Material quality assessment method based on machine learning

Abstract

The present invention discloses a material quality assessment method based on machine learning. A material quality assessment model is created, the artificial neural network algorithm of back propagation is selected, and a back propagation network model is established. The collected historical sample information is divided into two portions consisting of training data and verification data. The training data is used to perform training of the model to obtain model weight parameters and regulation factors. The verification data is used to perform test verification of a model training result until a verification result accords with collected information so as to obtain the non-linear relation of material quality and influence factor quality testing. The verified model and the model parameters are employed to predict the quality level of the materials. The material quality assessment method based on machine learning can more objectively and accurately assess the quality level of the materials.

Description

technical field [0001] The invention belongs to an electric power system, and relates to a material quality assessment method, in particular to a machine learning-based material quality assessment method. Background technique [0002] There are usually more than 4,000 items of materials purchased by the power material department, and there are as many as hundreds of thousands of suppliers. Different suppliers and different materials will have various quality problems and complaints during the use process. In daily work, the quality level of materials is often simply determined through linear analysis based on relevant information such as the number of problems that have occurred in materials. The associated data used is relatively single and has a certain one-sidedness. There are many factors related to the actual quality of materials, and the quality level of materials can be deduced through machine learning algorithms by collecting comprehensive related factors. Content...

AI Technical Summary

Problems solved by technology

In daily work, the quality level of materials is often simply determined through linear analysis based on relevant information such as the number of problems that have occurred in materials. The associated data used is relatively single and has a certain one-sidedness.

Images