Process type production equipment product quality prediction method based on self-updating model

Abstract

The invention discloses a process type production equipment product quality prediction method based on a self-updating model, and the method comprises the steps: (1), calculating the original data delay of process type production equipment, advancing the production parameters of each region of an original data set, and enabling the production parameters of each region to be aligned in a time dimension in the original data set after advancing; step (2), carrying out process type production equipment feature extraction; and step (3), performing self-updating of the product quality prediction model of the process type production equipment, wherein the self-updating comprises inter-batch self-updating and intra-batch self-updating. According to the method, the problems of large time lag and great influence of different batches of materials of the flow-type production equipment can be solved to a certain extent, and the accuracy of product quality prediction of the flow-type production equipment is improved.

Description

technical field [0001] The invention belongs to the field of computer science, and in particular relates to a method for predicting product quality of flow-type production equipment based on a self-updating model. Background technique [0002] Flow-type production process means that materials pass through various containers and pipelines, and undergo various physical, chemical or biological processes to achieve the effect of separation or produce new products. Fermentation, synthesis, refining, and tobacco leaf shredding are all process-based production. Effective prediction of the quality of products produced by flow-type production equipment can detect the production process more effectively, and learn the relationship between environmental variables and the quality of the output products, thereby guiding the production process and timely adjusting control parameters according to product quality value of . [0003] The flow-type production process generally involves very...

AI Technical Summary

Problems solved by technology

[0003] The flow-type production process generally involves very complex production processes, which have the characteristics of large time lag, high coupling, and nonlinearity, and the performance and quality of the output are greatly affected by different batches of materials, which affects the quality of key products. Forecasting brings great difficulty

In recent years, with the development of machine learning, prediction models such as Logistic regression model, decision tree model, ELM (Extreme Learning Machine) model have been widely used in quality prediction in industrial and manufacturing scenarios, but none of them take into account the process of production The large time lag of equipment and the characteristics of being greatly affected by material batches lead to unsatisfactory prediction results

Images