Deeppipe: Theory-guided LSTM method for monitoring pressure after multi-product pipeline shutdown

Zheng, Jianqin; Du, Ji-Xiang; Liang, Yongtu; Wang, Chang; Liao, Qi; Zhang, Haoran

doi:10.1016/j.psep.2021.09.046

Cited by 30 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Long-Short Term Memory (LSTM) Neural Network model is a recurrent neural network architecture (Hochreiter et al, 1997), which was originally designed to make up for the shortcoming of simple RNN models for long-term dependency mining, and was later widely used in applications such as the eld of economic and nancial forecasting (Katsuki et al, 2021). The empirical results (Dey et al, 2021;Zheng et al, 2021) show that the LSTM Neural Network model has higher prediction accuracy than other econometric models. Therefore, the introduction of the LSTM Neural Network model into the prediction of China's industrial carbon emissions can strengthen the identi cation of nonlinear laws in carbon emissions data, and can also be compared with the prediction results of the Monte Carlo simulation method.…”

Section: Prediction Of Carbon Emissionsmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of China's Industrial Carbon Peak: Based on GDIM-MC Model and LSTM-NN Model

Wen

Nie

2022

Preprint

View full text Add to dashboard Cite

The industrial sector is the key area for China to achieve the carbon peaking goals, as it accounts for more than 65% and 70% of the national total energy consumption and carbon emissions. However, the discussion on the time and route of carbon peak in China in the existing literature is still quite different. In this study, we establish three scenarios and comprehensively used Monte Carlo simulation and LSTM Neural Network model to predict the evolution trends of China's industrial carbon emissions during 2020–2030. Firstly, the decomposition results of the Generalized Divisia Index Method shows that fixed assets investment is the most important factor for promoting and carbon intensity of investment is the key for reducing carbon emissions. Then, basing on the Monte Carlo dynamic simulation, we could draw the three kinds of carbon emissions route that it will peak in 2031 in the Baseline scenario, in the Green Development scenario (environmental policy improvement) and Technological Breakthrough scenario (green technology progress) will peak in 2027 and 2025, and under the LSTM Neural Network model, peak time will occur in 2028. Comparing the results of above predictions, China's industrial carbon emissions could peak by 2030(in GD scenario, 2027; TB scenario, 2025). Finally, we discuss the path of China's industrial carbon emissions reduction and provide a reference for the rational formulation of low-carbon regulatory policies in the future and the realization of sustainable development.

show abstract

Section: Prediction Of Carbon Emissionsmentioning

confidence: 99%

“…( 14) shows its value, is the weight matrix, and is the bias. At the same time, new state information can be obtained by formula (15), where is the weight matrix and is the bias. Therefore, the current learning result state can be obtained by formula ( 16):…”

Section: Lstm Neural Network Modelmentioning

confidence: 99%

Prediction of China's Industrial Carbon Peak: Based on GDIM-MC Model and LSTM-NN Model

Wen

Nie

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The design and use of pipeline transportation system should be combined with the actual situation of refined oil transportation in this area, and the primary and secondary costs of refined oil transportation should be clear. Based on the trial operation data of various flow schemes, a set of practical pipeline transportation scheduling and operation model should be established [5][6].…”

Section: Refined Oil Transportation Structurementioning

confidence: 99%

Establishment of General Oil Pipeline Scheduling Model and Research on Interface Tracking Calculation Method

Shen,

Xu,

Song

et al. 2024

E3S Web Conf.

View full text Add to dashboard Cite

In order to understand the establishment of oil pipeline scheduling model and interface tracking calculation method, a research on the establishment of a universal product oil pipeline scheduling model and interface tracking calculation method has been proposed. Establish an automatic formulation and optimization model for the scheduling plan of finished oil pipelines with the objective of minimizing the consumption cost of the entire pump unit. The model mainly adopts a centralized distribution method, considering the hydraulic constraints of the pipeline, and adopts a genetic algorithm to optimize and solve the model. This article provides a detailed introduction to the encoding method of genetic algorithm for optimizing the scheduling plan of finished oil pipelines, the selection of main operators in the algorithm, the establishment of fitness functions, and the introduction of penalty functions. Based on the established mathematical model, an automatic programming and optimization program for product oil pipeline scheduling plan was developed using C language in Windows 7 environment. Secondly, through practical applications, the actual pipeline operation data is basically consistent with the software calculation results, with an error of no more than 5%; As the running time changes, the pump cost fluctuates greatly; Using a larger throughput can reduce the amount of mixed oil; Therefore, this mathematical model can better meet the actual needs of pipeline operation, facilitate the rapid identification of the most sensitive parameter indicators, and adjust the scheduling plan in a timely manner, reduce operational economic losses, and improve the efficiency of product oil pipeline scheduling and operation.

show abstract

“…In recent years, LSTM architecture and its variants have been well applied in time series prediction [17][18][19][20][21][22][23]. Miao K-C [24] proposed a new LSTM framework for short-term fog prediction, which consists of LSTM network and fully connected layers.…”

Section: Related Workmentioning

confidence: 99%

A multi-task prediction method for acid concentration based on attention-CLSTM

Zhu

Liu

Cao

et al. 2022

Preprint

View full text Add to dashboard Cite

The accurate measurement of acid concentration, including hydrogen chloride (HCl) and ferrous chloride concentrations (FeCl2), is a critical part of ensuring the quality of strip steel pickling. In this study, a multi-task attention convolutional long short-term memory (MACL) neural network model was proposed to predict hydrogen ion and ferrous ion concentrations simultaneously. Firstly, in order to extract significant information from the input sequence, an attention mechanism was added to the model to calculate the correlation between the input features and the acid concentration at each time step. Next, multi-task learning explores the connections between the two tasks and exploits hidden constraints to improve prediction accuracy. Finally, deep features were extracted through convolutional long short-term memory (CLSTM) neural network, and the acid concentration was predicted. The proposed MACL model was compared with other popular prediction models. The experimental results show that proposed MACL model generally outperforms other models, indicating that proposed model has excellent predictive performance and effectiveness.

show abstract

Deeppipe: Theory-guided LSTM method for monitoring pressure after multi-product pipeline shutdown

Cited by 30 publications

References 30 publications

Prediction of China's Industrial Carbon Peak: Based on GDIM-MC Model and LSTM-NN Model

Prediction of China's Industrial Carbon Peak: Based on GDIM-MC Model and LSTM-NN Model

Establishment of General Oil Pipeline Scheduling Model and Research on Interface Tracking Calculation Method

A multi-task prediction method for acid concentration based on attention-CLSTM

Contact Info

Product

Resources

About