.png){kind=icon}
.png){kind=icon}
Return
Developing a dynamic quality prediction model for limited samples target grade based on transfer learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.measurement.2024.114380.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In response to the dynamic demands of the market, this study addresses the challenge of frequent operational adjustments in a production line to accommodate diverse product grades. The resulting scarcity of data in the new operating conditions (target grade) impedes the development of reliable soft -sensor prediction models. A two-step learning method, termed S2-LGMNSSM-TS-T, is proposed. This method employs a semi -supervised latent Gaussian mixture nonlinear state space model (S2-LGMNSSM-TS) trained on both target and source data, providing a dynamic, one -step -ahead predictive soft sensor. To overcome data scarcity in the target grade, insights from the source are utilized. With a Gaussian mixture prior distribution, S2-LGMNSSM-TS identifies dynamic behaviors in both target and source grades. The enhanced S2-LGMNSSM-TS-T configuration focuses on target -grade predictions, leveraging source knowledge and mitigating data scarcity issues. A numerical example and an industrial case study demonstrate the model ' s effectiveness in improving target -grade predictions through source knowledge utilization.
Keywords:
Dynamic quality prediction model
Limited samples
Probabilistic model
Semi -supervised learning
Transfer learning
Journal
IF:
5.6
Papers:
2.0W
Citations:
5.4W