本文二维码信息
二维码（扫一下试试看！）
Construction and Comparison of Cardboard Quality Prediction Models Based on Machine Learning
Received:August 11, 2022  
DOI：10.11980/j.issn.0254-508X.2023.07.009
Key Words:machine learning  data mining  paper industry  quality prediction  soft measurement
Fund Project:国家重点研发计划（2020YFE0201400）；人工智能与数字经济广东省实验室（广州）青年学者项目（PLZ2021KF0019）。
Author NameAffiliationPostcode
QIAN Jiwei State Key Lab of Pulp and Paper Engineering， South China University of Technology， Guangzhou， Guangdong Province， 510640 510640
LI Jigeng State Key Lab of Pulp and Paper Engineering， South China University of Technology， Guangzhou， Guangdong Province， 510640 510640
MAN Yi State Key Lab of Pulp and Paper Engineering， South China University of Technology， Guangzhou， Guangdong Province， 510640
Guangdong Artificial Intelligence and Digital Economy Lab （Guangzhou）， Guangzhou， Guangdong Province， 510335 		510335
HONG Mengna State Key Lab of Pulp and Paper Engineering， South China University of Technology， Guangzhou， Guangdong Province， 510640
China-Singapore International Joint Research Institute， Guangzhou， Guangdong Province， 510555 		510555
HE Zhenglei* State Key Lab of Pulp and Paper Engineering， South China University of Technology， Guangzhou， Guangdong Province， 510640 510640
Hits: 1632
Download times: 896
Abstract:The production of cardboard in volves a series of complex processes and the lack of online monitoring methods for key qualities， which makes it difficult to control the quality of cardboard. This paper attempted to establish predictive models， also known as soft measurement models， which based on machine learning methods that could monitor cardboard quality on line to facilitate effective solutions to the above problems. This study used actual data from cardboard companies to train and compared the predictive performance of random forest （RF）， gradient boosted regression （GBR）， K-nearest neighbor regression （KNN）， and partial least squares regression （PLS） on a variety of quality indicators. The results showed that the different quality indicators themselves largely effected the upper limit of prediction accuracy， while the degree of approximation to the theoretical upper limit varied significantly among algorithms. Complex， nonlinear integrated models （RF， GBR） had better performance， compared to simple models （KNN，PLS）.
View Full Text  HTML  View/Add Comment  Download reader