Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/23761
Title: | DLUP: A Deep Learning Utility Prediction Scheme for Solid-State Fermentation Services in IIoT |
Authors: | Wang, M Pang, S Ding, T Qiao, S Zhai, X Wang, S Xiong, N Huang, Z |
Keywords: | solid-state fermentation;utility prediction;petri net;least squares generative adversarial network;fully connected neural network |
Issue Date: | 20-Aug-2021 |
Publisher: | IEEE |
Citation: | Wang, M., Pang, S., Ding, T., Qiao, S., Zhai, X., Wang, S., Xiong, N. and Huang, Z. (2021) 'DLUP: A Deep Learning Utility Prediction Scheme for Solid-State Fermentation Services in IIoT,' IEEE Transactions on Industrial Informatics, 0 (in press), pp. 1 - 10 (10). doi: 10.1109/TII.2021.3106590. |
Abstract: | © Copyright 2021 The Author(s). At present, Solid-State Fermentation (SSF) is mainly controlled by artificial experience, and the product quality and yield are not stable. Therefore, predicting the quality and yield of SSF is of great significance for improving the utility of SSF. In this works, we propose a Deep Learning Utility Prediction (DLUP) scheme for the SSF in the Industrial Internet of Things (IIoT), including parameter collection and utility prediction of the SSF process. Furthermore, we propose a novel Edge-rewritable Petri net to model the parameter collection and utility prediction of the SSF process and further verify their soundness. More impor- tantly, DLUP combines the generating ability of Least Squares Generative Adversarial Networks (LSGAN) with the predicting ability of Fully Connected Neural Network (FCNN) to realize the utility prediction (usually use the alcohol concentration) of SSF. Experiments show that the proposed method predicts the alcohol concentration more accurately than the other joint prediction methods. In addition, the method in our paper provides evidences for setting the ratio of raw materials and proper temperature through numerical analysis. |
URI: | https://bura.brunel.ac.uk/handle/2438/23761 |
DOI: | https://doi.org/10.1109/TII.2021.3106590 |
ISSN: | 1551-3203 |
Other Identifiers: | 9520292 |
Appears in Collections: | Dept of Electronic and Electrical Engineering Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | 12.6 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License