PSO neural network-based engineering ceramic electrospark machining effect prediction method

Abstract

The invention provides a PSO neural network-based engineering ceramic electrospark machining effect prediction method. The method comprises the steps of building a three-layer BP neural network prediction model of an insulated engineering ceramic line electrode discharge grinding process effect by utilizing a BP neural network; in combination with an adaptive variation particle swarm algorithm, optimizing connection weight and threshold of the BP neural network; building a particle swarm neural network-based engineering ceramic line electrode discharge grinding process effect prediction modelby utilizing Matlab programming; and verifying the reliability of the engineering ceramic line electrode discharge grinding process effect prediction model built by optimizing the BP neural network bythe adaptive position variation particle swarm algorithm. The method remarkably reduces an iterative frequency, has relatively high prediction precision, reliability and validity, has a certain practical value, and can be used for optimizing engineering ceramic line electrode discharge grinding process electric parameters to further improve surface quality of workpieces.

Description

technical field [0001] The invention relates to the technical field of electrical discharge grinding processing of engineering ceramics, in particular to a method for predicting the effect of electrical discharge machining of engineering ceramics based on a PSO neural network. Background technique [0002] Due to their excellent properties such as high strength, high hardness, wear resistance, corrosion resistance, high temperature resistance, and light weight, engineering ceramic materials are increasingly valued by material scientists and are increasingly widely used in modern industries. , defense and high-tech fields. Although engineering ceramics have so many superior properties and are more and more widely used, the sintered ceramic material products are different from metal powder products, and its dimensional shrinkage rate is above 10%, while the latter is below 0.2%, so ceramics The dimensional accuracy of the products is low, and most of them cannot be directly u...

AI Technical Summary

Problems solved by technology

Therefore, when it is used in the modeling of engineering ceramic wire discharge grinding, it can achieve better prediction results. However, when the BP neural network is trained, it searches according to the direction of the maximum gradient of the error decline, and it is easy to fall into the local The minimum value, so global search cannot be performed, and its search and training speed is slow, which will affect the accuracy and reliability of the prediction model

Images