Electric spark machining stability and energy consumption state optimization decision-making system and method based on deep learning

Abstract

The invention discloses an electric spark machining stability and energy consumption state optimization decision-making platform based on deep learning. A characteristic screening method is used for excavating and analyzing electric spark machining data, and machining stability and energy consumption state optimization indexes are obtained; a K-medoids algorithm is used for clustering the optimization indexes, the machining stability and energy consumption state distribution condition is obtained, and a stable machining state database and an energy-saving discharge state database are built; historical electric spark machining data are used for training LSTM recurrent neural network deep learning to obtain the real-time electric spark machining state predication value, in combination with statistics characteristic value of the optimization indexes, when it is judged that the current state is the non-normal machining state, the machining stability and energy consumption state is subjected to multi-target optimization, the stability-energy saving machining state comprehensive optimal target value is obtained, and the current machining parameter value is regulated. On the basis of thedeep learning, the stability-energy saving comprehensive optimal electric spark machining parameter optimization decision-making method is given, and electric spark machining runs in the stable and energy-saving state.

Description

technical field [0001] The present invention relates to the field of electrical machining in the field of special machining, and in particular to a decision-making system for optimizing the stability and energy consumption state of electrical discharge machining based on deep learning. Background technique [0002] EDM means that in a certain medium, through the pulse discharge between the tool electrode and the workpiece electrode, an instantaneous high temperature is formed to partially melt and vaporize the workpiece material, thereby realizing material erosion. This processing method does not generate cutting force, is not limited by the tool material, and can process workpieces with ultra-high hardness, brittleness and complex shapes, so it is widely used in molds, aviation industry, medical equipment and other fields. EDM is usually achieved by EDM machine tools. [0003] The main process parameters that characterize the performance of EDM include electrical parameter...

AI Technical Summary

Problems solved by technology

With the surge of global carbon emissions and the depletion of energy sources, the development of "green economy" has become a global hotspot.

Images