Multi-response parameter optimization method based on principal component analysis and neural network

Abstract

The invention discloses a multi-response parameter optimization method based on principal component analysis and a neural network. The method comprises the following steps: 1) eliminating the correlation of a plurality of responses by principal component analysis; 2) taking the horizontal combination value of influence factor variable temperature and time as an input variable of the neural network, taking a corresponding MPI (Multi-response Performance Index) value as the expected output variable of the neural network, and establishing a RBF (Radial Basis Function) neural network model; and 3) utilizing the RBF neural network model obtained by training to search an optimal technological parameter. A RBF neural network prediction model of a mapping relationship between a production process influence factor and the multiple responses is established, the principal component analysis is applied to convert a multi-response index into an irrelevant index, the multi-response index is converted to a single-response index of comprehensive assessment through weighting, the response with high prediction ability is optimally improved, and the optimization of the integral effect of the plurality of responses is realized.

Description

technical field [0001] The invention relates to process control of product production, in particular to a multi-response parameter optimization method based on principal component analysis and neural network. Background technique [0002] With the complexity of the production process and the improvement of product quality requirements, the product optimization design process often needs to consider multiple quality characteristics. The multi-quality characteristic parameter optimization design method aims to greatly improve product quality through the optimization of process parameters. In actual production, multi-quality characteristic optimization design plays an increasingly important role in the process of continuous quality improvement. Quality loss function method and satisfaction function method are widely used in multi-response optimization design, but they ignore the correlation between each response. In the optimization design of multi-quality characteristics, if ...

AI Technical Summary

Problems solved by technology

However, the mapping function model established by the response surface method is a first-order or second-order linear function model of the factor variable, or a model that can be transformed into a first-order or second-order linear function, which is not suitable for establishing a functional relationship model of a complex nonlinear process.

Images