent tool holder-assisted milling tool life prediction method. Background technique [0002] As an important tool in the industrial manufacturing process, the tool life and wear state affect the production quality of the workpiece, production efficiency and the health of the lathe. If the remaining life of the tool can be accurately predicted, the cost of industrial manufacturing will be effectively reduced. [0003] Rangwala et al. first applied artificial neural network to tool condition monitoring, which was later widely used in the field of tool condition monitoring because of its powerful learning ability. Different from the network structure used by previous scholars, Jiang Liying et al. established a one-step and multi-step tool wear state prediction model based on radial basis neural network, and the simulation e...

AI Technical Summary

Problems solved by technology

For the prediction of tool remaining life under variable working conditions, the same tool may process multiple parts during its life cycle. The tool works under a constantly changing processing condition, and its wear condition changes with the processing conditions. The relationship between working condition changes and tool wear is more complex

Many predictive methods are limited in their ability to track tool wear and predict remaining useful life

Images