Research on time series prediction of multi-process based on deep learning
Abstract Aiming at the problem of data fluctuation in multi-process production, a Soft Update Dueling Double Deep Q-learning (SU-D3QN) network combined with soft update strategy is proposed. Based on this, a time series combination forecasting model SU-D3QN-G is proposed. Firstly, based on productio...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-02-01
|
Series: | Scientific Reports |
Subjects: | |
Online Access: | https://doi.org/10.1038/s41598-024-53762-1 |
_version_ | 1797274600374009856 |
---|---|
author | Huali Zheng Yu Cao Dong Sun Mingjun Wang Binglong Yan Chunming Ye |
author_facet | Huali Zheng Yu Cao Dong Sun Mingjun Wang Binglong Yan Chunming Ye |
author_sort | Huali Zheng |
collection | DOAJ |
description | Abstract Aiming at the problem of data fluctuation in multi-process production, a Soft Update Dueling Double Deep Q-learning (SU-D3QN) network combined with soft update strategy is proposed. Based on this, a time series combination forecasting model SU-D3QN-G is proposed. Firstly, based on production data, Gate Recurrent Unit (GRU) is used for prediction. Secondly, based on the model, SU-D3QN algorithm is used to learn and add bias to it, and the prediction results of GRU are corrected, so that the prediction value of each time node fits in the direction of reducing the absolute error. Thirdly, experiments were carried out on the dataset of a company. The data sets of four indicators, namely, the outlet temperature of drying silk, the loose moisture return water, the outlet temperature of feeding leaves and the inlet water of leaf silk warming and humidification, are selected, and more than 1000 real production data are divided into training set, inspection set and test set according to the ratio of 6:2:2. The experimental results show that the SU-D3QN-G combined time series prediction model has a great improvement compared with GRU, LSTM and ARIMA, and the MSE index is reduced by 0.846–23.930%, 5.132–36.920% and 10.606–70.714%, respectively. The RMSE index is reduced by 0.605–10.118%, 2.484–14.542% and 5.314–30.659%. The MAE index is reduced by 3.078–15.678%, 7.94–15.974% and 6.860–49.820%. The MAPE index is reduced by 3.098–15.700%, 7.98–16.395% and 7.143–50.000%. |
first_indexed | 2024-03-07T15:00:40Z |
format | Article |
id | doaj.art-abef61c95c9a49439695e4ef9cc2175f |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-03-07T15:00:40Z |
publishDate | 2024-02-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-abef61c95c9a49439695e4ef9cc2175f2024-03-05T19:10:16ZengNature PortfolioScientific Reports2045-23222024-02-0114111410.1038/s41598-024-53762-1Research on time series prediction of multi-process based on deep learningHuali Zheng0Yu Cao1Dong Sun2Mingjun Wang3Binglong Yan4Chunming Ye5China Tobacco Zhejiang Industry Co., LTDBusiness School, University of Shanghai for Science and TechnologyChina Tobacco Zhejiang Industry Co., LTDChina Tobacco Zhejiang Industry Co., LTDBusiness School, University of Shanghai for Science and TechnologyBusiness School, University of Shanghai for Science and TechnologyAbstract Aiming at the problem of data fluctuation in multi-process production, a Soft Update Dueling Double Deep Q-learning (SU-D3QN) network combined with soft update strategy is proposed. Based on this, a time series combination forecasting model SU-D3QN-G is proposed. Firstly, based on production data, Gate Recurrent Unit (GRU) is used for prediction. Secondly, based on the model, SU-D3QN algorithm is used to learn and add bias to it, and the prediction results of GRU are corrected, so that the prediction value of each time node fits in the direction of reducing the absolute error. Thirdly, experiments were carried out on the dataset of a company. The data sets of four indicators, namely, the outlet temperature of drying silk, the loose moisture return water, the outlet temperature of feeding leaves and the inlet water of leaf silk warming and humidification, are selected, and more than 1000 real production data are divided into training set, inspection set and test set according to the ratio of 6:2:2. The experimental results show that the SU-D3QN-G combined time series prediction model has a great improvement compared with GRU, LSTM and ARIMA, and the MSE index is reduced by 0.846–23.930%, 5.132–36.920% and 10.606–70.714%, respectively. The RMSE index is reduced by 0.605–10.118%, 2.484–14.542% and 5.314–30.659%. The MAE index is reduced by 3.078–15.678%, 7.94–15.974% and 6.860–49.820%. The MAPE index is reduced by 3.098–15.700%, 7.98–16.395% and 7.143–50.000%.https://doi.org/10.1038/s41598-024-53762-1Deep reinforcement learningCombinational predictionD3QN algorithmNeural networkTime series prediction |
spellingShingle | Huali Zheng Yu Cao Dong Sun Mingjun Wang Binglong Yan Chunming Ye Research on time series prediction of multi-process based on deep learning Scientific Reports Deep reinforcement learning Combinational prediction D3QN algorithm Neural network Time series prediction |
title | Research on time series prediction of multi-process based on deep learning |
title_full | Research on time series prediction of multi-process based on deep learning |
title_fullStr | Research on time series prediction of multi-process based on deep learning |
title_full_unstemmed | Research on time series prediction of multi-process based on deep learning |
title_short | Research on time series prediction of multi-process based on deep learning |
title_sort | research on time series prediction of multi process based on deep learning |
topic | Deep reinforcement learning Combinational prediction D3QN algorithm Neural network Time series prediction |
url | https://doi.org/10.1038/s41598-024-53762-1 |
work_keys_str_mv | AT hualizheng researchontimeseriespredictionofmultiprocessbasedondeeplearning AT yucao researchontimeseriespredictionofmultiprocessbasedondeeplearning AT dongsun researchontimeseriespredictionofmultiprocessbasedondeeplearning AT mingjunwang researchontimeseriespredictionofmultiprocessbasedondeeplearning AT binglongyan researchontimeseriespredictionofmultiprocessbasedondeeplearning AT chunmingye researchontimeseriespredictionofmultiprocessbasedondeeplearning |