Journal
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Volume 17, Issue 9, Pages 6457-6465Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.3001054
Keywords
Data models; Quality assessment; Product design; Training; Microsoft Windows; Predictive models; Broadcasting; Deep learning; industrial big data; industrial intelligence; Industrial Internet of Things (IOT); product quality prediction; soft sensor
Categories
Funding
- National Key Research and Development Program of China [2018YFB1004001]
- National Science Foundation of China Project [61572057, 61836001]
Ask authors/readers for more resources
An efficient and effective soft sensor based on the semisupervised parallel deepFM model was proposed for product quality prediction in complex industrial Internet of Things systems. By using label broadcasting and data binning methods, quality information can be extracted from different model components to obtain high- and low-dimensional features.
In the modern industry, the information has been sufficiently shared among the production equipment, intelligent subsystems, and mobile devices via advanced network technology. For this purpose, many challenges on plant-wide performance evaluation such as product quality prediction have been received considerable attention in complex industrial Internet of Things systems. In this article, an efficient and effective soft sensor based on the semisupervised parallel deepFM model is proposed for the product quality prediction. First, a label broadcasting method is presented to augment labeled samples from unlabeled samples. Then, a data binning method is introduced to discretize process variables for an unbiased estimation. Based on the modified deepFM model, quality information can be separately extracted from different components of the model while high- and low-dimensional features can be obtained. Manifold regularization is embedded into the back propagation algorithm, in which unlabeled samples issue can be further resolved. Experiments on a real-world dataset demonstrate the effectiveness and performance of the proposed methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available