Transformer–Gate Recurrent Unit-Based Hourly Purified Natural Gas Prediction Algorithm

• Published in: Processes Vol. 13; no. 1; p. 116
• Main Authors: Su, Chang, Huang, Jingcai, Dong, Shasha, He, Yuqi, Li, Ji, Hu, Luyao, Liu, Xiao, Liao, Yong
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2025
• Subjects: Accuracy; Algorithms; Automation; Back propagation; Carbon dioxide; Carbon dioxide removal; Clean energy; Combustion; Computational linguistics; Data integration; Datasets; Electric transformers; Energy consumption; Energy sources; Environmental impact; Forecasting; Gas industry; Gases; Hydrocarbons; Impurities; Industrial development; International economic relations; Language processing; Machine learning; Natural gas; Natural language interfaces; Natural language processing; Neural networks; Nitrogen oxide; Nitrogen oxides; Prediction models; Predictions; Raw materials; Recurrent neural networks; Sulfur compounds; Sulfur dioxide; Sustainable development; Time series; Trends; New York; United States; China
• ISSN: 2227-9717; 2227-9717
• DOI: 10.3390/pr13010116

With the rapid development of industrial automation and intelligence, the consumption of resources and the environmental impact of production processes cannot today be ignored. Today, natural gas, as a commonly used energy source, produces significantly lower emissions of carbon dioxide, sulphur dioxide, and nitrogen oxides from combustion than coal and oil, and can be further purified to remove the small amount of impurities it contains, such as sulphur compounds. Therefore, purified natural gas (hereinafter referred to as purified gas), as a clean energy source, plays an important role in realising sustainable development. At the same time, It becomes more and more important to dispatch purified gas resources reasonably and accurately, and the paramount factor is that the load of purified gas needs to be predicted accurately. Therefore, this paper proposes a Transformer–GRU-based hourly prediction model for purified gas. The model uses the Transformer model for data fusion and feature extraction, and then combines the time series processing capability of the Gate Recurrent Unit (GRU) model to capture long-term dependencies and short-term dynamic changes in time series data. In this paper, the purified gas load data of Chongqing Municipality in 2020 was first preprocessed, and then divided into daily and hourly load datasets according to the measurement step. Meanwhile, considering the influence of temperature factor, the experimental dataset is subdivided according to whether it includes temperature data or not, and then the Transformer–GRU model was built for prediction, respectively. The results show that, compared with the Dual-Stage Attention-Based Recurrent Neural Network (DA-RNN) and the Transformer and GRU models alone, the Transformer–GRU model exhibits good performance in terms of the coefficient of determination, the average absolute percentage error, and mean square error, which can well meet the requirement of hourly prediction accuracy and has greater application value.